agentleFS
jcurbelojcurbelo/agent-seed/.claude/skills/setup/SKILL.md

setup

Skill8 starsChanged 8 months agoMITView on GitHub

Interactive setup wizard. Personalizes your agent-seed with voice, context, agents, and integrations. Run this first.

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

20 rules. 0 are common, 13 are distinctive, and 7 are very specific to this project.

  • 0

    Common

    Most of the 168 edited versions we read keep these.

  • 13

    Distinctive

    This author's own choices. Worth a look.

  • 7

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check what's available:

    line 12
  2. Distinctive:

    If installed: "I'll create PRs for all changes so you can review them."

    line 16
  3. Distinctive:

    If not: "No worries! I'll commit changes directly.

    line 17
  4. Distinctive:

    Ask these questions one at a time.

    line 22
  5. Distinctive:

    Ask: "I'd love to learn your communication style so I can draft messages that sound like you.

    line 34
  6. Very specific:

    Leave context/voice/patterns.md with a template for later

    line 46
  7. Distinctive:

    Leave template files in place

    line 49
  8. Distinctive:

    All defaults + suggest: drafter (writing), tracker (issue tracking)

    line 68
  9. Distinctive:

    Always include: todo-manager, reflection (these are core)

    line 71
  10. Distinctive:

    Ask: "Based on your role as [X], I'd suggest these agents: [list].

    line 73
  11. Very specific:

    Create the agent .md file with proper frontmatter

    line 76
  12. Very specific:

    Add it to .claude/agents/index.md routing table

    line 77
  13. Distinctive:

    Ask: "Do you want to connect any of these?

    line 81
  14. Distinctive:

    Create the agent definition

    line 91
  15. Very specific:

    Add safety hooks to .claude/settings.json if needed (e.g., Slack read-only)

    line 93
  16. Very specific:

    Update context/index.md to link to all created context files

    line 97
  17. Very specific:

    Update memory/MEMORY.md with basic profile info

    line 98
  18. Distinctive:

    If gh CLI is available:

    line 101
  19. Very specific:

    Commit: "feat: initial agent-seed setup"

    line 104
  20. Distinctive:

    If no gh CLI:

    line 107

“Common” is measured: kept by at least 6 in 10 of the 168 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 - Setup Wizard

Interactive wizard that personalizes your agent-seed installation. Can be re-run anytime to add new agents or integrations.

Step 0: Environment Check

Check what's available:

  1. git — run git --version. If missing, stop and tell the user to install git.
  2. gh CLI — run gh --version.
    • If installed: "I'll create PRs for all changes so you can review them."
    • If not: "No worries! I'll commit changes directly. You can install the GitHub CLI later if you want PR-based workflows: https://cli.github.com"
  3. Detect LLM tool — check which tool is running (Claude Code, Cursor, etc.) and note it for context.

Step 1: Identity

Ask these questions one at a time. Wait for each answer before proceeding.

  1. "What's your name?"
  2. "What do you do? (e.g., software engineer, product manager, designer, founder, student, etc.)"
  3. "What tools and services do you use daily? (e.g., GitHub, Linear, Slack, Jira, Notion, etc.)"

Save answers to:

  • context/work/index.md — role and overview
  • context/work/tools.md — tools and services

Step 2: Voice (Optional but Encouraged)

Ask: "I'd love to learn your communication style so I can draft messages that sound like you. You can:"

  • Option A: "Paste 5-10 messages you've sent recently (Slack, email, etc.)"
  • Option B: "Describe your style: formal or casual? Emoji or no emoji? Short or detailed?"
  • Option C: "Skip this for now — you can always add it later"

If Option A:

  • Analyze the messages for patterns: tone, capitalization, punctuation, greetings, closings, emoji usage, sentence length, formality level
  • Generate context/voice/index.md with a voice profile
  • Generate context/voice/patterns.md with extracted patterns and examples

If Option B:

  • Generate a basic context/voice/index.md from the description
  • Leave context/voice/patterns.md with a template for later

If Option C:

  • Leave template files in place

Step 3: Agent Selection

Based on the user's role, suggest a starter set of agents:

Software Engineer:

  • coder, reviewer, researcher, todo-manager, reflection (all ship by default)
  • Suggest: pr-agent (branch + PR creation)

Product Manager:

  • researcher, todo-manager, reflection (ship by default)
  • Suggest: note-taker (meeting notes), tracker (issue tracking)

Designer:

  • researcher, todo-manager, reflection (ship by default)
  • Suggest: feedback-collector (design review)

Founder / Generalist:

  • All defaults + suggest: drafter (writing), tracker (issue tracking)

Any role:

  • Always include: todo-manager, reflection (these are core)

Ask: "Based on your role as [X], I'd suggest these agents: [list]. Want me to add any of these? Or describe what else you need and I'll create a custom agent."

For each selected agent:

  1. Create the agent .md file with proper frontmatter
  2. Add it to .claude/agents/index.md routing table

Step 4: Integrations (Optional)

Ask: "Do you want to connect any of these? (just say which ones)"

IntegrationWhat it adds
Slack (read-only)slack-reader agent + safety hook to block posting
GitHubpr-agent for branch + PR workflows
Lineartracker agent for issue management
Jiratracker agent (Jira variant)

For each selected integration:

  1. Create the agent definition
  2. Update .claude/agents/index.md
  3. Add safety hooks to .claude/settings.json if needed (e.g., Slack read-only)

Step 5: Save and Commit

  1. Update context/index.md to link to all created context files
  2. Update memory/MEMORY.md with basic profile info
  3. Validate everything: run scripts/check-markdown-policy.sh

If gh CLI is available:

  1. Create branch: feat/initial-setup
  2. Stage all generated files
  3. Commit: "feat: initial agent-seed setup"
  4. Push and create PR with summary of what was configured

If no gh CLI:

  1. Stage all generated files
  2. Commit: "feat: initial agent-seed setup"
  3. Tell the user what was created

Step 6: Next Steps

Tell the user: "You're all set! Here's what you can do now:"

  • /standup — start your day with a briefing
  • /eod — end your day, capture learnings
  • /learn — let the system improve itself
  • "Edit context/voice/ anytime to refine your voice profile"
  • "The system will learn your preferences over time and propose improvements via PRs"

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.