Coordinates multi-skill workflows and records or runs follow-up actions when the host runtime supports them. Use when completing PRD creation, implementation, or any milestone that should be evaluated for additional skills.

Workflow Orchestrator A skill that coordinates workflows across multiple skills by evaluating hook metadata, recording pending follow ups, and running only the actions that are safe and supported in the current host runtime. When This Skill Activates This skill should be used when: A skill completes its main workflow A milestone is reached (PRD complete, implementation done, etc.) User says "complete workflow" or "finish the process" How It Works Trigger Configuration Read trigger definitions from skills/auto trigger/SKILL.md : Execution Modes Mode Behavior Use When auto Run or record a low risk follow up when the host supports it Logging, status updates background Record a non blocking follow up Reflection, analysis ask first Ask user before executing PRs, deployments, major changes Milestone Detection PRD Complete Implementation Complete Self Improvement Applied Learning Candidate (Skill Complete) Error Handling (on error) Detected when: A command returns non zero exit code Tests fail after following skill guidance User reports the guidance produced incorrect results Actions: 1. Record self improving agent (background) for self correction 2. Run or record session logger to capture error context Hook Implementation in Skills To declare follow up metadata, add this section to any skill's SKILL.md: yaml hooks: after complete: trigger: skill name mode: auto background ask first context: "relevant context" on error: trigger: self improving agent mode: background ┌─────────────────────────────────────────────────────────────┐ │ Skill Completes With Evidence │ └──────────────┬──────────────────────────────────────────────┘ │ ↓ ┌──────────────────────┐ │ workflow orchestrator │ └──────────┬───────────┘ │ ┌──────────┴─────────┐ ↓ ↓ self improving agent session logger ↓ ↓ Capture candidate Save bounded context ↓ ↓ Validate evidence Log session ↓ Apply to named owner ↓ create pr (only if submission was requested) Workflow Examples Example 1: PRD Creation Workflow Example 2: Full Feature Workflow Each milestone can produce a self improving agent follow up, but durable skill edits still require validation or explicit approval. Implementation Steps Step 1: Detect Milestone Check for completion indicators: Step 2: Read Trigger Config Step 3: Record or Execute Hooks For each hook in order (before start, after complete, on error): 1. Check if condition is met 2. Record or execute based on mode and host support 3. Pass context to triggered skill 4. Wait/continue based on mode Step 4: Update Status Log what was triggered and the result: Skills with Auto Trigger Skill Triggers After prd planner self improving agent, session logger self improving agent No automatic PR; applied changes may declare a logging follow up prd implementation precheck self improving agent, session logger code reviewer self improving agent, session logger create pr session logger refactoring specialist self improving agent, session logger debugger self improving agent, session logger Adding Follow up Metadata to Existing Skills To add follow up metadata to an existing skill, add to the end of its SKILL.md: yaml hooks: after complete: trigger: session logger mode: auto context: "Save session context" For more complex triggers, specify mode and context: yaml hooks: after complete: trigger: next skill mode: background context: "Description" trigger: session logger mode: auto context: "Save session" trigger: create pr mode: ask first context: "Create PR if files modified" on error: trigger: self improving agent mode: background Best Practices 1. Log only when supported and appropriate Session logging is a bounded optional follow up 2. Ask before major actions PRs, deployments, destructive changes 3. Background for analysis Reflection, evaluation, optimization 4. Auto for status Logging, status updates, bookmarks 5. Don't create loops Ensure chains terminate

workflow-orchestrator