analyze-repo
Skill1 starsChanged 7 months agoApache-2.0View on GitHub
Full repository analysis. Invoke at the start of a new session or when Claude needs to understand the project from scratch. Writes a comprehensive summary to SESSION_STATE.md.| Use when: starting fresh, after a long break, when context was lost, or when explicitly asked to "analyze the project".
- Reads credentials
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kriscard/Skillstheir own version, first seen Oct 28, 2026
- Azure/containerization-assisttheir own version, first seen Jun 8, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Azure/containerization-assist★ 45same name
- kriscard/Skills★ 15same name
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.mdCLAUDE.md
- augmentSkill
- code-reviewSkill
- context-guardSkill
- dep-checkSkill
- doctorSkill
- forgeSkill
- git-workflowSkill
- learnSkill
- onboardingSkill
- security-scanSkill
- self-updateSkill
- test-runnerSkill
- tipsSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
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
- Distinctive: line 23
Read (do not dump into conversation — just extract key info):
- Distinctive: line 29
Use the explorer sub-agent to explore large codebases:
- Distinctive: line 41
Test setup (unit? integration?
- Distinctive: line 49
Write a clean, structured summary:
- Distinctive: line 96
After the analysis is complete, call the tips skill to show 2-3 relevant tips:
- Distinctive: line 102
When calling from analyze-repo context:
- Distinctive: line 106
No tests found → tip about /test workflow
- Very specific: line 107
No SESSION_STATE.md → tip about session continuity
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Build a complete mental model of the project and write it to SESSION_STATE.md. This is the "repo memory reload" skill — it turns a cold start into a warm start.
Steps
1. Discover Structure
# Get top-level layout
ls -la
# Find key config files
ls package.json tsconfig.json pyproject.toml Cargo.toml go.mod 2>/dev/null
# Framework detection
cat package.json | grep -E '"next"|"react"|"vue"|"express"|"fastapi"|"django"' 2>/dev/null2. Read Key Config Files
Read (do not dump into conversation — just extract key info):
package.json/pyproject.toml/Cargo.toml— dependencies and scripts.env.example— what environment variables are needed- Existing
CLAUDE.mdif present — don't overwrite it, extend it
3. Map the Codebase
Use the explorer sub-agent to explore large codebases:
Use the explorer agent to: map the top 3 levels of directory structure and identify what each major directory containsFor smaller repos, read directly.
4. Identify Key Patterns
- Auth pattern (JWT, session, OAuth?)
- Database access pattern (ORM, raw SQL, query builder?)
- API style (REST, GraphQL, tRPC?)
- State management (if frontend)
- Test setup (unit? integration? e2e?)
5. Find Existing Scripts
cat package.json | python3 -c "import sys,json; d=json.load(sys.stdin); [print(k,':',v) for k,v in d.get('scripts',{}).items()]" 2>/dev/null6. Write SESSION_STATE.md
Write a clean, structured summary:
# Session State
*Analyzed: [date]*
## Project
- **Name**: [name]
- **Stack**: [e.g., Next.js 14 + Supabase + Tailwind + TypeScript]
- **Package Manager**: [npm/pnpm/yarn]
## Key Commands
- Dev: `[command]`
- Test: `[command]`
- Build: `[command]`
- Lint: `[command]`
## Directory Map
- `/src/app` — Next.js App Router pages
- `/src/components` — Reusable UI components
- `/src/lib` — Utilities and helpers
- `/api` — API routes
- `/tests` — Test files
## Architecture Notes
[Key architectural decisions, patterns, and things Claude needs to know]
## Active Work
[What was being worked on — if any TODO.md or recent commits indicate this]
## Agents Available
[List the .claude/agents/ files found]
## Skills Available
[List the .claude/skills/ directories found]7. Report to User
Print a short 5-line summary:
- Stack detected
- Key commands found
- Number of agents/skills configured
- Anything unexpected or worth noting
- "SESSION_STATE.md updated. Ready to work."
Final Step — Surface Tips
After the analysis is complete, call the tips skill to show 2-3 relevant tips:
Skill("tips")When calling from analyze-repo context:
- Show only 2-3 tips (not 5)
- Prioritize based on what the analysis revealed:
- Large files found → tip about targeted reads
- No tests found → tip about /test workflow
- No SESSION_STATE.md → tip about session continuity
- Many agents → tip about context window
- Label them: "Quick wins for this setup"
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.

