agentleFS
nrjdalalnrjdalal/zerostarter/.agents/skills/doc-sync/SKILL.md

doc-sync

Skill65 starsChanged 14 days agoMITView on GitHub

Sync docs and skills so they never drift from the code. Use before opening or updating a PR, or when a change touches a command, path, convention, or the skill set a doc or skill documents.

34 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use perf-budget, improve and 4 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.
  • 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

  • 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

  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 4 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

Files
SKILL.md

Doc Sync

A change ships with its docs or it ships drift. This is the procedure that catches drift across every hand-authored surface before the PR goes up: AGENTS.md makes the sync mandatory, this makes it checkable.

Surfaces

Hand-authored, keep each in step with the code:

SurfaceDocumentsDrifts when
web/next/content/docs/**.mdxconcepts and how-to (getting-started, deployment, manage, resources)a feature, convention, API, command, script, or env var it describes changes
web/next/docs.config.tsthe docs nav and page registry, the single source the sidebar, meta.json, and MDX frontmatter all derive froma doc page is added, removed, renamed, or re-slugged
README.mdtop-level story: stack, structure, quick start, scripts, deploymentthe stack, setup, scripts, or pitch changes
.agents/skills/<name>/SKILL.mdone task procedure each (canonical; .claude and .github symlink in)a command, path, convention, or tooling a skill encodes changes, or a skill is added or removed
AGENTS.md (CLAUDE.md symlinks in)the rules and the skills catalog table; ships to every fork whole, so a rule must read true there tooa rule changes, or the skill set changes
packages/config/src/site.tsthe brand, the feature flags, and the hand-written preamble served at the top of /llms-full.txtthe layout, the route groups, the packages, or the API surface it describes changes

Generated, never hand-edit (they regenerate from the surfaces above): content/docs/meta.json (git-ignored), the /llms.txt and /llms-full.txt routes, and the fumadocs search index. The one hand-written part of those routes is the /llms-full.txt preamble, which lives in site.ts above.

1. Scope the change

List what the diff touched: paths, commands, script names, env vars, conventions, tooling, and whether the skill set changed. Start from git diff --stat and the code diff.

2. Hunt drift

Grep every surface for each changed path, command, or symbol; every hit is a candidate:

rg -n "<changed-path-or-command>" web/next/content/docs README.md AGENTS.md .agents/skills web/next/docs.config.ts

3. Sync, coupled surfaces included

Fix each hit in the same change. Two couplings are easy to miss:

  • Adding or removing a skill touches the AGENTS.md skills table (generated, so run bun packages/scripts/src/skills-manager.ts) and the resources/ai-skills.mdx catalog row. A vendored one also touches that page's count of how many skills are vendored, and skills-lock.json when it is a stub pinned for integrity (agent-browser); one copied in full (portless) has no lock entry.
  • Adding, removing, or renaming a doc page touches web/next/docs.config.ts, not the .mdx alone.

4. Verify with the repo's own drift gate

bun packages/scripts/src/docs.ts --strict

This is the fast gate (seconds): it exits non-zero on any .mdx missing from docs.config.ts, any config entry with no file, or frontmatter drifted from docs.config.ts. To fix a failure, run it without --strict to rewrite the managed frontmatter and scaffold missing pages, then commit. Before the PR, also run cd web/next && bun run build once: it reruns this check inside the full build, and additionally catches type errors and rebuilds the search index. Done when the strict gate passes AND a fresh rg for every removed or renamed path, command, and skill name finds zero stale mentions across the surfaces.

Notes

  • Skills are symlinked: .agents/skills is canonical, so edit once.
  • The /llms.txt and /llms-full.txt routes mirror the docs and regenerate at build, so fix the doc, never the route.

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.