Skip to content
Skills Library
Programming · Testing

test-guide

/test-guide

Guided manual testing session. Use when the user wants to manually test a feature, endpoint, CLI or UI, verify a bug fix, or resume a test session. Builds context, designs evidence-based scenarios, then guides the user step by step while the USER runs every command.

Repository
test-guide ↗
Licence
MIT
Last repository change
05.11.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 05.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Guided manual testing session. Use when the user wants to manually test a feature, endpoint, CLI or UI, verify a bug fix, or resume a test session. Builds context, designs evidence-based scenarios, then guides the user step by step while the USER runs every command.

Original author description

Guided manual testing session. Use when the user wants to manually test a feature, endpoint, CLI or UI, verify a bug fix, or resume a test session. Builds context, designs evidence-based scenarios, then guides the user step by step while the USER runs every command.

How it works

  1. Golden rule
  2. Phase 1 · Context
  3. Phase 2 · Scenarios
  4. Phase 3 · Execution
  5. Phase 4 · Close
  6. Resume
  7. State (write after every result; trust the files, not chat memory)
  8. Formats (use exactly; no prose outside the cards except a one-line clarification)
Original SKILL.md headings · 85 lines, 532 words
SKILL.md preview
---
name: test-guide
description: Guided manual testing session. Use when the user wants to manually test a feature, endpoint, CLI or UI, verify a bug fix, or resume a test session. Builds context, designs evidence-based scenarios, then guides the user step by step while the USER runs every command.
license: MIT
---
# Guided manual testing

## Golden rule
You plan, explain and compare. The USER runs every command (`!cmd`). Never execute commands yourself.

## Phase 1 · Context
Collect only what's needed to test the feature:
- System under test: start command, URL/binary, auth, test data
- Rules from the spec/code: `[Rn] rule — source (file§ / file:line / KEY AC#)`
- Gaps: where the spec is silent or the code ≠ the spec
If a Jira key is given, load `test-guide-jira`. Keep the brief to ≤ 40 lines.
Show the brief and ask: "Correct / missing?"

## Phase 2 · Scenarios
Write the Scenario Table. Rules:
- Every [Rn] is covered by at least one scenario. Add a Coverage line.
- Order: happy → auth → validation/edge → negative → regression. Use 5–10 rows.
- "Why" = which wrong implementation this scenario would catch, in one sentence.
- Put ambiguities under ❓ Open questions. Never guess.
The user may add, remove or reorder scenarios. Wait for their OK.

## Phase 3 · Execution
One scenario at a time:
1. Load the surface skill for this scenario (`test-guide-api` | `test-guide-cli` | `test-guide-ui`).
2. Show the Step Card. Wait for the user's output.
3. Show the Result Card and append a block to log.md.
Before calling something FAIL, triage: test data/setup, spec, or system? Give ONE check command.
If the spec is silent → OPEN ❓ and record the question.
Bug fix: reproduce on the old code first (must FAIL), then verify on the fix (must PASS).

## Phase 4 · Close
Write report.md. Offer the extras once, in one line: bug draft (/test-bug) and automation (/test-automate).

## Resume
Read the session files only. Show the Status Board. Ask the user to run
`!git log --oneline <last-commit>..HEAD --stat`, map the changed files to scenarios, and propose a re-run plan.

## State (write after every result; trust the files, not chat memory)
`.manual-tests/<session>/` → context.md · scenarios.md · log.md · report.md · evidence/

## Formats (use exactly; no prose outside the cards except a one-line clarification)

### Scenario Table
```
## Scenarios · <feature>
| # | Scenario | Surface | Expected | Covers | Why it proves correctness | Status |
Coverage: R1→S1,S3 · R2→S2
❓ Open questions: …
```

### Step Card
```
## ▶ S<n> · <title>          [<done>/<total> · ✅<p> ❌<f> ❓<q>]
**Surface:** API | CLI | UI    **Covers:** <Rn>
### Do
1. <step; commands in a bash block, prefixed with !>
### Expect
- <observable>
### Why this proves it
<one sentence>
```

### Result Card
```
## S<n> · PASS ✅ | FAIL ❌ | OPEN ❓
| Check | Expected | Actual | |
### Next
<one line>
```

### Status Board (after every 3 scenarios and on request)
```
## 📋 <session> · <done>/<total>
| # | Scenario | Surface | Result |
```

### log.md block
```
## S<n> · <result> · <yyyy-mm-dd hh:mm> · commit <sha>
Command · Expected · Actual (trimmed) · Evidence · Triage notes
```

### report.md
Header (feature, commit, date) · Summary `✅ · ❌ · ❓ · ⏭` · results table with evidence · Failures · Open questions · Setup/test-data issues.

Versions

The database has no other skills named test-guide.

Database snapshot: 13.11.2026 · package version 0f11f5b8af15 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100step-interactive-execution
    Prepare and run a user-confirmed interactive execution or test session for a source file, executable, script, demo, or directory. This skill must be invoked manually: use it only when the user explicitly invokes step-interactive-execution by name or clearly asks for this exact…
  • 100hatch3r-bug-fix
    Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
  • 90walkthrough
    Turn a multi-step ask into guided execution instead of a command dump: self-execute every step you can, hand the owner only the steps that genuinely need them — one command at a time, each result verified before the next. Use when the owner invokes /walkthrough or asks to be…
  • 95manual-test
    Click through a feature in a real browser and verify it behaves — navigate, interact, observe. Use when asked to manually test, QA, or try out a feature as a user would, rather than writing an automated test.
  • 100test-scenarios
    Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.
  • 95test-scenarios
    Create comprehensive test scenarios from user stories with test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use when writing QA test cases, creating test plans, defining acceptance tests, or preparing for feature validation.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.