This is pure infrastructure. It's a configuration layer that lets skills automatically chain together based on hooks like after_complete, on_error, or before_start. You define triggers in YAML front matter, set modes like auto, ask_first, or background, and skills fire each other off when conditions are met. The vision is clear: PRD planner finishes, kicks off self-improving-agent in the background, which triggers create-pr with a confirmation prompt, which logs to session-logger. In practice, you're architecting workflow choreography instead of hardcoding sequences. The risk is obvious though. Get your conditions wrong and you'll either spam the user with confirmations or create circular dependencies that never terminate.

skills.sh installs
628
GitHub stars
66
last updated
Jul 14, 2026

Install

$ npx -y skills add charon-fan/agent-playbook --skill auto-trigger --agent claude-code

Installs into .claude/skills of the current project.

Files

Auto-Trigger Hooks

This skill defines trigger intent between skills. When a skill completes its workflow, a host runtime or agent may read this metadata, record a pending follow-up, and execute the next skill only when that action is supported and safe for the current session.

Hook Definitions

PRD Creation Chain

prd_complete:
  triggers:
    - skill: self-improving-agent
      mode: background
      condition: PRD file exists and is complete
    - skill: session-logger
      mode: auto
      context: "PRD created for {feature_name}"

prd_implemented:
  triggers:
    - skill: session-logger
      mode: auto
      context: "Implemented PRD: {feature_name}"

Implementation Chain

implementation_complete:
  triggers:
    - skill: code-reviewer
      mode: ask_first
      message: "Implementation complete. Run code review?"
    - skill: create-pr
      mode: ask_first
      condition: user_requested_submission

Session Management

session_start:
  auto_triggers:
    - skill: session-logger
      action: create_session_file

session_end:
  auto_triggers:
    - skill: session-logger
      action: update_session_file

Sponsors

Details

Repository
github.com/charon-fan/agent-playbook
Category
AI & Agent Building
First seen
May 16, 2026

More from charon-fan/agent-playbook

All 24
1narumiruna avatarsvg-illustrationnarumiruna/agent-skillssvg illustration628skills.sh installs
2alirezarezvani avatarboard-meetingalirezarezvani/claude-skillsMulti-agent board meeting protocol for strategic decisions. Runs a structured 6-phase deliberation: context loading, independent C-suite contributions (isolated622skills.sh installs
3sugarforever avatarpublish-substack-articlesugarforever/01coder-agent-skillsPublish Markdown articles to Substack as drafts. Use when user wants to publish a Markdown file to Substack, or mentions "发布到 Substack", "Substack article", "pu609skills.sh installs
4tencentcloudbase avatarcloudbasetencentcloudbase/skillsUse this skill when you develop, design, build, deploy, debug, migrate, or troubleshoot CloudBase (腾讯云开发, 云开发, TCB, 微信云开发) projects. Covers Web, 微信小程序, 小程序, uni608skills.sh installs
5alirezarezvani avataragenthubalirezarezvani/claude-skillsMulti-agent collaboration plugin that spawns N parallel subagents competing on the same task via git worktree isolation. Agents work independently, results are 599skills.sh installs
6therealharpaljadeja avatarmonskilltherealharpaljadeja/monskillsSet of skills for developing/building apps on Monad. Always start with this skill, this skill helps the agent/llm maneuver and choose the right skills for the t599skills.sh installs