repo-onboarder
Skill1 starsChanged 5 months agoMITView on GitHub
First time in a codebase? This skill gives you a 5-minute tour: entry points, key modules, conventions, and where to start reading. Trigger phrases: new repo, show me around, where do I start, tour this codebase, cold on this project. Activate automatically on the FIRST message in a new project directory if the user appears unfamiliar (asks where things are, what does X do). /tour — run on current directory. User: /tour Skill (after scanning):
1 other project uses a version of this.
Adopted by
Most recently taken up by
- surfmind-space/awesome-surfmindtheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- surfmind-space/awesome-surfmind★ 8same 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 repository12 other files it gives its agents.
- commit-curatorSkill
- context-compactorSkill
- cost-trackerSkill
- decision-recorderSkill
- mcp-finderSkill
- permission-auditorSkill
- prd-builderSkill
- prompt-matcherSkill
- pr-reviewerSkill
- scope-clarifierSkill
- skill-matcherSkill
- tdd-flowSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Very specific: line 13
Read top-level files: README.md, package.json/pyproject.toml/Cargo.toml/go.mod, Makefile, docker-compose.yml
- Distinctive: line 19
Commit style (from git log)
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
repo-onboarder
First time in a codebase? This skill gives you a 5-minute tour: entry points, key modules, conventions, and where to start reading.
When to activate
Trigger phrases: new repo, show me around, where do I start, tour this codebase, cold on this project.
Activate automatically on the FIRST message in a new project directory if the user appears unfamiliar (asks where things are, what does X do).
Process
- Read top-level files:
README.md,package.json/pyproject.toml/Cargo.toml/go.mod,Makefile,docker-compose.yml - Identify entry points (
main.py,index.ts,cmd/*/main.go,app.py, etc.) - Map directory roles:
src/,tests/,docs/,scripts/,infra/,migrations/ - Detect conventions:
- Test framework
- Code style (formatter config, linter rules)
- Commit style (from git log)
- Branch naming (from
git branch -a) - PR template (
.github/PULL_REQUEST_TEMPLATE.md)
- Surface the 5 most important files to read first
- Emit a one-page tour
Output format
Repo: <name>
Lang: <language> | Framework: <fw> | Tests: <framework>
Entry point(s):
- <path> — <one-line role>
Directory map:
- src/ <one-line>
- tests/ <one-line>
- ...
Conventions:
- Style: <e.g. black + ruff>
- Tests: <e.g. pytest, run with `make test`>
- Commits: <e.g. conventional>
Start reading here (in order):
1. <path>:<line> — <why>
2. <path>:<line> — <why>
3. <path>:<line> — <why>
4. <path>:<line> — <why>
5. <path>:<line> — <why>
How to run it locally:
<commands>
Where to add a new feature:
<pattern matching how features are added in recent commits>Inputs
- Project root path
- Recent git activity (what files changed recently = currently active areas)
Outputs
- One-page tour (markdown)
- 5 numbered files to read with rationale
Slash command
/tour — run on current directory.
Anti-patterns prevented
- Reading every file before doing anything (wastes 1+ hour)
- Asking the user "what does this codebase do" when the README answers it
- Recommending paths that don't exist in this project
Example
User: /tour
Skill (after scanning):
Repo: proteus
Lang: Python | Framework: stdlib + anthropic SDK | Tests: pytest
Entry point: proteus.py — boots event bus + orchestrator + agents
Directory map:
- agents/ domain handlers (memory, research, admin, content, code, trading)
- server/ BYOK API + scheduler + user store
- sources/ external event sources (file watcher today, gmail/cal planned)
- sync/ always-on daemon
- tests/ pytest suite
Conventions:
- Style: black + ruff (no config = defaults)
- Tests: pytest, run with `python -m pytest tests/`
- Commits: conventional commits (feat:, fix:, chore:)
Start here:
1. proteus.py:1 — see how the pieces wire together
2. agents/event_bus.py:1 — the async queue
3. agents/orchestrator.py:1 — routing logic
4. agents/tier0_filter.py:1 — local Ollama call
5. agents/memory_agent.py:1 — pattern for a domain agent
Run it: `python proteus.py`
Add a new agent: drop a module in agents/, register in proteus.py _register_agents()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.

