skills.rest
product-on-purpose
product-on-purposeOFFICIAL
Explore all skills by this author →
GitHub

utility-pm-workflow-orchestrator

Runs an ordered sequence of pm-skills against one input with checkpointed go/no-go pauses.

640|81|Updated Jan 9, 2026
Search Tags:#product management#checkpointing#action plan#dry run#skill chaining#multi-step execution#Workflow orchestration
One-click install
npx skills add https://github.com/product-on-purpose/pm-skills --skill utility-pm-workflow-orchestrator
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: utility-pm-workflow-orchestrator
Source: https://github.com/product-on-purpose/pm-skills/tree/main/skills/utility-pm-workflow-orchestrator
Command: npx skills add https://github.com/product-on-purpose/pm-skills --skill utility-pm-workflow-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Running several product management skills in sequence normally means manually invoking each one, re-pasting outputs, and babysitting every step. This Skill executes an ordered chain of pm-skills against shared context, pausing for approval between steps and stopping automatically when a step fails or returns empty.

Core Features & Use Cases

  • Mode A plan execution: Runs the runnable Section 7 prompts from a saved prioritized action plan in document order, with a top-3 runnable cap and manual steps surfaced separately.
  • Mode B ad-hoc chains: Executes a user-named chain of skills (for example deliver-prd then deliver-user-stories), with an optional --thread flag that passes each step's confirmed artifact to the next step.
  • Run modes and safety: CHECKPOINTED by default with approve/edit/skip/redo pauses, GUARDED AUTO for unattended clean runs, stop-on-fail semantics, and a --dry-run readiness probe that validates parsing and tool capability before any real execution.
  • Use Case: You have a saved quarterly action plan and want its top three runnable prompts executed in order, each artifact written to a run directory, with your approval required before advancing.

Quick Start

Ask the AI to run your saved prioritized action plan's Section 7 prompts in order with a confirmation pause after each step, starting with a dry run.

Frequently Asked Questions about utility-pm-workflow-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run multiple pm-skills in sequence automatically?▼

Invoke the orchestrator with either a saved prioritized action plan (Mode A) or a named chain of skills (Mode B). It walks the steps in order, pausing for your approval after each OK step, and stops the run if any step fails or returns empty.

What is the difference between Mode A and Mode B chain execution?▼

Mode A parses Section 7 of a saved foundation-prioritized-action-plan and runs up to three runnable prompts in document order. Mode B runs an ad-hoc chain you name directly, with no step cap, and supports the --thread flag to pass each step's artifact to the next.

Does the workflow orchestrator work outside Claude Code?▼

Yes, on clients like Codex CLI, Cursor, Windsurf, Copilot CLI, and Gemini CLI it reads the sub-agent definition and executes each step inline. That path is experimental, so run --dry-run first to verify file-write and Bash capability.

When should I use the workflow builder instead of the orchestrator?▼

Use utility-pm-workflow-builder when you want to author a durable, reusable named workflow. The orchestrator only runs an ephemeral chain once and persists no workflow definition; it also does not replace curated workflow-* commands like workflow-foundation-sprint.

What happens when a step in the chain fails or returns empty?▼

A FAILED step halts the entire run with a terminal block describing the failure. An EMPTY step always pauses for confirmation, even in guarded auto mode, and never silently advances to completion.

Related Skills

Explore More Product & Management Skills→
davila7davila7
30.5k

product-manager-toolkit

Prioritize features with RICE scoring and analyze customer interview transcripts using Python scripts.

Community
Intermediate
muammeryldrm42muammeryldrm42

Sprint Planning

Automate sprint planning with prioritized plans, risk analysis, and rollback guidance.

Community
Intermediate
sluongngsluongng
6

cli-creator

Scaffold a composable CLI with a stable JSON surface from API docs or OpenAPI specs.

Community
Advanced
m2ai-portfoliom2ai-portfolio
4

compound-skill-orchestrator

Chains multiple existing skills into a unified multi-stage workflow with isolated contexts.

Official
Advanced