doc-sync
Skill3 starsChanged 34 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
- onegunsamurai/OpenLearningtheir own version, first seen Nov 8, 2026
- bas1l/claude-skillstheir own version, first seen Nov 3, 2026
- sayeediftekhar/Keeltheir own version, first seen Nov 1, 2026
- michaelalber/ai-toolkittheir own version, first seen Nov 1, 2026
- Cassandra-Collective/Ephesustheir own version, first seen Nov 1, 2026
- Univers42/harness42their own version, first seen Nov 1, 2026
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.
vindreshsinghSkillperf-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
AnasX7Skillimprove
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
dillonluiSkilldesign-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
NVIDIASkillresearch
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
GoogleSkillcode-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
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
Other versions34 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- nrjdalal/zerostarter★ 6597% same
Wrote their own version · 33
- JetBrains/ideavim★ 10ksame name
- taruma/SceneFlow★ 382same name
- PLC-lang/rusty★ 372same name
- chmouel/lazyworktree★ 315same name
- NVIDIA/TensorRT-Model-Connect★ 290same name
- fancyboi999/open-tag★ 181same name
- aspenkit/aspens★ 100same name
- tykisgod/quick-question★ 12same name
- foryouself83/harness-tier★ 10same name
- Reef123/OpenVera★ 9same name
23 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- AGENTS.mdAGENTS.md
- add-packageSkill
- agent-browserSkill
- api-endpointSkill
- auditSkill
- codebase-mapSkill
- db-migrationSkill
- designSkill
- devSkill
- docker-testSkill
- fontsSkill
- gh-commitSkill
- iceboxSkill
- ignore-syncSkill
- portlessSkill
- releaseSkill
- runtime-apisSkill
- shadcn-syncSkill
- shipSkill
- skills-managerSkill
- ui-verifySkill
The file
Files
[!CAUTION] Synced from https://github.com/nrjdalal/zerostarter. Customize this skill or remove this note to stop syncing.
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:
| Surface | Documents | Drifts when |
web/next/content/docs/**.mdx | concepts and how-to (getting-started, deployment, manage, resources) | a feature, convention, API, command, script, or env var it describes changes |
web/next/docs.config.ts | the docs nav and page registry, the single source the sidebar, meta.json, and MDX frontmatter all derive from | a doc page is added, removed, renamed, or re-slugged |
README.md | top-level story: stack, structure, quick start, scripts, deployment | the stack, setup, scripts, or pitch changes |
.agents/skills/<name>/SKILL.md | one 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 too | a rule changes, or the skill set changes |
packages/config/src/site.ts | the brand, the feature flags, and the hand-written preamble served at the top of /llms-full.txt | the 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.ts3. 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.mdskills table (generated, so runbun .github/scripts/skills-manager.ts) and theresources/ai-skills.mdxcatalog row. A vendored one also touches that page's count of how many skills are vendored, andskills-lock.jsonwhen 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.mdxalone.
4. Verify with the repo's own drift gate
bun .github/scripts/docs.ts --strictThis 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/skillsis canonical, so edit once. - The
/llms.txtand/llms-full.txtroutes mirror the docs and regenerate at build, so fix the doc, never the route.
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
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.

