agentleFS
michaelalbermichaelalber/ai-toolkit/skills/doc-sync/SKILL.md

doc-sync

Skill3 starsChanged 3 months agoMITView on GitHub

Documentation staleness detection, XML doc comment generation, and README synchronization -- keeps documentation accurate and in sync with code changes. Use when auditing documentation coverage, generating XML doc comments, or systematically syncing READMEs after code changes. Do NOT use for a single, already-identified fix like "there's a typo, fix it" -- just make the edit directly.

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use api-endpoint, perf-budget and 7 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.
  • tadoEngSkill

    api-endpoint

    Add or change a backend API endpoint on this product, keeping Pydantic as the single contract authority and regenerating the TypeScript client. Use when asked to add an endpoint, expose data to the frontend, change a request or response shape, or wire a new backend capability into a page.

    Also in 4 projects that use this

  • vindreshsinghSkill

    perf-budget

    Optimizes performance by measuring first and fixing the real bottleneck. Use when something is slow, before optimizing, when setting latency or bundle targets, or reviewing changes for performance traps — not for speculative micro-tuning.

    Also in 3 projects that use this

  • AnasX7Skill

    improve

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.

    Also in 3 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    design

    Design rules and conventions for the API Center Portal. Use when editing detail pages, card components, badges, layout, navigation, sidebars, or headers. Covers badge styling, metadata placement, page navigation patterns, and layout alignment.

    Also in 3 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 27 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    READ BEFORE WRITING — read the full implementation before documenting.

    line 25
  2. Very specific:

    NO HALLUCINATED APIs — confirm every member exists (Grep/Glob) before documenting.

    line 26
  3. Distinctive:

    Exit criteria: every in-scope item classified.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 27 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

Doc Sync

"The only thing worse than no documentation is wrong documentation — someone will trust it and make a bad decision." -- adapted from Steve McConnell, "Code Complete"

Core Philosophy

Documentation decays the moment code changes. This skill detects when documentation has drifted from code, generates accurate XML doc comments from implementation analysis, and keeps READMEs synchronized with the project's actual state. The goal is not comprehensive documentation — it is accurate documentation. A perfectly documented codebase that was accurate six months ago is a liability; a minimally documented one verified this morning is an asset. Freshness and accuracy always beat completeness. Documentation is a derived artifact of code: when they diverge, the code is always right and the docs must change to match.

Non-Negotiable Constraints:

  1. CODE IS TRUTH — when docs and code disagree, update the docs to match; never the reverse.
  2. READ BEFORE WRITING — read the full implementation before documenting; never generate from the signature alone.
  3. NO HALLUCINATED APIs — confirm every member exists (Grep/Glob) before documenting; verify every <see cref>/<paramref> resolves.
  4. DETECT BEFORE GENERATING — audit for staleness first; assume all existing docs are stale until verified.
  5. PRESERVE VOICE — match the project's existing documentation style exactly; document the why, not the what.

Full principle table, discipline rules, anti-patterns, and error recovery live in references/conventions.md.

Workflow

STALENESS DETECTION
    SCAN      Identify scope: target dir/namespace, file types (.cs/.md/.xml), doc types.
    COMPARE   Per documented file: code vs. doc modification dates (git log); signatures vs. doc
              content; new public members without docs; removed members still in docs.
    CLASSIFY  CURRENT | STALE (code changed after doc) | MISSING (public API, no doc) |
              ORPHANED (doc references gone code) | DRIFT (doc ≠ current signatures).
    PRIORITIZE  ORPHANED → DRIFT → STALE → MISSING-on-public → CURRENT.
    (Heuristics: references/staleness-detection.md.)

XML DOC GENERATION
    READ      Full implementation; exact signature; throwing paths; edge cases; existing docs.
    GENERATE  <summary> WHAT+WHY not HOW · <param> each param + constraints · <returns> each
              non-void · <exception> each throw + condition · <remarks> edge/threading/perf ·
              <example> only when non-obvious · <see cref> related members.
    VERIFY    Every <param name> matches a real param; every <exception cref> is actually thrown;
              every <see cref> resolves; no <returns> on void; examples compile; summary ≠ name.
    (C# tag patterns: references/xml-doc-patterns.md.)

README SYNC
    INVENTORY  What the README covers (description, setup, config, usage, API, deps, contributing).
    DIFF       Each section vs. current state: setup vs. build files; deps vs. manifests; examples
               vs. current signatures; description vs. current capabilities.
    UPDATE     Read the current code/config; update to match; preserve existing style/format; don't
               add sections without an obvious gap; note anything you cannot verify.
    VALIDATE   All paths exist; commands valid; dep versions match manifests; API refs current.

Exit criteria: every in-scope item classified; updated docs match the implementation; every reference verified to resolve; unverifiable items flagged with a note; README sections validated against manifests and build files.

State Block

<doc-sync-state>
phase: SCAN | COMPARE | CLASSIFY | GENERATE | VALIDATE
scope: [directory, namespace, or file]
files_scanned: [count]
gaps_found: [count]
stale_docs: [count]
items_updated: [count]
items_validated: [count]
last_verified: [description of last action]
</doc-sync-state>

Output Template

  • Staleness report, XML doc coverage report — references/output-templates.md.
  • C# XML tag patterns, when to use each tag, quality examples — references/xml-doc-patterns.md.
  • Staleness heuristics (git-blame compare, signature drift, coverage, broken examples) — references/staleness-detection.md.
  • Principle table, discipline rules, anti-patterns, error recovery — references/conventions.md.

Integration with Other Skills

SkillRelationship
architecture-journalWhen an audit reveals undocumented architecture decisions, record them as ADRs there — documentation gaps often indicate decision gaps. Typical flow: doc-sync audit → discover an undocumented API redesign → architecture-journal records the decision → return to doc-sync to update XML docs + README.

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.