agentleFS
frameforgedframeforged/technical-documentation-framework/technical-review/SKILL.md

technical-review

Skill2 starsChanged 4 months agoApache-2.0View on GitHub

Reviews generated documentation for correctness, clarity, depth, example quality, terminology consistency, assumptions, completeness, and publishing readiness.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Technical Review Skill

Purpose

Evaluate whether the documentation is ready to publish.

Output format

# Technical Documentation QA Report

## Overall Score

/5

## Correctness

## Clarity

## Depth

## Example Quality

## Terminology Consistency

## Natural Voice

## Language Compliance

## Missing Sections

## Inconsistent Terms

## Shallow Areas

## Risky Assumptions

## Recommended Revisions

## Final Decision

Scoring

Use this weighting:

CategoryWeight
Correctness25%
Clarity15%
Depth15%
Example quality15%
Terminology consistency15%
Natural voice10%
Language compliance5%

Score natural voice against the self-check list in rules/natural-writing-rules.md. Read the two or three densest sections aloud in your head: template openers, stacked terms, uniform sentence rhythm, and filler intensifiers each cost points.

Blocking issues

The documentation is not ready if:

  • No glossary exists.
  • Core terms are undefined.
  • Product boundaries are missing.
  • Examples are missing.
  • Unknown facts are presented as confirmed facts.
  • The same concept is used with inconsistent names.
  • The documentation language does not follow the user's instruction or conversation language.
  • The structure does not match the requested documentation type.
  • The text reads machine-generated: template section openers, unexplained term stacking, uniform sentence rhythm, or filler intensifiers throughout.

Final decision values

Use one of:

  • Ready to publish
  • Minor revision required
  • Major revision required
  • Rewrite required

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.