What do I need to use Action Runner?

The recommendations to act on; The connected action MCP; Approval posture.

Is Action Runner free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

Action Runner

Q: How do I know the Action Runner output is good?

The skill verifies itself against its own quality checks: A dry-run plan is shown before anything executes; Every action has a risk level; 🔴 actions are individually approved; Execution stays within the named scope and uses only the connected MCP; Each executed action is recorded back to the brain with an `[external]` tag.

🟡 Experimental🕐 updated 2026-06-24 🔷 SkillSpec L3 pm-cross

Turn a skill's recommendations into real, executed actions — open the tickets, file the issues, post the updates — safely: dry-run preview, risk-classified, approval-gated, then recorded back to the brain. Use when asked to act on a plan, file tickets from a checklist, create issues from a PRD, execute the recommended next steps, or wire a skill's output into GitHub/Linear/Slack. Produces a dry-run actions plan with per-action risk, executes only after approval via the connected action MCP, and logs what was done. Nothing acts silently.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸The recommendations to act on — (a launch checklist, PRD requirements, postmortem follow-ups…).

▸The connected action MCP — and targets — which GitHub repo / Linear project / Slack channel. Scope is limited to what the user names; never act outside it.

▸Approval posture — what may run with a single OK vs. what needs per-action confirmation.

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓A dry-run plan is shown before anything executes

✓Every action has a risk level; 🔴 actions are individually approved

✓Execution stays within the named scope and uses only the connected MCP

✓Each executed action is recorded back to the brain with an `[external]` tag

✓On failure, it stops and reports rather than retrying blindly

⚠️ What it refuses to do

Executing anything without showing the dry-run plan first

Treating an outbound/destructive action (post, email, delete, deploy) as low-risk

Acting outside the scope the user named, or fanning out to many targets

"Helpfully" doing more than was approved

Forgetting to record what was done — the brain must reflect reality

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Start with

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="action-runner"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Action Runner is one of 599 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog