agentsclimarketplace

Onboard

Skill latuconsinafr/claude-code-config/skills/onboard

The claude code config, tailored to myself, battle-tested (might inspires you)

Install
npx -y skills add latuconsinafr/claude-code-config --skill onboard

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use at the start of a session on an unfamiliar or returning project β€” reads architecture docs, recent activity, open work, and coding conventions to prime context before starting any task. Invoke this before /plan or /issue when you haven't worked on the project recently.

SKILL.md

3.7 KB, 930 tokens by cl100k_base, as published. Nobody here has run it

Project Onboarding

Prime context about the project before starting work. Do not modify any files.

Step 1: Identify the project

pwd
basename $(git rev-parse --show-toplevel 2>/dev/null || pwd)
git remote get-url origin 2>/dev/null

Step 2: Map the project β€” spawn the explorer agent

Spawn the explorer agent to investigate the project's documentation and structure. Pass:

Project directory: <pwd from Step 1>
Investigate and return:

1. Documentation: read CLAUDE.md, README.md/rst, ARCHITECTURE.md, CONTRIBUTING.md
   (maxdepth 2). Also read any architecture.*, overview.*, design.*, or adr/ files
   found in docs/ subdirectories.

2. Environment setup: find .env.example, .env.sample, Makefile, justfile (maxdepth 2).
   Note any required env vars or setup steps.

3. Stack: detect primary language and runtime from package.json / go.mod / Cargo.toml /
   pyproject.toml. Extract: language, framework, database(s), test runner, key dependencies.

4. Project structure: list top-level directories (maxdepth 2), excluding node_modules,
   .git, dist, build, coverage, .next. Find entry points: main.*, index.*, app.*, server.*

Return a structured summary of all findings.

Step 5: Recent activity

# What's been worked on recently
git log --oneline --since="2 weeks ago" 2>/dev/null | head -20

# Open branches (active work)
git branch -r 2>/dev/null | grep -v HEAD | head -10

# Recent files changed
git diff --name-only HEAD~10 HEAD 2>/dev/null | sort -u | head -20

Step 6: Open work

# Open PRs
gh pr list --limit 10 2>/dev/null

# Open issues assigned to you or unassigned
gh issue list --limit 10 --assignee "@me" 2>/dev/null
gh issue list --limit 5 --state open 2>/dev/null

If gh is not available, skip silently.

Step 7: Coding conventions

Scan for project-specific conventions:

# Linting / formatting config
find . -maxdepth 2 -name ".eslintrc*" -o -name "eslint.config.*" \
  -o -name ".prettierrc*" -o -name "biome.json" \
  -o -name ".golangci*" -o -name "pyproject.toml" \
  -o -name ".rubocop*" 2>/dev/null | grep -v node_modules | head -5

# Git conventions
cat .gitmessage 2>/dev/null
find . -maxdepth 3 -path "*/.git/hooks/commit-msg" 2>/dev/null | xargs cat 2>/dev/null | head -30

Note any enforced commit message format, branch naming patterns, or PR conventions.

Step 8: Produce the context summary

Structure output as:

πŸ—οΈ Project

Name: <project name> Repo: <remote URL> Stack: <language> + <framework> + <database> Test runner: <jest/pytest/go test/etc>

πŸ“ Structure

Brief description of the top-level directories and what lives where.

πŸ”„ Recent activity

What has been actively worked on in the last 2 weeks. What areas are "hot."

🌿 Active branches

Open branches and what they're working on (inferred from branch names + recent commits).

πŸ“‹ Open work

Open PRs and issues. What's in flight.

πŸ“ Conventions

  • Commit format: <detected format>
  • Branch naming: <detected pattern>
  • Code style: <linter/formatter in use>
  • Any other project-specific rules found in CLAUDE.md or CONTRIBUTING.md

⚠️ Things to know

Anything from the docs that's non-obvious β€” gotchas, known issues, things to be careful about.

βœ… Ready

"Context loaded. You can now use /issue, /plan, or ask questions about the codebase."

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.