analyze
Skill0 starsChanged 4 months agoMITView on GitHub
Generate or refresh the project map — the structural overview an agent reads before touching unfamiliar parts of the codebase. Use when the user says /analyze, after a structural change, or when the map has gone stale.
74 other projects use a version of this.
Adopted by
Most recently taken up by
- mikeleg/skillstheir own version, first seen Nov 16, 2026
- Imtylerrrrrr/second-braintheir own version, first seen Nov 16, 2026
- Yomudogly/oh-my-agytheir own version, first seen Nov 16, 2026
- markmhendrickson/neotomatheir own version, first seen Nov 15, 2026
- codeboehm/maximtheir own version, first seen Nov 15, 2026
- link7373/agentic-bi-teamtheir own version, first seen Nov 10, 2026
Used with
Projects with it also use constitution, revise 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.
ArvorCoSkillconstitution
Create or update the project constitution - personalized governance and coding principles. Use when starting a project or updating project standards. Triggers on: create constitution, update principles, set project rules.
Also in 4 projects that use this
stormlightlabsSkillrevise
Address review comments on an open pull request and push the fixes. Use for /edit, /revise, or when asked to respond to review feedback on a PR number.
Also in 3 projects that use this
DockerSkillwrite
Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.
Also in 6 projects that use this
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 5 projects that use this
H-mmerSkillsubmit
Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.
Also in 3 projects that use this
GoogleSkillquality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
Also in 3 projects that use this
- +1 more from ArvorCo
Other versions74 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 74
- anthropics/knowledge-work-plugins★ 36ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- oxsecurity/megalinter★ 2.6ksame name
- H-mmer/pentest-agents★ 815same name
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- hardisgroupcom/sfdx-hardis★ 432same name
- nwiizo/tfmcp★ 373same name
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- ansvisor/ansvisor★ 241same name
64 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 repository14 other files it gives its agents.
- .claude/skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- .claude/skills/vercel-react-view-transitions/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- auditSkill
- browserSkill
- checkSkill
- gitpushSkill
- shipSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- vercel-react-view-transitionsSkill
- web-design-guidelinesSkill
- writing-guidelinesSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 64 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Write .claude/project-map.md: what lives where, what talks to what, and where the load-bearing pieces are.
- Very specific: line 62
Write it to .claude/project-map.md, under ~150 lines:
- Distinctive: line 98
Prefer a table to a paragraph, a number to an adjective, and a path to a description.
- Very specific: line 109
Do not commit it — leave that to /gitpush.
“Common” is measured: kept by at least 6 in 10 of the 64 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.
Files
Write .claude/project-map.md: what lives where, what talks to what, and where
the load-bearing pieces are. Optional $ARGUMENTS narrows the refresh to one
area instead of the whole tree.
The map is not auto-loaded — CLAUDE.md is. This is the file an agent reads
on demand before working somewhere it has not been, which is why it must be
short enough to actually read and honest about size.
What to gather
Measure, do not recall:
git ls-files -- src webview/src | xargs wc -l | sort -rn | head -20
git ls-files -- src webview/src | wc -l- Both halves.
src/is the extension host,webview/src/is the React app. They are separate builds joined bypostMessage, and that seam is the single most important thing on the map. - The protocol. Enumerate the message union in
webview/src/lib/rpc.tsby area — chat, permissions, plan, skills, MCP, checkpoints — with a count each, both directions. A reader wants to know the shape, not all hundred names. Then say what enforces it:HandlerTableinsrc/ui/messages.tsmakes a missing handler a compile error, andtest/unit/protocol-contract.test.tsfails when the two declarations drift. That answer changes over time and is the most useful sentence on the map — check it, do not copy it forward. - Entry points.
extension.ts,panel.ts,main.tsx, and what each owns. - The pure core.
src/core/*imports no VS Code API and is unit-tested in isolation — say so, because it is the only part that can be tested cheaply. - The design system.
themes/*(core tokens per palette, derived in_base.scss) → modules;design/motion.ts;design/icons.tsx;design/primitives/*. There is nodesign/tokensdirectory — tokens are CSS custom properties, and they live inthemes/. - Sizes. Name the files over ~700 lines. Whichever is largest is the god-file — say so plainly rather than let each newcomer rediscover it, and measure which one that is rather than assuming it is still the last one.
What makes this map worth reading
Anyone can list directories. What saves time is the part a directory listing cannot show:
- Where the seams are. Which file you change to add a message, a token, a motion preset, an icon — one line each.
- What is shared and therefore dangerous.
theme.css,design/motion.ts,themes/_base.scssare read by everything; two agents editing them at once is how the last rounds produced conflicts. - What is inherited and unreviewed. The extension host came from a fork and the webview was rewritten. Say which parts have had eyes on them.
- What is big for a reason and what is big by accident.
Format
Write it to .claude/project-map.md, under ~150 lines:
# Project map
_Generated <date>. Regenerate with `/analyze` after structural changes._
## Two halves
<the postMessage seam, one paragraph>
## Extension host — `src/`
| Path | Owns | Lines |
## Webview — `webview/src/`
| Path | Owns | Lines |
## The protocol
<message areas with counts, where to add one>
## Where to change what
| To add… | Touch |
## Shared resources — edit deliberately
<the three files, and why>
## Size and debt
<files over 700 lines, with a one-line judgement each>Prefer a table to a paragraph, a number to an adjective, and a path to a description.
Hard rules
- Read-only apart from the map itself.
- Measure sizes and counts. A map that says "large" instead of "2,763 lines" is a map nobody trusts twice.
- Do not restate
CLAUDE.md. Rules live there; structure lives here. If the two disagree,CLAUDE.mdwins and the map is stale. - Keep it short. A map nobody finishes reading is a map nobody reads.
- Do not commit it — leave that to
/gitpush.
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.

