Workflow Orchestrator
Chain follow-up agent skills automatically when a milestone finishes instead of manually prompting each next step.
Overview
Workflow Orchestrator is an agent skill most often used in Build (also Ship, Operate) that executes configured hook chains when a skill milestone completes.
Install
npx skills add https://github.com/charon-fan/agent-playbook --skill workflow-orchestratorWhat is this skill?
- Reads auto-trigger hook definitions from skills/auto-trigger/SKILL.md
- Runs follow-ups in auto, background, or ask_first modes
- Activates on milestones such as PRD complete or implementation done
- Logs execution context to session-logger after completion
- Supports explicit phrases like "complete workflow" or "finish the process"
- 3 hook execution modes: auto, background, ask_first
Adoption & trust: 646 installs on skills.sh; 58 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You finish one agent skill milestone but the playbook still expects logging, triggers, or follow-up skills you keep forgetting to invoke.
Who is it for?
Solo builders using charon-fan/agent-playbook with auto-trigger hooks who want PRD-to-implementation workflows to continue without manual re-prompting.
Skip if: One-shot tasks with no hook config, or teams that do not use Claude Code skill hooks and session-logger in the same playbook layout.
When should I use this skill?
A skill completes its main workflow, a milestone is reached, or the user says complete workflow or finish the process.
What do I get? / Deliverables
Configured after_complete hooks run in the right mode and session-logger captures context so the next skill in the chain can start with continuity.
- Executed hook chain per configuration
- Session context logged via session-logger
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Workflow hooks attach to completion events during product work (PRD done, implementation done), so the canonical shelf is agent tooling in Build. It coordinates skills and hooks rather than shipping app code—placement under agent-tooling matches playbook-style orchestration.
Where it fits
After implementation skill marks done, orchestrator runs auto hooks for logging and the next validation skill.
When PRD creation completes, triggers configured follow-ups without you restating the playbook.
Post-launch checklist skill completion kicks background hooks for distribution or doc updates.
How it compares
Use instead of copy-pasting "now do X" after every skill; it is orchestration glue, not a replacement for individual domain skills.
Common Questions / FAQ
Who is workflow-orchestrator for?
Indie and solo builders running multi-skill Claude Code playbooks who define milestones and want automatic follow-up actions.
When should I use workflow-orchestrator?
At Build milestones after PRD or implementation work, at Ship when a review skill completes and logging or triggers should fire, and in Operate when you say "complete workflow" to flush a configured chain.
Is workflow-orchestrator safe to install?
It can Read, Write, Edit, Bash, and Grep per skill metadata—review hook targets and side effects in your repo; check the Security Audits panel on this Prism page before trusting auto mode.
Workflow Chain
Then invoke: session logger
SKILL.md
READMESKILL.md - Workflow Orchestrator
# Workflow Orchestrator > A Claude Code skill that coordinates multi-skill workflows using hook definitions. ## Installation This skill is part of the [agent-playbook](../../README.md) collection. ## Usage ``` You: Complete workflow You: Finish the process and trigger next steps ``` ## How It Works - Reads hook definitions from `skills/auto-trigger/SKILL.md` - Executes follow-up actions based on `auto`, `background`, or `ask_first` modes - Logs progress and context to `session-logger` --- name: workflow-orchestrator description: Automatically coordinates multi-skill workflows and triggers follow-up actions. Use when completing PRD creation, implementation, or any milestone that should trigger additional skills. This skill reads the auto-trigger configuration and executes the workflow chain. allowed-tools: Read, Write, Edit, Bash, Grep, AskUserQuestion metadata: hooks: after_complete: - trigger: session-logger mode: auto reason: "Save workflow execution context" --- # Workflow Orchestrator A skill that automatically coordinates workflows across multiple skills, triggering follow-up actions at appropriate milestones. ## When This Skill Activates This skill should be triggered automatically 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 ``` ┌─────────────────────────────────────────────────────────────┐ │ Workflow Orchestration │ ├─────────────────────────────────────────────────────────────┤ │ │ │ 1. Detect Milestone → 2. Read Hooks → 3. Execute Chain │ │ │ │ prd-planner complete │ │ ↓ │ │ workflow-orchestrator │ │ ↓ │ │ ┌─────────────────────────────────────┐ │ │ │ auto-trigger self-improving-agent │ (background) │ │ │ auto-trigger session-logger │ (auto) │ │ └─────────────────────────────────────┘ │ │ │ └─────────────────────────────────────────────────────────────┘ ``` ## Trigger Configuration Read trigger definitions from `skills/auto-trigger/SKILL.md`: ```yaml hooks: after_complete: - trigger: self-improving-agent mode: background - trigger: session-logger mode: auto on_error: - trigger: self-improving-agent mode: background ``` ## Execution Modes | Mode | Behavior | Use When | |------|----------|----------| | `auto` | Execute immediately, no confirmation | Logging, status updates | | `background` | Execute without blocking | Reflection, analysis | | `ask_first` | Ask user before executing | PRs, deployments, major changes | ## Milestone Detection ### PRD Complete ```markdown Detected when: - docs/{scope}-prd.md exists - All phases in {scope}-prd-task-plan.md are checked - Status shows "COMPLETE" Actions: 1. Trigger self-improving-agent (background) 2. Trigger session-logger (auto) ``` ### Implementation Complete ```markdown Detected when: - All PRD requirements implemented - Tests pass - Code committed Actions: 1. Trigger code-reviewer (ask_first) 2. Trigger create-pr if changes staged 3. Trigger session-logger (auto) ``` ### Self-Improvement Complete ```markdown Detected when: - Reflection complete - Patterns abstracted - Skill files modified Actions: 1. Trigger create-pr (ask_first) 2. Trigger session-logger (auto) ``` ### Universal Learning (Any Skill Complete) ```markdown Detected when: - ANY skill completes its workflow - User provides feedback - Error or issue encountered Actions: 1. Trigger self-improving-agent (backg