agentleFS
websublimewebsublime/mister-anderson/skills/setup/SKILL.md

setup

Skill3 starsChanged 7 months agoMITView on GitHub

Bootstrap project orchestration with beads task tracking.

  • Deletes or force-pushes

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord 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.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

Show its rules and text

We split this skill into the rules it gives an agent

18 rules. 0 are common, 10 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 10

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    beads CLI must be installed (>= 0.60): Test with bd --version.

    line 18
  2. Distinctive:

    If either check fails, stop the setup process.

    line 21
  3. Distinctive:

    Before doing anything else, detect if this is a fresh setup or a resume after restart.

    line 36
  4. Distinctive:

    Project info: Ask the user about the project name and overview

    line 63
  5. Distinctive:

    Project docs: Ask the user where to find documents (PRD, spec, plans)

    line 64
  6. Very specific:

    Detect tech stack: Check for package.json (JS/TS), Cargo.toml (Rust), go.mod (Go), pyproject.toml/requirements.txt (Python)

    line 65
  7. Distinctive:

    If no docs provided, skip that step.

    line 67
  8. Very specific:

    Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/setup/templates/CLAUDE.md and fill in project info.

    line 73
  9. Distinctive:

    Write to the root of the project (generate from template, do NOT copy verbatim).

    line 87
  10. Very specific:

    Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/setup/templates/AGENTS.md.

    line 93
  11. Very specific:

    Ensure .claude/agents/ exists, then dispatch:

    line 99
  12. Distinctive:

    Check for legacy local copies from pre-0.1.0 versions:

    line 125
  13. Distinctive:

    Ask for confirmation before removing

    line 135
  14. Very specific:

    Remove legacy skills (rm -rf .claude/skills/), hooks (rm -rf .claude/hooks/), and core agents only

    line 136
  15. Distinctive:

    Verify CLAUDE.md exists at project root

    line 144
  16. Distinctive:

    Verify AGENTS.md exists at project root

    line 145
  17. Very specific:

    Verify .claude/agents/ contains dynamic supervisors

    line 146
  18. Very specific:

    Verify .claude/.mister-anderson-version matches expected version

    line 147

“Common” is measured: kept by at least 6 in 10 of the 171 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

Set up lightweight multi-agent orchestration with git-native task tracking for Claude Code.


<on-init> This skill has no arguments. It detects project state automatically. </on-init><on-check> 1. **beads CLI must be installed (>= 0.60).** Test with `bd --version`. 2. **Dolt SQL server must be reachable.** beads 0.56+ requires a running Dolt sql-server (port 3307 or 3306).

If either check fails, stop the setup process. </on-check>

<on-check-fail if="beads"> beads CLI not found. Install from: https://github.com/steveyegge/beads/tree/main </on-check-fail><on-check-fail if="dolt"> Dolt SQL server not reachable. beads 0.56+ requires a running Dolt sql-server on port 3307 or 3306. </on-check-fail><on-execute>

Step 0: Detect Setup State

Before doing anything else, detect if this is a fresh setup or a resume after restart.

bd list 2>/dev/null && echo "BEADS_INITIALIZED" || echo "BEADS_NOT_INITIALIZED"

If BEADS_NOT_INITIALIZED:

  • Init: bd init
  • Config custom statuses: bd config set status.custom "in-review"

If BEADS_INITIALIZED: proceed to next check.

ls ./CLAUDE.md 2>/dev/null && echo "BOOTSTRAP_COMPLETE" || echo "FRESH_SETUP"

If BOOTSTRAP_COMPLETE: Bootstrap already ran — do NOT ask for project info again. Skip to Step 4.

If FRESH_SETUP: Proceed to Step 1.


Step 1: Get Project Info (Fresh Setup Only)

YOU MUST GET PROJECT INFO BEFORE PROCEEDING TO STEP 2.

  1. Project directory: Get current working directory
  2. Project info: Ask the user about the project name and overview
  3. Project docs: Ask the user where to find documents (PRD, spec, plans)
  4. Detect tech stack: Check for package.json (JS/TS), Cargo.toml (Rust), go.mod (Go), pyproject.toml/requirements.txt (Python)

If no docs provided, skip that step.


Step 2: Create CLAUDE.md

Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/setup/templates/CLAUDE.md and fill in project info.

MANDATORY: Create a Repository Structure section by scanning the project directory. Example:

project-name/
├── packages/
│   ├── core/                         # Core logic
│   └── plugin/                       # Plugin wrapper
├── docs/                             # Planning and architecture
├── .github/workflows/                # CI/CD
└── config files

Write to the root of the project (generate from template, do NOT copy verbatim).


Step 3: Create AGENTS.md

Use the template at ${CLAUDE_PLUGIN_ROOT}/skills/setup/templates/AGENTS.md. Write to the root of the project.


Step 4: Create Tech Supervisors

Ensure .claude/agents/ exists, then dispatch:

Agent(
    subagent_type="discovery",
    prompt="Detect tech stack and create supervisors for this project. Write supervisor files to .claude/agents/."
)

Do NOT add extra parameters unless the user explicitly requests it.


Step 5: Write Version File

PLUGIN_VERSION=$(grep -o '"version": *"[^"]*"' "$CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json" | cut -d'"' -f4)
echo "$PLUGIN_VERSION" > ./.claude/.mister-anderson-version

The version is read dynamically from plugin.json — no manual update needed when bumping.


Step 6: Cleanup Legacy Local Copies

Check for legacy local copies from pre-0.1.0 versions:

ls -d .claude/skills/*/ 2>/dev/null
ls .claude/hooks/ 2>/dev/null
ls .claude/agents/{architect,product-manager,research,discovery,code-reviewer,qa-gate,beads-owner}.md 2>/dev/null

If legacy files found:

  • Inform user these are now provided by the plugin system
  • Ask for confirmation before removing
  • Remove legacy skills (rm -rf .claude/skills/), hooks (rm -rf .claude/hooks/), and core agents only
  • NEVER remove *-supervisor.md files created by Discovery

If no legacy files found: skip this step.

</on-execute><on-complete> 1. Verify CLAUDE.md exists at project root 2. Verify AGENTS.md exists at project root 3. Verify `.claude/agents/` contains dynamic supervisors 4. Verify `.claude/.mister-anderson-version` matches expected version 5. Report setup summary to user </on-complete><on-next> Setup complete. Recommend starting the product pipeline with `/requirements` or checking project state with `/workflow`. </on-next>

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.