Index of every page on this site: llms.txt
All skills
tristanmanchester avatar

/write-good-docs

@3323bc9
by Tristan Manchestertristanmanchester/agent-skills3 stars
2
Run it yourself

Write, edit, and review human-facing technical documentation. Use for READMEs, guides, tutorials, how-tos, API or CLI reference, runbooks, troubleshooting, onboarding, architecture and design docs, RFCs, ADRs, migration guides, release notes, technical findings reports, docstrings, and explanatory comments. Also use for requests such as "document this" or "make this guide clearer." Do not automatically activate for chat explanations, email, marketing, social posts, fiction, translation-only tasks, or code-only work. When explicitly asked to use this skill for another nonfiction format, apply its prose and fidelity guidance without imposing documentation templates.

Use this Skill: https://skilld.dev/gh/tristanmanchester/agent-skills/write-good-docs

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

VALIDATION.md

≈623 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Validation record

Version: 2.1.0. Date: September 13, 2026.

Checks performed

The package was checked locally with:

python3 scripts/check_package.py
python3 -m unittest discover -s evals/tests -v

The structural check passed for the package's simple frontmatter layout, naming and version consistency, local Markdown file targets and applicable anchors, the 20 case definitions and their supplied fixtures, and the release manifest. All 36 maintenance-tool unit tests passed.

The tests cover case loading, writer/rubric separation, overwrite refusal, relative path safety, output outside the skill directory, protected literals, exact-text preservation, platform line-ending normalization, local edit boundaries, warning repetition and ordering, explicit format/length constraints, error handling, local-link checks, and manifest mutation detection.

One test deliberately supplies an unsupported claim that contains all required literal tokens. It confirms that the tool reports only a mechanical pass and still requires semantic review. Mechanical checks do not establish factual or stylistic quality.

The archive was extracted into a fresh directory and the same package and unit-test checks were repeated. ZIP integrity and the extracted file hashes were checked. No macOS resource-fork entries, temporary build files, Python bytecode, or model-run outputs are included.

Editorial inspection

The source package and supplied review were read before revision. The revised instructions and examples were checked for contradictory authority rules, unsupported enrichment, modality drift, destructive-validation authorization, and overgeneralized prose restrictions. Selected primary guidance was rechecked as recorded in the source map; inherited external links were not comprehensively re-audited.

Not performed

No controlled comparison of model-generated output with no skill, v2.0.0, and v2.1.0 was run. The 20 writing cases and 32 routing probes are supplied for that comparison, not reported as passed model evaluations. Generated prose, automatic activation, actual reference-loading cost, and model-dependent behavior remain to be evaluated on the target agents.

The package checker is intentionally small. It validates the frontmatter and Markdown conventions used by this package, not arbitrary YAML syntax or every renderer's anchor algorithm. Hashes detect changes relative to the manifest; the manifest is not signed proof of origin.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is a high-quality documentation assistant based on the Google developer documentation style guide. It incorporates robust safety practices, explicitly prohibiting the inclusion of sensitive data like credentials in examples and prioritising technical accuracy. All external links are to trusted and well-known documentation platforms.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: MEDIUM · 1 issue

Provenance

Signed by skilld at 3323bc9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated last month

Capability

Other metadata
metadata
{
  "version": "2.1.0",
  "source": "Google developer documentation style guide; see ATTRIBUTION.md",
  "revised": "2026-09-13"
}

README badge

README badge for tristanmanchester/agent-skills/write-good-docs