agentleFS
chuckplayerchuckplayer/claude-agent-pack/skills/setup-project/SKILL.md

setup-project

Skill8 starsChanged 35 days agoMITView on GitHub

Scaffolds a project with the Claude Agent Pack structure: copies CLAUDE.md (the consumer block, from docs/CLAUDE.template.md), docs/CONVENTIONS.md (from template), docs/MEMORY-WRITING.md, and creates the memory/ subdirectories. Runs scripts/setup-project.sh and guides the user through next steps. Trigger this when someone says: set up this project, initialize the agent pack, scaffold the project structure, add Claude Agent Pack to this repo, new project setup, onboard this repo. Do NOT use to verify an existing installation — use /system-check instead.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use research, tdd and 1 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.
  • NVIDIASkill

    research

    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 5 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

  • GoogleSkill

    code-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 3 projects that use this

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 3

    Distinctive

    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
  1. Distinctive:

    After the script completes, work through these follow-up steps with the user:

    line 38
  2. Distinctive:

    All follow-up skills are optional.

    line 54
  3. Very specific:

    Script not found: If scripts/setup-project.sh cannot be located, ask the user where they cloned the agent pack.

    line 58
  4. Distinctive:

    Target directory confusion: If the user's working directory and the target project directory differ (e.g., they want to set up a sibling …

    line 61

“Common” is measured: kept by at least 6 in 10 of the 19 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setup Project

Scaffold a project directory with the Claude Agent Pack structure.

1. Confirm the target directory

The target defaults to the current working directory. If the user specified a different path, use that. Confirm with the user if there is any ambiguity.

2. Locate the pack

Find the pack directory by locating scripts/setup-project.sh. If you cannot locate it, ask the user where they cloned the pack.

3. Run the setup script

bash <pack-dir>/scripts/setup-project.sh <target-dir>

Capture the full output.

4. Interpret the output

LineMeaning
[ok] CLAUDE.md (from docs/CLAUDE.template.md)Consumer block copied (overwrites any existing file). Its long-form rules are read on demand from the pack's installed agent-pack/references/ -- if that directory is missing, run the pack's install.sh
[ok] docs/CONVENTIONS.md (from template)Template copied — needs to be filled in
[--] docs/CONVENTIONS.md already exists, skippedExisting file preserved — no action needed
[ok] docs/MEMORY-WRITING.mdCopied successfully
[ok] memory/<subdir>/Directory created with .gitkeep

5. Guide next steps

After the script completes, work through these follow-up steps with the user:

  1. Commit the scaffolding — suggest the commit command printed by the script:
    git add CLAUDE.md docs/ memory/ && git commit -m 'chore: add Claude Agent Pack scaffolding'
  2. Ask about conventions — if docs/CONVENTIONS.md was created from the template, ask:

    "The conventions file was created from a template and needs to be filled in. Would you like me to run /conventions now to document your team's standards interactively?"

  3. Ask about onboarding — after the commit, ask:

    "Would you like me to run /onboard to generate a structured orientation for this codebase?"

  4. Ask about the repo map — offer to seed a durable structure map:

    "Would you like me to run /repo-map to generate a directory-level map of this codebase? It gets stored in memory/architecture/ (so it shares across sessions and syncs to Obsidian) and is read by /onboard, tech-lead, /plan, /refactor, and /scaffold."

All follow-up skills are optional. None blocks the others.

Gotchas

  • Script not found: If scripts/setup-project.sh cannot be located, ask the user where they cloned the agent pack. Do not attempt to recreate the script manually — the script has specific file content and permissions that are not reproducible from memory.
  • Running setup on a non-empty project: The script preserves an existing docs/CONVENTIONS.md (already exists, skipped) but overwrites CLAUDE.md and docs/MEMORY-WRITING.md every run, so a customised CLAUDE.md is replaced by the template. Confirm with the user before running it on a project whose CLAUDE.md they have edited.
  • Forgetting to commit the scaffolding: The scaffolded files (CLAUDE.md, docs/, memory/) are meaningless until committed. Always suggest the commit command in step 5.1 before moving to follow-up skills.
  • Target directory confusion: If the user's working directory and the target project directory differ (e.g., they want to set up a sibling repo), confirm the target path explicitly before running the script.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.