Auto Trigger
Wire automatic follow-up skills (session-logger, code-reviewer, self-improving-agent) after PRD or implementation milestones in agent-playbook workflows.
Overview
Auto-Trigger is an agent skill for the Build phase that defines YAML hook relationships so playbook skills automatically chain to session-logger, reviewers, and improvement skills after milestones.
Install
npx skills add https://github.com/charon-fan/agent-playbook --skill auto-triggerWhat is this skill?
- Configuration-only skill: other skills reference hooks—not meant for direct invocation
- PRD creation chain: prd_complete triggers self-improving-agent (background) and session-logger (auto)
- PRD implemented chain: prd_implemented triggers session-logger with feature context
- Implementation chain: implementation_complete triggers code-reviewer (per excerpt)
- YAML hook patterns for after_complete with mode auto or background and conditions
- Documents named chains: PRD creation, PRD implemented, and implementation completion hooks
Adoption & trust: 568 installs on skills.sh; 58 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your agent finishes a PRD or implementation step but nothing reliably triggers logging, review, or follow-up skills unless you remember to invoke them manually.
Who is it for?
Builders standardizing agent-playbook workflows who already use workflow-orchestrator or hook front matter on feature skills.
Skip if: Anyone trying to run a one-off task by invoking auto-trigger directly—the readme states it is not intended for direct invocation.
When should I use this skill?
You are authoring or extending agent-playbook skills that need after_complete or milestone hooks—via workflow-orchestrator or front matter references, not by invoking auto-trigger directly.
What do I get? / Deliverables
Hook definitions let workflow-orchestrator or referencing skills run the next skill in the chain with the right mode and context after prd_complete or implementation_complete.
- Hook definition YAML for prd_complete, prd_implemented, and implementation_complete chains
- Documented trigger modes (auto, background) and conditions
Recommended Skills
Journey fit
Lives on Build/agent-tooling because it configures how your agent chain fires the next skill—not end-user product features. Agent-tooling is the shelf for hook definitions, orchestration config, and skill-to-skill automation referenced by other playbook skills.
How it compares
Hook configuration layer for skill chains, not a replacement for workflow-orchestrator or individual task skills.
Common Questions / FAQ
Who is auto-trigger for?
Solo builders maintaining charon-fan agent-playbook stacks who want declarative after_complete hooks between PRD, implementation, logging, and review skills.
When should I use auto-trigger?
During Build agent-tooling setup when you define or extend PRD and implementation chains; reference its YAML from other skills rather than calling it standalone.
Is auto-trigger safe to install?
It declares Read, Write, Edit tool allowance for config maintenance; review the Security Audits panel on this Prism page and restrict write paths in your agent policy.
Workflow Chain
Requires first: workflow orchestrator
Then invoke: session logger, code reviewer
SKILL.md
READMESKILL.md - Auto Trigger
# Auto-Trigger > Configuration skill that defines automatic trigger relationships between skills. ## Installation This skill is part of the [agent-playbook](../../README.md) collection. ## Usage This is a configuration skill and is **not** intended for direct invocation. Typical usage is through `workflow-orchestrator`, which reads the hook definitions from this skill and executes follow-up actions. ## Example ``` # In another skill's front matter hooks: after_complete: - trigger: session-logger mode: auto ``` --- name: auto-trigger description: Workflow automation hooks for agent-playbook skills. This skill defines automatic triggers between skills - DO NOT use directly, it's a configuration skill that other skills reference. allowed-tools: Read, Write, Edit --- # Auto-Trigger Hooks This skill defines automatic trigger relationships between skills. When a skill completes its workflow, it should automatically trigger the next skill in the chain. ## Hook Definitions ### PRD Creation Chain ```yaml 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 ```yaml implementation_complete: triggers: - skill: code-reviewer mode: ask_first message: "Implementation complete. Run code review?" - skill: create-pr mode: auto condition: changes_staged ``` ### Session Management ```yaml session_start: auto_triggers: - skill: session-logger action: create_session_file session_end: auto_triggers: - skill: session-logger action: update_session_file ``` ## Hook Format in Skills To add auto-trigger capability to a skill, add to its front matter: ```yaml --- name: my-skill description: Skill description allowed-tools: Read, Write, Edit hooks: before_start: - trigger: session-logger mode: auto context: "Start {skill_name}" after_complete: - trigger: self-improving-agent mode: background - trigger: session-logger mode: auto on_error: - trigger: self-improving-agent mode: background --- ``` ## Implementation Guide When a skill completes its workflow: 1. **Check `hooks`** in its own front matter (`before_start`, `after_complete`, `on_error`, `on_progress`) 2. **For each hook:** - If `mode: auto`, trigger immediately - If `mode: background`, trigger without waiting - If `mode: ask_first`, ask user before triggering - If `condition:` exists, check it first 3. **Pass context** to the triggered skill ## Example Integration ### prd-planner should add: ```yaml --- name: prd-planner description: Creates PRDs using persistent file-based planning... allowed-tools: Read, Write, Edit, Bash, Grep, Glob, AskUserQuestion, WebSearch hooks: after_complete: - trigger: self-improving-agent mode: background context: "PRD created at {prd_file}" - trigger: session-logger mode: auto context: "PRD creation complete" --- ``` ### self-improving-agent already has: ```yaml --- name: self-improving-agent description: Universal self-improvement that learns from all skill experiences... allowed-tools: Read, Write,Edit, Bash, Grep, Glob, WebSearch hooks: after_complete: - trigger: create-pr mode: ask_first condition: skills_modified - trigger: session-logger mode: auto context: "Self-improvement cycle complete" on_error: - trigger: self-improving-agent mode: background --- ``` ### create-pr should add: ```yaml --- name: create-pr description: Creates pull requests with bilingual documentation updates... allowed-tools: Read, Write, Edit, Bash, Grep, AskUserQuestion hooks: after_complete: - trigger: session-logger