What do I need to use Ranked Climb Coach?

The game, current rank, peak rank, role/agent/champion pool; Their own diagnosis of why they're stuck; Tilt honesty; Time actually available.

Is Ranked Climb Coach 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.

Ranked Climb Coach

Q: How do I know the Ranked Climb Coach output is good?

The skill verifies itself against its own quality checks: Exactly one focus habit — a five-point improvement plan improves nothing; The review questions target decisions-before-deaths, not the death; frame itself; The tilt protocol has hard numbers (loss checkpoint, session cap).

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

Climb ranked on purpose instead of on tilt — a VOD-review protocol (three deaths per game, one pattern per week), a tilt debrief that ends queue-rage sessions, and honest fundamentals-first improvement planning for competitive games like League, Valorant, or Rocket League. Use when someone says 'I'm hardstuck', 'review my gameplay approach', 'I keep tilting', or 'how do I actually improve at ranked'. Produces a weekly improvement plan, a self-review template, and the tilt protocol.

▶ Run it free — no key needed 📝 Grade your existing draft ⬇ Add to Claude (works in Duet) 📱 Use as an app View SKILL.md ↗ What changed

🗣 Say this to your agent

“I'm hardstuck.”“Review my gameplay approach.”“I keep tilting.”“How do I actually improve at ranked?”

What to give it

▸The game, current rank, peak rank, role/agent/champion pool — games per week

▸Their own diagnosis of why they're stuck — then the last 3 losses described concretely (the gap between those two answers is usually the coaching)

▸Tilt honesty — longest loss-streak queued through recently, what happens to their play after a bad game

▸Time actually available — a plan for 6 hours/week that assumes 20 fails

✅ 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.

✓Exactly one focus habit — a five-point improvement plan improves nothing

✓The review questions target decisions-before-deaths, not the death

✓frame itself

✓The tilt protocol has hard numbers (loss checkpoint, session cap)

✓agreed in advance

✓The plan fits their real hours, with the 20% miss assumption stated

✓The skill is honest about its limits: it structures self-review from

✓the user's observations; it has not seen the VOD and never pretends

⚠️ What it refuses to do

Do not blame teammates anywhere in the output — the protocol reviews

the only player the user controls; "my team" tags are auto-converted to

"what could I have done with that information?"

Do not prescribe meta champions/agents as the fix — pool discipline

beats pool chasing at every rank below the one where it doesn't

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

Related skills

🔌 Embed this skill

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

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

💬 Discussion

Ranked Climb Coach is one of 1326 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog