agentleFS
Sign inStart free
ZeeshanSultanZeeshanSultan/DocGov/skills/review/SKILL.md

review

Skill0 starsChanged 2 months agoMITView on GitHub

Inventory, classify and produce a migration plan for a repository that already has documentation. Detects duplicates, contradictions, oversized documents, wrong locations, missing frontmatter and coverage gaps, then writes a plan that changes nothing until approved. Use for existing repositories, messy documentation trees, or "organize my docs".

192 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use close-spec, design-with-images and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dzhngSkill

    close-spec

    When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec), archive it to specs/done/ and rewrite it from a build-plan into a durable rationale — the why, the principles, the invariants — pointing back to the real code for the how. Use when implementation has landed and the plan no longer matches what shipped, or the user says a feature/spec is finished. Pairs with [write-spec](../write-spec/SKILL.md) (the plan this closes) and [review](../review/SKILL.md) (run before closing).

    Also in 5 projects that use this

  • dzhngSkill

    design-with-images

    Explore UI and visual design with image generation, then iterate the real implementation against the user-selected concept. Use when brainstorming visual directions, offering mockup variants, or implementing an approved generated design; do not stop at the mockups or the first code approximation.

    Also in 5 projects that use this

  • LambenthanSkill

    daily-arxiv

    每日从 arXiv 拉取新论文，过滤相关性，auto-ingest 高优先级论文，检测 SOTA 更新

    Also in 5 projects that use this

  • LambenthanSkill

    exp-eval

    实验判决门：Review LLM 独立评判实验结果 → 4 种判决路径 → 自动更新 claims confidence、ideas status、graph edges

    Also in 5 projects that use this

  • +3 more from dzhng
  • +5 more from Lambenthan

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 157 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Verify: After migrating, run docgov check and docgov health.

    line 58
  2. Very specific:

    Do not move files yourself — migrate repairs links in the same transaction and your mv will not.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 157 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Onboard an existing repository

Plan

!docgov review --json --compact 2>&1 | head -c 24000

What to do

The JSON above is the full plan; .docgov/fix-plan.md is the human-readable version. Nothing has been changed.

  1. Summarize honestly, shortest first. How many documents, how many DocGov could not classify, how many moves, how many real judgement calls. Do not pad the summary with the things that went fine.

  2. Work the low-confidence classifications. classifications[] entries with needsReview: true are where the deterministic classifier gave up. Read each document (just enough of it) and decide its class yourself. Run docgov types if you need the list. Then write the decision into the document's frontmatter:

    docgov:
  id: <kebab-id>
  type: <class>
  authority: <from the class>
  visibility: internal|public|confidential

    Declaring the type is what turns a guess into a fact — the classifier never overrides a declared type.

  3. Adjudicate the contradiction candidates. contradictionCandidates[] is a narrowed list, not a verdict. For each pair, read both and decide: genuine contradiction, acceptable overlap (different audiences saying the same thing in different words), or genuine duplicate. Use the architect agent for the non-obvious ones. Only real contradictions need fixing, and the higher-authority document is the one that is right unless you have a reason to think otherwise.
  4. Propose, do not perform, the high-risk actions. SPLIT, MERGE and EXTRACT rewrite prose. Present them to the user as a short list with your recommendation, and handle them one at a time through /docgov:tag.
  5. When the user approves, run the mechanical half:
    docgov fix --dry-run     # every file operation, nothing touched
docgov fix               # on a branch, with link repair and verification
    migrate refuses to run without git or with a dirty tree. That is deliberate: the "no information lost" promise is only real if every change is revertible.
  6. Verify. After migrating, run docgov check and docgov health. Report the health score and the top three things that would raise it most.

Do not

Do not move files yourself — migrate repairs links in the same transaction and your mv will not. Do not merge two documents' prose without showing the user what you are about to delete.

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.

Check your setup, free