What do I need to use Autopilot Charter?

The recurring outputs; Who consumes each one; Where the inputs live; Tolerance for error.

Is Autopilot Charter 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.

Autopilot Charter

Q: How do I know the Autopilot Charter output is good?

The skill verifies itself against its own quality checks: Every ritual has an explicit call — including the ones kept manual, with the reason stated; No ritual is marked Automate with unreachable inputs ("somehow reads the dashboard" is Assist at best); Every Automate has all four guardrails, including kill criteria; The rollout starts with a low-blast-radius ritual, not the board update.

🔵 Stable🕐 updated 2026-10-06 ✅ 4.8/5 🔷 SkillSpec L3 pm-autopilot

Decide which of your recurring rituals to put on autopilot — and which to keep manual. Use when asked what to automate, how to set up recurring AI runs, which reports or briefings could run on a schedule, or to design an automation charter for a team. Produces a ritual inventory with automate/assist/keep-manual calls, guardrails per ritual, and a rollout order.

▶ Run it free — no key needed 📝 Grade your existing draft 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“What to automate?”“How to set up recurring AI runs?”“Which reports?”“Design an automation charter for a team.”

What to give it

▸The recurring outputs — the user or team produces (weekly updates, monthly reviews, monitors, digests)

▸Who consumes each one — and what they do with it

▸Where the inputs live — (git, analytics, CRM, inbox, notes) and whether an agent can reach them

▸Tolerance for error — per artifact — what happens if a run is wrong or missing?

✅ 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.

✓Every ritual has an explicit call — including the ones kept manual, with the reason stated

✓No ritual is marked Automate with unreachable inputs ("somehow reads the dashboard" is Assist at best)

✓Every Automate has all four guardrails, including kill criteria

✓The rollout starts with a low-blast-radius ritual, not the board update

✓The charter names who owns each automated ritual — autopilot still has a pilot

⚠️ What it refuses to do

Do not classify everything as Automate — a charter with no keep-manual entries wasn't a decision

Do not automate a ritual whose consumers haven't been told it's now machine-drafted

Do not skip failure behaviour — a monitor that silently stops running is worse than no monitor

Do not automate judgement-bearing artifacts (performance feedback, strategy calls) no matter how reachable the inputs

Do not set a schedule tighter than the inputs actually change — a daily brief on weekly data is noise

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 -p pm-claude-skills 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="autopilot-charter"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

Autopilot Charter is one of 1307 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog