Skip to content
Skills Library
Science & research · Writing

report

/report

Assemble a factual Markdown and JSON report from a sweep study or saved runs without rerunning - identity, inputs, edits, target outcomes, counts with denominators, diagnostics, freshness, plots and an artifact list with sha256. Use it to hand results to a person.

Licence
MIT
Last repository change
11.11.2026

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 11.11.2026, 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

Assemble a factual Markdown and JSON report from a sweep study or saved runs without rerunning - identity, inputs, edits, target outcomes, counts with denominators, diagnostics, freshness, plots and an artifact list with sha256. Use it to hand results to a person.

Original author description

Assemble a factual Markdown and JSON report from a sweep study or saved runs without rerunning - identity, inputs, edits, target outcomes, counts with denominators, diagnostics, freshness, plots and an artifact list with sha256. Use it to hand results to a person.

How it works

  1. When to use
  2. When not to use
  3. Inputs
  4. Outputs
  5. Minimal example
  6. Limits
  7. Version
Original SKILL.md headings · 46 lines, 232 words
SKILL.md preview
---
name: report
description: Assemble a factual Markdown and JSON report from a sweep study or saved runs without rerunning - identity, inputs, edits, target outcomes, counts with denominators, diagnostics, freshness, plots and an artifact list with sha256. Use it to hand results to a person.
version: 0.2.0
command: os-optics-kit report
requires: os-optics>=0.13,<0.14
kind: tool
---

# report

## When to use

- A study or a set of runs is finished and needs a reviewable record with links and hashes.
- An edit's change record should appear next to its results (`--changes`).

## When not to use

- Deciding from numbers in a script: read `summary` / `compare` JSON directly.
- Making plots: run `plot` first, then link them with `--plots`.

## Inputs

- `PATH ...`: one study directory (from `sweep`, `sensitivity` or `tolerance`), or run directories.
- `--project CURRENT.json`: freshness of every run (a historical PASS is labelled `HISTORICAL PASS`).
- `--plots PNG_OR_DIR ...`: plot files or directories to link.
- `--changes NEW.changes.json`: the change record written by `edit`.
- `--out DIR`: default `STUDY_DIR/report`, or `./report` for run directories.

## Outputs

`DIR/report.md` and `DIR/report.json` (links relative to DIR). Stdout: paths, kind, counts, best sample
or no-feasible outcome, diagnostics, numbers of artifacts and plots. Exit 0 written, 4 invalid input.

## Minimal example

```
os-optics project example --kind focus > project.json
os-optics project run project.json --out-dir run
os-optics-kit report run --project project.json --out report
```

For a study: `os-optics-kit report study --project project.json --plots study/plots`.

## Limits

- Numbers are copied from the saved files; nothing is interpreted beyond the computed comparisons.
- From Python, `os_optics_kit.build_report.build_report(..., sections=[...], artifacts=[...])` adds your
  own sections and files.

## Version

0.2.0 (os-optics-kit 0.2.0), verified with os-optics 0.13.0 and catalog release 2026-10-28.1.

Versions

RepositoryScoreLicence
This page · JunLin615/os-optics-kit100MIT
petrbouda/jeffrey100Apache-2.0
petrbouda/jeffrey100Apache-2.0
onmax/comark-ui100MIT
renzrollon/interlock100MIT
digital-stoic-org/agent-skills100MIT
90p-labs/harness100MIT
emaballarin/ccplugins100MIT
quantskills/agent-quantspace100GPL-3.0

Database snapshot: 13.11.2026 · package version b27db16ab6cc (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

  • 100compare
    Compare saved runs, or the samples of a sweep study, by target and observation-plane ID without rerunning; lists differing inputs, deltas to a reference run and, with a current Project, each run's freshness. Use it to explain what an edit changed.
  • 95results-report
    Create a clean, minimal results summary report from a completed behavioral-science study or pilot. Use when the user wants to write up findings for an advisor, lab meeting, co-author, or their own records. Default output is Markdown; an optional HTML slide-style variant is…
  • 100session-start
    Session-orientation workflow — read the project's Markdown corpus (CLAUDE.md, the outline, project MEMORY, the wiki landing page), build a genuine understanding of the study, then report a concise project summary and an honest current-status snapshot. Read-only with zero side…
  • 90report-regressions
    Use when assembling or refreshing an evidence-linked regression report from saved campaign decisions.

Feedback and reports

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