course-export

---
name: course-export
description: |
  Export course content to an LMS. Generates IMS Common Cartridge files (.imscc) for
  Canvas, Blackboard, Moodle, and D2L, a SCORM 1.2 package, or pushes directly to Canvas
  through the REST API. Reads the /idstack:course-builder output and the idstack
  manifest. Use when asked to export, package, upload, or publish a course to an LMS or
  to Canvas.
  Framework phase: ADDIE Implement. (idstack)
allowed-tools:
  - Bash
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - AskUserQuestion
  - WebFetch
---
<!-- AUTO-GENERATED from SKILL.md.tmpl -- do not edit directly -->
<!-- Edit the .tmpl file instead. Regenerate: scripts/idstack-gen-skills -->


## Preamble: Interaction Conventions

idstack runs in Claude Code. Skill bodies name these tools:

- **AskUserQuestion** — when a skill says "ask via AskUserQuestion" or "using AskUserQuestion",
  present a single multiple-choice question (e.g., "Which of these best describes X?")
  and stop, waiting for the user's answer before proceeding. Ask **one** question at a time,
  never batch. This maps to the `AskUserQuestion` tool. The tool takes **2 to 4 options**
  per question and adds an "Other" option itself, so do not add "Other". When there are
  more than 4 choices, write them as a numbered list in chat and ask the user to type a
  number. When the answer is free text (a name, a URL, a file path, a description), ask
  in plain chat and stop for the answer.
- **Agent (sub-agents)** — four skills start sub-agents with the `Agent` tool.
  accessibility-review and course-quality-review run their reviews in parallel. red-team
  starts one orchestrator, which runs its five dimensions. course-builder
  starts one agent that does the alignment review.
  The written-out steps after each dispatch define the work. If a sub-agent fails or
  returns nothing, accessibility-review and course-quality-review run its steps
  themselves, in sequence. course-builder skips the alignment review and records that in
  the Limitations. red-team tells the user and stops if the orchestrator returns no valid
  findings file. A sub-agent cannot start its own
  sub-agents, so the red-team orchestrator runs its five dimensions in sequence when it
  cannot dispatch them.
- **Skill (cross-skill invocation)** — used by `/idstack:pipeline`, which invokes each
  child skill in-process through the `Skill` tool. `/idstack:start` also uses it to start
  the first skill for the user.
- **Skill invocation syntax in user-facing text** — every skill is invoked as
  `/idstack:<name>`. Always write the namespaced form: a bare `/<name>` is not a valid
  command. This applies in reports, manifests, and AskUserQuestion options as much as in
  chat output.

## Preamble: Writing Standard (ASD-STE100)

All text that idstack writes for a person must obey the rules in this section. This
includes chat text, AskUserQuestion questions and options, reports, the course
dashboard, course content for learners, and export packages. `scripts/idstack-ste-check`
reads the word list between the two `ste-core` markers. `scripts/idstack-gen-skills` writes
`extension/shared/ste-rules.js` from the text between the markers.

The rules also apply to the text that idstack writes in `.idstack/project.json` and in
learnings, for example finding text and recommendations. Other skills use this text in
their output. The checker does not read these files. Do not change text that comes from
the course. Do not change JSON keys or the values that a script or a skill reads.

<!-- ste-core:begin -->
Writing standard: ASD-STE100 Simplified Technical English (STE)

This summary uses the ASD-STE100 writing rules. ASD does not endorse idstack. This summary does not replace the ASD-STE100 standard.

Use these rules only for text in English. If the text is not in English, do not use these rules.

Words:
- Use one word for one meaning. Use the same term for the same item in all of the text.
- Use short words that are easy to understand. Do not use the words in the first column of the word list.
- Use the technical nouns and technical verbs of instructional design when no simple word has the same meaning. Examples of technical nouns are learning objective, ILO, rubric, criterion, formative assessment, scaffold, cognitive load, meta-analysis, evidence tier, finding and severity.
- The Bloom's taxonomy verbs are technical verbs. Examples are remember, understand, apply, analyze, evaluate, create, assess, critique, demonstrate, design and implement. Use them in learning objectives and in text about Bloom's levels.
- Software verbs are technical verbs. Examples are run, click, open, save, install and update.
- Do not use a technical noun as a verb.
- Do not use contractions. Write "do not", not "don't".
- Do not use Latin abbreviations. Write "for example", not "e.g.".

Verbs:
- Use the active voice. In a description, use the passive voice only when you do not know who or what does the work.
- Use only the simple tenses. Write "writes", "wrote" or "will write". Do not write "has written", "had written" or "is writing".
- Do not use a verb that ends in "-ing". You can use an "-ing" word only in a technical noun, for example "learning objective".

Sentences:
- Write one topic in each sentence.
- An instruction has a maximum of 20 words. A description has a maximum of 25 words.
- Do not remove words, for example "the", "a" and "is", to make a sentence shorter.
- A noun cluster has a maximum of three nouns.
- Do not use semicolons. Write two sentences.
- Use a vertical list for text that has many parts.

Instructions and descriptions:
- Write an instruction as a command. Write one instruction in each sentence. Give a number to each step.
- If the reader must know a condition first, write the condition first. Example: "If the course has no rubric, add a rubric."
- Do not write commands in a description. A paragraph has one topic and a maximum of six sentences.

Recommendations:
- First show the problem that idstack found. Then show the evidence. Then give the recommendation.
- In a description, write a recommendation as "idstack recommends that you ..." or as "You can ...".
- In a numbered list of steps, write each step as a command.
- Do not use "consider", "may", "should" or "suggest".

Text that you do not change:
- Do not change a quotation from a course, a person, a standard or a different software tool. Put each quotation in quotation marks. A new version of a text is not a quotation. Write it with these rules.
- Do not change code, file names, commands, URLs, citations, for example [Domain-N] [T1], or the names of products and standards.

Word list. Do not use the word in the first column. Use the word in the second column.

| Do not use | Use | Note |
|---|---|---|
| "utilize" | "use" | |
| "ensure" | "make sure" | |
| "verify" | "make sure" | |
| "confirm" | "make sure" | |
| "commence" | "start" | |
| "begin" | "start" | |
| "initiate" | "start" | |
| "terminate" | "stop" | |
| "prior to" | "before" | |
| "in order to" | "to" | |
| "assist" | "help" | |
| "facilitate" | "help" | |
| "obtain" | "get" | |
| "achieve" | "get" | |
| "require" | "necessary" | |
| "indicate" | "show" | |
| "appear" | "show" | |
| "consider" | "idstack recommends that you" or "think about" | |
| "suggest" | "recommend" | |
| "suggestion" | "recommendation" | |
| "may" | "can" | lowercase only |
| "might" | "can" | |
| "should" | "must" or "idstack recommends that you" | |
| "would" | "can" | |
| "shall" | "must" | |
| "perform" | "do" | |
| "accomplish" | "do" | |
| "additional" | "more" | |
| "numerous" | "many" | |
| "enough" | "sufficient" | |
| "provide" | "give" | |
| "allow" | "let" | |
| "choose" | "select" | |
| "determine" | "find" | |
| "locate" | "find" | |
| "modify" | "change" | |
| "attempt" | "try" | |
| "therefore" | "thus" | |
| "however" | "but" | |
| "whether" | "if" | |
| "via" | "through" | |
| "upon" | "on" | |
| "such as" | "for example" | |
| "e.g." | "for example" | |
| "i.e." | "that is" | |
| "etc." | (write the full list) | |
| "please" | (remove the word) | |
<!-- ste-core:end -->

How to use the standard:

1. If the conversation or the course is not in English, do not run the checker.
2. When you write a file for a person, run `scripts/idstack-ste-check` on it at the step that the skill shows.
3. If the checker shows problems, write each sentence that it shows again. Then write the file again and run the checker again.
4. Run the checker a maximum of three times. If problems stay after the third time, tell the user which lines have problems.
5. If the output is `STE_CHECK_UNAVAILABLE`, python3 is not available. Continue the skill. Tell the user one time that the check did not run.
6. If the output starts with `STE_CHECK_MISSING:`, the idstack install at the path after the token has no checker. Continue the skill. Tell the user one time that the check did not run. Give the user the path and tell the user to update idstack. If the path is empty, tell the user that idstack did not find its install.
7. If the checker shows an error, continue the skill. Tell the user one time which file the checker did not examine.

The checker finds only some problems: long sentences, long paragraphs, semicolons,
contractions, "has been" verbs and the words in the word list. Apply all of the rules
when you write. The verbosity and experience settings change how much you write. They do
not change these rules.

Identify text from a different source for the checker:
- In HTML, put a short quotation in `<q>` and a long quotation in `<blockquote>`. If a full list item or table cell is a quotation, add `data-ste="quoted"` to that element.
- In Markdown, put a long quotation on lines that start with `> `. Put a short quotation in quotation marks.
- The name of a standard or a principle can have a word from the word list. Identify that name as a short quotation. Example: `<q>3.3.3 Error Suggestion</q>`.
- The checker counts each quotation, citation, code span and placeholder as one word.
  A <placeholder> that is not in backticks counts as no word.

When a skill sends work to a sub-agent, put a copy of this section in the sub-agent
prompt. The sub-agent cannot see this preamble.

Example sentences in a skill show the content of a message. Write them in STE when you
use them.

## Preamble: Project Manifest

Before starting, check for an existing project manifest.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
[ -n "$_IDSTACK" ] || echo "IDSTACK_NOT_FOUND"
if [ -f ".idstack/project.json" ]; then
  echo "MANIFEST_EXISTS"
  "$_IDSTACK/scripts/idstack-migrate" .idstack/project.json 2>&1 || cat .idstack/project.json
else
  echo "NO_MANIFEST"
fi
```

**If MANIFEST_EXISTS:**
- Read the manifest. If the JSON is malformed, report the specific parse error to the
  user, offer to fix it, and STOP until it is valid. Never silently overwrite corrupt JSON.
- Preserve all existing sections when writing back.

**If NO_MANIFEST:**
- This skill will create or update the manifest during its workflow.

**If IDSTACK_NOT_FOUND:** Tell the user: "idstack cannot find its files. Install
idstack again with these two commands in a terminal:
`claude plugin uninstall idstack@idstack` and
`claude plugin install idstack@idstack`. Then start a new session." STOP.

**If the output has a `NEWER_SCHEMA` line:** A newer idstack wrote this manifest.
Tell the user: "A newer version of idstack wrote this course. Update idstack
before you continue. This version cannot save to this course." STOP.

**When you save to the manifest:** A skill saves its results with
`scripts/idstack-manifest-merge`. If the merge command shows an error, or its
exit status is not 0, show the error to the user and STOP. Do not tell the user
that idstack saved the results. Do not write `.idstack/project.json` with the
Write or Edit tool.

## Preamble: Preferences

```bash
if [ -f ".idstack/project.json" ] && command -v python3 &>/dev/null; then
  python3 -c "
import json, sys
try:
    data = json.load(open('.idstack/project.json'))
    prefs = data.get('preferences', {})
    v = prefs.get('verbosity', 'normal')
    if v != 'normal':
        print(f'VERBOSITY:{v}')
except: pass
" 2>/dev/null || true
fi
```

**If VERBOSITY:concise:** Keep explanations brief. Do not cite evidence in chat prose.
Always cite evidence in Step Review tables and in reports.
**If VERBOSITY:detailed:** Include full evidence citations, alternative approaches
considered, and rationale for each recommendation.
**If VERBOSITY:normal or not shown:** Default behavior — cite evidence tiers inline,
explain key decisions, skip exhaustive alternatives.

## Preamble: Designer Profile

```bash
_PROFILE="$HOME/.idstack/profile.yaml"
if [ -f "$_PROFILE" ]; then
  # Simple YAML parsing for experience_level (no dependency needed)
  _EXP=$(grep -E '^experience_level:' "$_PROFILE" 2>/dev/null | sed 's/experience_level:[[:space:]]*//' | tr -d '"' | tr -d "'")
  [ -n "$_EXP" ] && echo "EXPERIENCE:$_EXP"
else
  echo "NO_PROFILE"
fi
```

**If EXPERIENCE:novice:** Provide more context for recommendations. Explain WHY each
step matters, not just what to do. Define jargon on first use. Offer examples.
**If EXPERIENCE:intermediate:** Standard explanations. Assume familiarity with
instructional design concepts but explain idstack-specific patterns.
**If EXPERIENCE:expert:** Be concise. Skip basic explanations. Focus on evidence
tiers, edge cases, and advanced considerations. Trust the user's domain knowledge.
**If NO_PROFILE:** On first run, after the main workflow is underway (not before),
mention: "Note: To change how much information idstack gives, type `/idstack:start` and
select your experience level."

## Preamble: Report Links

A skill that writes a report runs a block that prints a `Report path:` line.
The line gives the path of the Markdown report, relative to the course folder.
`/idstack:pipeline` and `/idstack:start` print a `Dashboard path:` line for the
course dashboard.

When you tell the user about a report or the dashboard, put the path from that
line in a Markdown link. Use the same path as the link text. For example:

[.idstack/exports/bio-101/course-import.md](.idstack/exports/bio-101/course-import.md)

Do not change the path to a full path, and do not put angle brackets around it.
The course slug has no spaces, so the relative path always makes a link that
works. In the Claude desktop app, the user clicks the link to open the report.
Give only a path from a `Report path:` or `Dashboard path:` line, or a path that
a sub-agent returns. Do not make up a path. If the skill stopped before it wrote
the report, do not give the path.

## Preamble: Step Review

Only the skills that write a report do a Step Review. After each step that makes
an output, idstack adds the output to the report as a draft section with a table.
The user reads the section in the report file, not in the chat. The user approves
the section, and idstack removes the draft mark. If the session stops, the report
keeps each section, and a section that the user did not approve keeps its draft
mark.

The skill tells you where to do a Step Review with a `**Step review:**` line.
That line gives the section heading and the table columns.

**The shape of a section**

- Start the section with a `## <Heading>` line. Then write the table.
- The first column is `ID`. Give each row an ID that does not change, for
  example `T-1` or `ILO-2`.
- The last two columns are `Justification` and `Evidence`.
- In the Justification cell, write one sentence. Tell why the row is correct for
  this course. Use the evidence from the research.
- In the Evidence cell, write only the citation, for example
  `[Assessment-8] [T1]`. Use a code from the "Evidence list:" file. Use the tier
  that the file gives for that code.
- If you cannot cite a row, do not put it in the table. Put the text in the
  Limitations section.
- These fact sections have no Justification or Evidence columns: Project context,
  Course information, Imported structure, Readiness, Export contents and
  Generated artifacts.
- A findings table has these columns:
  `ID | Severity | What we saw | Recommendation | Justification | Evidence`.
  Write the severity as `critical`, `warning` or `info`. Put the `critical` rows
  first, then `warning`, then `info`. Do not write `### Finding` blocks.
  idstack writes them from the rows when it adds the section.

**The procedure**

1. Write the section to `.idstack/.report-section.<skill>.md` with the Write tool.
   In this name and in each command below, `<skill>` is the name of this skill
   (for example `red-team`).
2. Run the check command:

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" check .idstack/.report-section.<skill>.md; fi
```

3. If the output shows problems, correct the draft. Then do step 2 again. Do the
   check a maximum of three times. If a row still has a problem, remove the row
   and put its text in the Limitations section.
4. Run the append command. It adds the section to the report as a draft. In
   this command, replace `<path>` with the path from the "Report path:" line.
   Then run the command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" append "<path>" .idstack/.report-section.<skill>.md; fi
```

5. Tell the user about the section in a maximum of three short lines:
   - The section name and the number of rows. For findings, give the number of
     each severity.
   - The most important row, in one sentence.
   - This line, with the path from the "Report path:" line of the append
     output in place of `<path>`: `Read the draft in [<path>](<path>).` Write
     the link exactly in this form. Do not write the name of the report as
     text only. The user clicks the link to open the report.
   Do not show the table in the chat. Do not put the table, a row or a citation
   in the question or in its options.
6. Ask with AskUserQuestion: "Do you approve the <section name> section?" Give
   these three options. Each option must have its description. Do not add a
   preview.
   - "Approve", with the description "Keep this section as it is."
   - "Change a row", with the description "Tell me the row ID and the change."
   - "Remove a row", with the description "Tell me the row ID to remove."
7. If the user selects "Change a row" or "Remove a row", ask in chat for the row
   ID and the change. Change the draft file. Then go to step 2. The append
   command replaces the section in the report.
8. If the user selects "Approve", run the approve command. In this command,
   replace `<path>` with the path from the "Report path:" line. Then run the
   command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" approve "<path>" --draft .idstack/.report-section.<skill>.md; fi
```

9. Go to the next step only if the output starts with `SECTION_APPROVED`.

**Rules**

- Ask one question for each Step Review. For the last draft, ask one question
  for its sections together: "Do you approve the last sections of the report?"
  This question replaces the old approval question of the step. Questions that collect data from the user stay.
- If a later step changes the data in an approved section, do the Step Review of
  that section again. Use the same heading. idstack replaces the old section.
- Use only the approved rows in the manifest. Calculate each score from the
  approved rows.
- If a step has no rows, do not do its Step Review. For example, if idstack
  found no problems, do not write a Findings section. Tell the result in the
  Summary. In the last draft, do not write a Top recommendations section if it
  has no rows.
- If the user removes a finding, add this sentence to Limitations: "You removed
  finding `<ID>`."
- The last Step Review has one draft with four sections: `## Summary`,
  `## Top recommendations`, `## Limitations` and `## Next steps`. The Summary,
  Limitations and Next steps sections are text, with no table. The Top
  recommendations table has the columns `ID | Action | Justification | Evidence`.
- After the user approves the last section, run the finish command. In this
  command, replace `<path>` with the path from the "Report path:" line. Then run
  the command.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-report-section" ]; then echo "REPORT_SECTION_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "REPORT_SECTION_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-report-section" finish "<path>"; fi
```

- If the skill stops after the report starts, for any reason, end the report
  first. Do the last Step Review. In the Summary, tell why the skill stopped. Do
  not write a Top recommendations section. Then run the finish command with
  `--stopped` after `finish "<path>"`. Do not do a Step Review for a score section
  that has no data: `--stopped` writes a note in it. This includes an error, a
  missing file, and a user who stops the skill.
- If the finish command shows a section with no text, do the Step Review for that
  section. If it shows a draft section, ask the user to approve that section.
  Then run the finish command again.
- The verbosity and experience settings do not change the tables or the chat
  note of three lines. Each table always has its citations.
- If the output of a command starts with `REPORT_WRITE_FAILED:`, idstack cannot
  write the report. Do not change the draft. Show the line to the user and STOP.
- If the output starts with `REPORT_SECTION_MISSING:` or is
  `REPORT_SECTION_UNAVAILABLE`, do the Step Reviews without the commands. If the
  report does not exist, write its header, Summary and footer from the "Report
  template:" file with the Write tool. Add each section to the report with the
  Edit tool, with the line `**Draft:** this section waits for your approval.`
  under its heading. Remove that line when the user approves the section. Tell the user one time that idstack did not check the
  citations.

## Preamble: Context Recovery

Check for session history and learnings from prior runs.

```bash
# Context recovery: timeline + learnings
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
"$_IDSTACK/scripts/idstack-status" --context 2>/dev/null || true
```

**If QUALITY_TREND is shown:** Synthesize a welcome-back message. Example: "Welcome back.
Quality score trend: 62 -> 68 -> 72 over 3 reviews. Last skill: /idstack:learning-objectives."
Keep it to 2-3 sentences. LAST_PRESENCE has the scores of the most recent review only. If a
dimension in it is below 5/10, mention it with its evidence citation.

**If LAST_SKILL is shown but no QUALITY_TREND:** Just mention the last skill run.
Example: "Welcome back. Last session you ran /idstack:course-import."

**If SUGGESTED_NEXT is shown:** Mention the suggested next skill naturally.
Example: "From your progress, the next skill is /idstack:assessment-design."

**If LEARNINGS > 0:** Mention relevant learnings if they apply to this skill's domain.
Example: "Note: this Canvas instance uses a custom rubric format (idstack found this during the import)."

---

**Skill-specific manifest check:** If the manifest `export_metadata` section already has data,
ask the user: "You ran this skill previously. Do you want to update the results or start again?"

# Course Export — IMS Common Cartridge & Canvas API

You are a course export partner. Your job is to take the content generated by
/idstack:course-builder and package it for import into any Learning Management System.
You are the last mile between generated course content and a live course that
students can access.

Three export paths:
1. **IMS Common Cartridge (.imscc)** — Universal format. Works with every major
   LMS: Canvas, Blackboard, Moodle, D2L/Brightspace. You generate a standards-
   compliant package file that the instructional designer imports through their
   LMS admin interface. Zero API credentials needed.
2. **Canvas REST API** — Canvas-specific, richest integration. Pushes modules,
   pages, assignments, and discussions directly to a Canvas course instance.
   Requires an access token. Results appear immediately in Canvas.
3. **SCORM 1.2 package (.zip)** — Standard e-learning format. You generate a
   SCORM ZIP that the instructional designer uploads to an LMS or a SCORM
   player. Zero API credentials needed.

The output IS the course. You are not generating a spec, a plan, or a description
of what the course should contain. You are generating the actual importable
course content: HTML pages, assignment definitions, quiz questions, and the
manifest that ties them together. The instructional designer should be able to
import your output and have a functioning course shell ready for review.

You read from two sources:
- The `.idstack/course-content/` directory, where /idstack:course-builder writes its
  generated files (syllabus, module content, assessments, rubrics)
- The `.idstack/project.json` manifest, which contains the course structure,
  learning objectives, and alignment data from upstream skills

## Evidence Tier Key

Every recommendation includes its evidence tier in brackets:
- [T1] RCTs, meta-analyses with learning outcome measures
- [T2] Quasi-experimental with appropriate controls
- [T3] Systematic reviews (synthesis of mixed evidence)
- [T4] Observational / pre-post without comparison groups
- [T5] Expert opinion, literature reviews, theoretical frameworks

When multiple tiers apply, cite the strongest.

---

## Course Content Inputs

The shared preamble above already ran the manifest existence check
(`MANIFEST_EXISTS` / `NO_MANIFEST`), and the skill-specific manifest check above asked this skill's re-run question.

Before starting the export, verify that generated course content exists:

```bash
if [ -d ".idstack/course-content" ]; then
  echo "CONTENT_EXISTS"
  ls -la .idstack/course-content/
else
  echo "NO_CONTENT"
fi
```

**If NO_MANIFEST or NO_CONTENT:**
Tell the user: "idstack must have generated course content to export. Run `/idstack:course-builder`
first to generate your syllabus, modules, and assessments. The builder reads
your manifest and produces the files I package for your LMS."

**If MANIFEST_EXISTS but no `course_content` section:**
Check whether `.idstack/course-content/` has files. If it does, proceed using
the files directly. If not, nudge for /idstack:course-builder.

---

## Prepare Course Export Folder

Every artifact this skill produces — the Markdown report, the LMS package — lands
under `.idstack/exports/<course-slug>/`, alongside the per-skill reports
produced by the rest of the pipeline. Compute the slug and prepare the folder
now, then reuse `$_EXPORT_DIR` throughout the workflow:

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
# Course-slug-based export folder. Required before any artifact write.
_SLUG=$("$_IDSTACK/scripts/idstack-slugify" --from-manifest 2>/dev/null || echo "untitled-course")
_EXPORT_DIR=".idstack/exports/$_SLUG"
_REPORT_PATH="$_EXPORT_DIR/course-export.md"
mkdir -p "$_EXPORT_DIR"
echo "Report template: $_IDSTACK/templates/report.md.tmpl"
echo "Report rules: $_IDSTACK/templates/report-format.md"
echo "Evidence list: $_IDSTACK/evidence/references.md"
echo "Course export folder: $_EXPORT_DIR"
echo "Report path: $_REPORT_PATH"
if [ -x "$_IDSTACK/scripts/idstack-report-section" ] && command -v python3 >/dev/null 2>&1; then "$_IDSTACK/scripts/idstack-report-section" init "$_REPORT_PATH" --skill course-export --title "Course Export Report"; else echo "REPORT_SECTION_MISSING: $_IDSTACK"; fi
```

Before the first Step Review, use the Read tool on the files from the "Report rules:" and "Evidence list:" lines.

All subsequent paths (`.imscc`, SCORM `.zip`, Markdown report) write into
`$_EXPORT_DIR`, never directly into `.idstack/`. The folder becomes the
canonical, self-describing deliverable. Zip the whole folder to hand to a
stakeholder. If you ran `/idstack:pipeline`, open its `index.md` course
dashboard to navigate.

---

## Pre-Export Readiness Check

Before you start the export, run the readiness dashboard:

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
"$_IDSTACK/scripts/idstack-status" --readiness
```

**Step review:** do the Step Review in the preamble. Section: `## Readiness`. Columns: `ID | Check | Value | Threshold | Status`.

Write one row for each line of the readiness output. R-1 is the quality review, R-2 is the red team audit, R-3 is the accessibility review and R-4 is the verdict. Copy the values, the thresholds and the status from the output.

If the output is only `No timeline data. Run the pipeline skills first.`, no review has run. Write R-1, R-2 and R-3 with the Value `-`, the Threshold `-` and the Status `NOT RUN`. Write R-4 with the verdict `INCOMPLETE (run /idstack:course-quality-review, /idstack:red-team, /idstack:accessibility-review)`.

The verdict changes the question of the Step Review:

- **READY TO EXPORT:** Ask the usual question of the Step Review.
- **NOT-READY or INCOMPLETE:** After the append command (step 4 of the Step Review), the Readiness section is in the report as a draft. Ask one question with AskUserQuestion. This question replaces the usual question. Ask: "The readiness check found problems. Do you approve this section and export the course?" The options and their descriptions are "Approve and export" ("Keep this section and make the package"), "Correct the problems first" ("Stop the export now") and "Change a row" ("Tell me the row ID and the change"). If the verdict is INCOMPLETE, write the second option as "Run those skills first".
- If the user selects "Approve and export", run the approve command (step 8 of the Step Review). Continue the export only if the output starts with `SECTION_APPROVED`.
- If the user selects "Change a row", do step 7 of the Step Review. Then ask this question again.
- If the user selects "Correct the problems first" or "Run those skills first", run the approve command of the Step Review for the Readiness section. Then do the last Step Review (see "Generate Export Report"), with its append and approve commands. In the Summary, tell that the export stopped before the package and give the verdict. Do not write a Top recommendations section. Then run the finish command and stop this skill. Tell the user which skills to run, from the verdict line.

The readiness check gives advice only. The user can always export the course.

---

## Writing Standard Check (course content)

If the course content is not in English, do not run this check. Go to "Export Format Selection". If the course content is in English, run the ASD-STE100 checker on it before you make a package or send content to Canvas. This check only shows problems. Do not change the course files. The designer wrote this text or gave approval to it.

```bash
_IDSTACK=""
_idstack_cache_root="$HOME/.claude/plugins/cache/idstack/idstack"
_idstack_cache=""
if [ -d "$_idstack_cache_root" ]; then
  _idstack_v=$(ls "$_idstack_cache_root" 2>/dev/null | sort -t. -k1,1n -k2,2n -k3,3n -k4,4n | tail -1)
  [ -n "$_idstack_v" ] && _idstack_cache="$_idstack_cache_root/$_idstack_v"
fi
_idstack_skill="${CLAUDE_SKILL_DIR}"
[ -n "$_idstack_skill" ] && _idstack_skill="$_idstack_skill/../.."
for _p in "${CLAUDE_PLUGIN_ROOT}" "$_idstack_skill" "${IDSTACK_HOME:-}" "$_idstack_cache"; do
  if [ -n "$_p" ] && [ -d "$_p" ]; then _IDSTACK="${_p%/}"; break; fi
done
if [ ! -x "$_IDSTACK/scripts/idstack-ste-check" ]; then echo "STE_CHECK_MISSING: $_IDSTACK"; elif ! command -v python3 >/dev/null 2>&1; then echo "STE_CHECK_UNAVAILABLE"; else "$_IDSTACK/scripts/idstack-ste-check" ".idstack/course-content"; fi
```

1. If the output is `STE_CHECK_UNAVAILABLE` or starts with `STE_CHECK_MISSING:`, do step 5 or step 6 of "How to use the standard" in the preamble. Continue the export.
2. If the checker shows no problems, continue the export.
3. If the checker shows problems, tell the user only the number of problems and the files with problems. Then use AskUserQuestion with two alternatives: "Continue the export" and "Stop the export to correct the content".
4. If the user selects "Stop the export to correct the content", do the last Step Review (see "Generate Export Report"), with its append and approve commands. In the Summary, tell that the export stopped before the package because the course content has writing problems. Do not write a Top recommendations section. Then run the finish command and stop this skill. Tell the user to correct the files in `.idstack/course-content/` and then run `/idstack:course-export` again.
5. If the checker shows an error, tell the user which files the checker did not read. Then continue with the steps above for the problems that it shows.

The package files (HTML pages, XML files and quiz text) get no file check. When you write text for the package, for example quiz questions, quiz feedback or item titles, obey the "Writing Standard (ASD-STE100)" section of the preamble.

---

## Export Format Selection

Ask the user how they want to export. Use AskUserQuestion:

"How do you want to export your course?"

Options:
- **A) IMS Common Cartridge (.imscc)** — Universal format. Import into Canvas,
  Blackboard, Moodle, D2L. No API credentials needed. Produces a single file
  you upload through your LMS admin interface.
- **B) Canvas API** — Push directly to a Canvas course. Modules, pages,
  assignments, and discussions appear immediately. Requires a Canvas access
  token and course ID.
- **C) SCORM 1.2 package (.zip)** — Standard e-learning format. Works with every
  LMS, every authoring tool, and every corporate training platform. Produces a
  SCORM-compliant ZIP you upload to any LMS or host on any SCORM player.

---

## Export Plan

Do this step after the path reads the course content (A1, B3 or C1). Do it before you write a package file or send a request that changes Canvas.

**Step review:** do the Step Review in the preamble. Section: `## Export plan`. Columns: `ID | Item type | Count | Conversion | Justification | Evidence`.

Write one row for each item type that the selected path exports, with IDs `EP-1`, `EP-2` and so on. In the Conversion cell, write what idstack makes from the Markdown, for example "HTML page", "QTI quiz with elaborated feedback" or "Canvas assignment, not published".

Use these citations. For the syllabus, use `[Online-2] [T4]`. For module pages with their heading structure, use `[Access-1] [T5]`. For assignments with their rubric in the description, use `[Assessment-19] [T1]`. For quizzes with elaborated feedback, use `[Assessment-10] [T1]`. For discussions, use `[Online-18] [T1]`.

Export only the item types in the approved rows. If the user removes a row, do not write files or send Canvas requests for that item type.

---

## Path A: IMS Common Cartridge Export

### A1. Read Course Content Files

Read all files in `.idstack/course-content/`:

```bash
find .idstack/course-content/ -type f | sort
```

Read each file to understand the content structure. /idstack:course-builder writes these files:
- `syllabus.md` — Course syllabus
- `modules/module-01-<slug>.md`, `modules/module-02-<slug>.md`, etc. — Module content pages. A module page for an online or hybrid course also has its discussion prompt, in a `## Discussion Prompt` section.
- `assessments/assessment-01-<slug>.md`, `assessments/assessment-02-<slug>.md`, etc. — Assignment and quiz specs
- `rubrics/rubric-01-<slug>.md`, `rubrics/rubric-02-<slug>.md`, etc. — Rubric definitions

Also read the manifest to get the course title, module structure, and ILO
alignment data. The manifest provides the organizational spine; the content
files provide the body.

Then do the "Export Plan" step. Go to A2 only after the user approves the plan.

### A2. Generate imsmanifest.xml

The manifest XML defines the course structure for the LMS. Generate it following
the IMS Common Cartridge 1.3 specification:

```xml
<?xml version="1.0" encoding="UTF-8"?>
<manifest identifier="idstack-export-{uuid}"
  xmlns="http://www.imsglobal.org/xsd/imsccv1p3/imscp_v1p1"
  xmlns:lom="http://ltsc.ieee.org/xsd/LOM">
  <metadata>
    <schema>IMS Common Cartridge</schema>
    <schemaversion>1.3.0</schemaversion>
    <lom:lom>
      <lom:general>
        <lom:title><lom:string>{course title}</lom:string></lom:title>
      </lom:general>
    </lom:lom>
  </metadata>
  <organizations>
    <organization identifier="org-1" structure="rooted-hierarchy">
      <item identifier="root">
        <!-- One item per module -->
        <item identifier="mod-1" identifierref="res-mod-1">
          <title>{Module 1 Title}</title>
          <!-- Nested items for module content -->
          <item identifier="mod-1-page-1" identifierref="res-mod-1-page-1">
            <title>{Page Title}</title>
          </item>
          <item identifier="mod-1-assign-1" identifierref="res-mod-1-assign-1">
            <title>{Assignment Title}</title>
          </item>
        </item>
        <!-- Repeat for each module -->
      </item>
    </organization>
  </organizations>
  <resources>
    <!-- Web content resources (module pages) -->
    <resource identifier="res-mod-1-page-1" type="webcontent"
              href="modules/mod-1-page-1.html">
      <file href="modules/mod-1-page-1.html"/>
    </resource>
    <!-- Assignment resources -->
    <resource identifier="res-mod-1-assign-1" type="assignment_xmlv1p0"
              href="assignments/assign-1.xml">
      <file href="assignments/assign-1.xml"/>
    </resource>
    <!-- Quiz resources (QTI) -->
    <resource identifier="res-mod-1-quiz-1" type="imsqti_xmlv1p2/imscc_xmlv1p3/assessment"
              href="quizzes/quiz-1.xml">
      <file href="quizzes/quiz-1.xml"/>
    </resource>
    <!-- Discussion resources -->
    <resource identifier="res-mod-1-disc-1" type="imsdt_xmlv1p3"
              href="discussions/disc-1.xml">
      <file href="discussions/disc-1.xml"/>
    </resource>
  </resources>
</manifest>
```

Key rules for manifest generation:
- Every content item in `<organizations>` must have a matching `<resource>` entry
- `identifierref` in organization items must match `identifier` in resources
- Generate a UUID for the manifest identifier (use `uuidgen` or equivalent)
- Use descriptive, slugified identifiers: `mod-1-page-1`, not `item-47`
- Include the syllabus as the first resource in the first module or as a
  standalone item at the root level

### A3. Convert Markdown to HTML

For each `.md` file in course-content, convert to clean HTML suitable for LMS
import. You do this conversion directly — no external tools needed.

**Conversion rules:**
- Convert all markdown formatting: headings, bold, italic, lists, links, tables,
  code blocks, blockquotes
- Wrap in a minimal HTML document structure:

```html
<!DOCTYPE html>
<html>
<head>
  <meta charset="UTF-8">
  <title>{page title}</title>
</head>
<body>
  {converted content}
</body>
</html>
```

- Use inline styles only for essential formatting. Do not reference external
  CSS — it will not transfer to the LMS. Keep styling minimal and semantic.
  The LMS applies its own theme.
- Preserve heading hierarchy: `# ` becomes `<h1>`, `## ` becomes `<h2>`, etc.
- Convert markdown tables to HTML `<table>` elements with basic borders:
  `<table style="border-collapse: collapse; width: 100%;"> ...`
- Convert markdown links to HTML `<a>` tags
- Convert code blocks to `<pre><code>` elements
- Convert images to `<img>` tags (if image files exist in course-content,
  include them in the package)

Save converted HTML files in the export directory structure:
- `modules/mod-{N}-page-{M}.html` for module content pages
- `syllabus.html` for the syllabus

### A4. Generate Assignment XML

For each assessment identified in the course content, generate the appropriate
XML format.

**For essay, project, and upload-type assessments — assignment XML:**

```xml
<?xml version="1.0" encoding="UTF-8"?>
<assignment identifier="assign-{id}"
  xmlns="http://www.imsglobal.org/xsd/imscc_extensions/assignment">
  <title>{title}</title>
  <text texttype="text/html">{description HTML}</text>
  <gradable points_possible="{points}">{grading type}</gradable>
  <submission_formats>
    <format type="online_text_entry"/>
    <format type="online_upload"/>
  </submission_formats>
</assignment>
```

Include rubric criteria in the description HTML if a rubric file exists for the
assessment. Format the rubric as an HTML table within the `<text>` element so
it is visible to both instructors and students after import.

**For quiz-type assessments — QTI XML (IMS Question & Test Interoperability):**

```xml
<?xml version="1.0" encoding="UTF-8"?>
<questestinterop xmlns="http://www.imsglobal.org/xsd/ims_qtiasiv1p2">
  <assessment ident="quiz-{id}" title="{title}">
    <section ident="section-1">
      <!-- Multiple choice question -->
      <item ident="q-1" title="{question title}">
        <presentation>
          <material>
            <mattext texttype="text/html">{question text}</mattext>
          </material>
          <response_lid ident="resp-1" rcardinality="Single">
            <render_choice>
              <response_label ident="opt-a">
                <material>
                  <mattext>{option A text}</mattext>
                </material>
              </response_label>
              <response_label ident="opt-b">
                <material>
                  <mattext>{option B text}</mattext>
                </material>
              </response_label>
              <response_label ident="opt-c">
                <material>
                  <mattext>{option C text}</mattext>
                </material>
              </response_label>
              <response_label ident="opt-d">
                <material>
                  <mattext>{option D text}</mattext>
                </material>
              </response_label>
            </render_choice>
          </response_lid>
        </presentation>
        <resprocessing>
          <outcomes>
            <decvar maxvalue="1" minvalue="0" varname="SCORE" vartype="Decimal"/>
          </outcomes>
          <respcondition continue="No">
            <conditionvar>
              <varequal respident="resp-1">{correct option ident}</varequal>
            </conditionvar>
            <setvar action="Set" varname="SCORE">1</setvar>
            <displayfeedback feedbacktype="Response" linkrefid="correct"/>
          </respcondition>
        </resprocessing>
        <itemfeedback ident="correct">
          <flow_mat>
            <material>
              <mattext texttype="text/html">{feedback explaining why}</mattext>
            </material>
          </flow_mat>
        </itemfeedback>
      </item>
      <!-- Repeat for each question -->
    </section>
  </assessment>
</questestinterop>
```

**Quiz generation notes:**
- Generate questions from the assessment description, rubric criteria, and
  learning objectives mapped in the alignment matrix
- Include elaborated feedback for each question — not just "correct/incorrect"
  but explaining WHY the answer is right. Elaborated feedback produces
  significantly larger learning gains [Assessment-8] [T1]
- Quiz question generation is best-effort. The instructional designer should
  review and edit questions in the LMS after import. Flag this clearly:
  "idstack generated the quiz questions from your assessment specs. Review each
  question in your LMS before you publish the quiz to students."
- Support these question types: multiple choice, true/false, short answer
  (essay type in QTI)

**For discussion-type activities — discussion topic XML:**

```xml
<?xml version="1.0" encoding="UTF-8"?>
<topic xmlns="http://www.imsglobal.org/xsd/imsccv1p3/imsdt_v1p3">
  <title>{title}</title>
  <text texttype="text/html">{discussion prompt HTML}</text>
</topic>
```

### A5. Package as ZIP

Each Bash call runs in a new shell. Thus each block below sets its own paths.
The staging folder is in the course export folder, so the Write tool writes
inside the project.

First, make the staging folder. Replace `<export folder>` with the folder from
the "Course export folder:" line, then run the command:

```bash
_EXPORT_DIR="<export folder>"
_STAGE="$_EXPORT_DIR/.imscc-staging"
rm -rf "$_STAGE"
mkdir -p "$_STAGE/modules" "$_STAGE/assignments" "$_STAGE/quizzes" "$_STAGE/discussions"
echo "Staging folder: $_STAGE"
```

Then write each file into the staging folder with the Write tool:

- `imsmanifest.xml` at the root of the staging folder
- module HTML files in `modules/`
- assignment XML files in `assignments/`
- quiz QTI XML files in `quizzes/`
- discussion XML files in `discussions/`
- `syllabus.html` at the root of the staging folder

Write each file individually. Make sure that each file is correctly formed
before you make the package.

Then make the package. Replace `<export folder>` again, then run the command:

```bash
_EXPORT_DIR="<export folder>"
_STAGE="$_EXPORT_DIR/.imscc-staging"
_OUT="$(cd "$_EXPORT_DIR" && pwd)/course-export.imscc"
[ -f "$_STAGE/imsmanifest.xml" ] || { echo "PACKAGE_FAILED: $_STAGE/imsmanifest.xml is missing"; exit 1; }
rm -f "$_OUT"
( cd "$_STAGE" && zip -qr "$_OUT" . ) || { echo "PACKAGE_FAILED: zip error. The staging folder is still at $_STAGE"; exit 1; }
[ -s "$_OUT" ] || { echo "PACKAGE_FAILED: $_OUT is empty"; exit 1; }
rm -rf "$_STAGE"
echo "Export saved to $_EXPORT_DIR/course-export.imscc"
```

If the output starts with `PACKAGE_FAILED`, tell the user the error. Do not say
that the export is complete.

Do the Step Review of "Export Contents" with one row
for `course-export.imscc` and the status "failed: <error>". Then do the last Step Review (see "Generate Export Report"), with its append and approve commands. In the Summary, tell that the export failed and give the error. Do not write a Top recommendations section. Then run the finish command and stop this skill.

### A6. Verify the Package

Replace `<export folder>` with the folder from the "Course export folder:" line,
then run the command:

```bash
_EXPORT_DIR="<export folder>"
# Verify it's a valid zip
file "$_EXPORT_DIR/course-export.imscc"
# List contents
unzip -l "$_EXPORT_DIR/course-export.imscc"
# Count items
echo "---"
echo "Module pages: $(unzip -l "$_EXPORT_DIR/course-export.imscc" | grep 'modules/[^/]' | wc -l)"
echo "Assignments: $(unzip -l "$_EXPORT_DIR/course-export.imscc" | grep 'assignments/[^/]' | wc -l)"
echo "Quizzes: $(unzip -l "$_EXPORT_DIR/course-export.imscc" | grep 'quizzes/[^/]' | wc -l)"
echo "Discussions: $(unzip -l "$_EXPORT_DIR/course-export.imscc" | grep 'discussions/[^/]' | wc -l)"
```

Do not show this output in the chat. From it, collect the data for the rows of
"Export Contents": the package size and the number of module pages,
assignments, quizzes and discussions. Keep the package path
`.idstack/exports/<course-slug>/course-export.imscc` for the closing message.

---

## Path B: Canvas API Push

### B1. Get Credentials

idstack keeps your Canvas details in `.idstack/canvas.env`. Each Bash call
runs in a new shell, so each API command reads this file again. Your token
does not go into the chat.

Ask the user in plain chat (not AskUserQuestion, because the answers are free
text) for two items:

1. **Canvas URL** — Your institution's Canvas address
   (for example, `https://canvas.university.edu`)
2. **Course ID** — The number in the URL when you open the course
   (for example, `https://canvas.university.edu/courses/12345` → course ID is `12345`)
   Use an existing empty course shell, or create a new course first in Canvas.

Do NOT ask for the access token in the chat. If the user pastes a token in the
chat, tell them to revoke it in Canvas and make a new one.

Replace `<canvas url>` and `<course id>`, then run the command. It keeps a
token that is already in the file:

```bash
umask 077
mkdir -p .idstack
IFS= read -r _URL <<'IDSTACK_CANVAS_URL'
<canvas url>
IDSTACK_CANVAS_URL
IFS= read -r _COURSE <<'IDSTACK_COURSE_ID'
<course id>
IDSTACK_COURSE_ID
case "$_URL" in *\'*) echo "CANVAS_URL_BAD: $_URL"; exit 1 ;; https://*) ;; *) echo "CANVAS_URL_NOT_HTTPS: $_URL"; exit 1 ;; esac
case "$_COURSE" in ''|*[!0-9]*) echo "CANVAS_COURSE_ID_BAD: $_COURSE"; exit 1 ;; esac
_TOKEN_LINE=$(grep '^CANVAS_TOKEN=' .idstack/canvas.env 2>/dev/null || echo "CANVAS_TOKEN=''")
printf "CANVAS_BASE_URL='%s'\nCANVAS_COURSE_ID='%s'\n%s\n" "$_URL" "$_COURSE" "$_TOKEN_LINE" > .idstack/canvas.env
chmod 600 .idstack/canvas.env
[ -s .idstack/.gitignore ] && [ -n "$(tail -c1 .idstack/.gitignore)" ] && echo >> .idstack/.gitignore
grep -qx 'canvas.env' .idstack/.gitignore 2>/dev/null || echo 'canvas.env' >> .idstack/.gitignore
grep -qx 'canvas-push/' .idstack/.gitignore 2>/dev/null || echo 'canvas-push/' >> .idstack/.gitignore
echo "Canvas settings file: $PWD/.idstack/canvas.env"
```

If the command prints one of these codes, tell the user the text. Then ask for
the correct value and run the command again.

- `CANVAS_URL_NOT_HTTPS`: "The Canvas URL must start with `https://`. idstack
  does not send your token on a connection that is not encrypted."
- `CANVAS_URL_BAD`: "The Canvas URL cannot contain a quotation mark. Check the
  address."
- `CANVAS_COURSE_ID_BAD`: "The course ID must be a number. Check the course URL
  in Canvas."

Then tell the user:

"Open `.idstack/canvas.env` in a text editor. Paste your Canvas access token
between the two quotes after `CANVAS_TOKEN=`. Save the file, then tell me
when it is done.

To make a token in Canvas: Account → Settings → Approved Integrations → New
Access Token. Only you can read this file, and `.idstack/.gitignore` stops git
from adding it. When you are done with idstack, you can delete the file or
revoke the token in Canvas."

### B2. Validate Connection

```bash
. ./.idstack/canvas.env || { echo "CANVAS_ENV_MISSING"; exit 1; }
[ -n "$CANVAS_TOKEN" ] || { echo "CANVAS_TOKEN_EMPTY: add the token to .idstack/canvas.env"; exit 1; }
case "$CANVAS_TOKEN" in *'"'*|*'\'*) echo "CANVAS_TOKEN_BAD: the token in .idstack/canvas.env has a quotation mark or a backslash"; exit 1 ;; esac
case "$CANVAS_BASE_URL" in https://*) ;; *) echo "CANVAS_URL_NOT_HTTPS: $CANVAS_BASE_URL"; exit 1 ;; esac
RESPONSE=$(printf 'header = "Authorization: Bearer %s"\nproto = "=https"\n' "$CANVAS_TOKEN" | curl -K - -s --max-time 60 -w "\n%{http_code}" \
  "$CANVAS_BASE_URL/api/v1/users/self" 2>&1)
HTTP_CODE=$(printf '%s\n' "$RESPONSE" | tail -1)
BODY=$(printf '%s\n' "$RESPONSE" | sed '$d')
echo "HTTP: $HTTP_CODE"
printf '%s\n' "$BODY" | head -5
```

Handle errors:
- `CANVAS_URL_NOT_HTTPS`: "The Canvas URL in `.idstack/canvas.env` must start
  with `https://`. Give me the correct address." Then run the settings command again.
- HTTP 401: "Token rejected. Make sure you copied the full token. In Canvas:
  Account → Settings → Approved Integrations → New Access Token."
- HTTP 403: "Access denied. Your token does not have the necessary permissions for
  this course. You must have the Teacher role, the Designer role or a higher role."
- Network error: "idstack cannot connect to Canvas at that URL. Check the address and make
  sure it includes `https://`."

Verify course access:
```bash
. ./.idstack/canvas.env || { echo "CANVAS_ENV_MISSING"; exit 1; }
printf 'header = "Authorization: Bearer %s"\nproto = "=https"\n' "$CANVAS_TOKEN" | curl -K - -s --max-time 60 -w "\n%{http_code}" \
  "$CANVAS_BASE_URL/api/v1/courses/$CANVAS_COURSE_ID" 2>&1
```

- HTTP 404: "Course not found. Check the course ID. You can find it in the URL
  when you open the course in Canvas."
- HTTP 403: "You do not have access to this course. Get the Teacher or Designer
  role from your Canvas admin."

**SECURITY RULE: The token is only in `.idstack/canvas.env`. Use
`$CANVAS_TOKEN` ONLY in the `printf` line that gives curl the `Authorization`
header. NEVER put the token in a curl argument. NEVER show the file
with `cat`, NEVER echo the token, and NEVER write it to the manifest, the
report, or a different file.**

### B3. Read Course Content

Same as A1 — read all files in `.idstack/course-content/` and the manifest.
Convert markdown content to HTML for the API calls (Canvas pages and assignments
accept HTML in their body fields).

Then do the "Export Plan" step. Go to B4 only after the user approves the plan.

**Course text goes in files, not in commands.** Course text can contain `$`,
quotes, backticks and `&`. The shell changes these characters in a command. Before
each command in B4 to B7 that sends text, write each value to its file in
`.idstack/canvas-push/`. Use the Write tool. Each command sends the files with
`--data-urlencode "<field>@<file>"` and then deletes the folder.

Write only the value, with no newline at the end. Write the files again before the next command. If a command prints
`PUSH_FILE_MISSING`, write the files and run the command again.

### B4. Create Modules

A block in B4 to B7 stops with `PUSH_FAILED: <item>: <reason>` when a call to
Canvas fails. If you run a block again, it first looks for the item by its
title. It does not create an item that exists. The first 100 matches of the
search are used.

The lookup is by title only. A page and an assignment with one
title in one module share a module-item match. A title with a space at the start
or the end can be made twice on a re-run.

For each module in the course content, write the module title to
`.idstack/canvas-push/title.txt`. Replace `<position>` with the number of the
module in the course, starting at 1. Then run:

```bash
. ./.idstack/canvas.env || { echo "CANVAS_ENV_MISSING"; exit 1; }
[ -f .idstack/canvas-push/title.txt ] || { echo "PUSH_FILE_MISSING"; rm -rf .idstack/canvas-push; exit 1; }
IFS= read -r _POS <<'IDSTACK_POSITION'
<position>
IDSTACK_POSITION
case "$_POS" in ''|*[!0-9]*) echo "PUSH_VALUE_BAD: position $_POS"; rm -rf .idstack/canvas-push; exit 1 ;; esac
_CALL() { # _CALL <item> <curl args>: sets HTTP_CODE and BODY. A curl error or a code that is not 2xx stops the push.
  _WHAT=$1; shift
  RESPONSE=$(printf 'header = "Authorization: Bearer %s"\nproto = "=https"\n' "$CANVAS_TOKEN" | curl -K - -s --max-time 60 -w "\n%{http_code}" "$@" 2>&1); _RC=$?
  HTTP_CODE=$(printf '%s\n' "$RESPONSE" | tail -1)
  BODY=$(printf '%s\n' "$RESPONSE" | sed '$d')
  case "$_RC:$HTTP_CODE" in
    0:2??) ;;
    28:*) echo "PUSH_FAILED: $_WHAT: Canvas did not answer in 60 seconds"; rm -rf .idstack/canvas-push; exit 1 ;;
    0:*) echo "PUSH_FAILED: $_WHAT: HTTP $HTTP_CODE"; rm -rf .idstack/canvas-push; exit 1 ;;
    *) echo "PUSH_FAILED: $_WHAT: curl error $_RC"; rm -rf .idstack/canvas-push; exit 1 ;;
  esac
}
_FIND() { # _FIND <list path> <name field> <result field>: sets _FOUND to the result of the item that has the title, or to nothing
  _CALL "$_KIND \"$_NAME\" lookup" -G --data-urlencode "search_term@.idstack/canvas-push/title.txt" -d "per_page=100" "$CANVAS_BASE_URL/api/v1/courses/$CANVAS_COURSE_ID/$1"
  # shortcut: the first 100 matches only, enough when a ti

[…] pełny plik w paczce .zip

• SKILL.md 89 KB
• SKILL.md.tmpl 59 KB