Agent skill

Ranked Climb Coach

by mohitagw15856 in mohitagw15856/pm-claude-skills

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…

MITAuto-check passed

Install Ranked Climb Coach

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill ranked-climb-coach -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills ranked-climb-coach --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ranked-climb-coach .claude/skills/ranked-climb-coach && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ranked-climb-coach
GitHub stars
1.4k
Token cost
~1.5k tokens
SKILL.md length
730 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

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…

  • Works in 5 steps: Shrink the pool first. Hardstuck + large… → The three-deaths review. After each game… → One habit per week. The most frequent… → …
  • Someone says Im hardstuck
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework and Output Format, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ranked Climb Coach is an agent skill from mohitagw15856/pm-claude-skills. 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.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Someone says Im hardstuck
  • Review my gameplay approach
  • How do I actually improve at ranked

Example prompts

  • “m hardstuck”
  • “review my gameplay approach”
  • “I keep tilting”
  • “/ranked-climb-coach”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Shrink the pool first. Hardstuck + large champion/agent pool = the
  2. The three-deaths review. After each game (or from memory for the last
  3. One habit per week. The most frequent tag becomes the week's single
  4. The tilt protocol, non-negotiable. Two losses = mandatory 10-minute
  5. Fundamentals over highlights. The genre's boring gates (last-hitting,

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ranked Climb Coach loads about 1.5k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 730 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 730 words, ~1,545 tokens.

Download SKILL.mdSave it as .claude/skills/ranked-climb-coach/SKILL.md (or your agent's skills folder).
name
ranked-climb-coach
description
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.

Ranked Climb Coach Skill

Hardstuck players grind games; improving players study deaths. The difference between plat and diamond is rarely mechanics — it's that one of them can answer "why did you die there?" with something other than "their Jett is smurfing." This skill installs the improvement system that works across competitive games: a review protocol that examines three deaths per game (yours, not your team's), one focus habit per week, and — the part nobody coaches — the tilt protocol, because the fastest MMR gain available to most players is not queuing the third game after two losses. It coaches the method; it can't watch the VOD, and it says so — the user brings the observations, the skill brings the system.

What This Skill Produces

  • A weekly improvement plan: ONE focus habit, chosen from the user's own reported death patterns, with a success metric that isn't rank
  • A self-review template: the three-deaths protocol with the questions that convert deaths into patterns
  • The tilt protocol: hard queue rules, the two-loss checkpoint, and the reset ritual (a gamer-shaped [[stoic-setback-debrief]])
  • A fundamentals audit for their game genre: the boring things that gate rank (CS/economy/positioning/rotation — genre-appropriate), self-scored

Required Inputs

Ask for (if not already provided):

  • 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

Framework

  1. Shrink the pool first. Hardstuck + large champion/agent pool = the diagnosis, most of the time. Two mains + one flex until the next rank. Consistency compounds; variety is a hobby (fine! — but pick which this is).
  2. The three-deaths review. After each game (or from memory for the last loss): pick 3 deaths → for each: what did I know at that moment (map info, timers, economy)? · what did I assume? · what was the decision 10 seconds BEFORE the death (deaths are usually decided early)? · tag the cause: info / positioning / greed / tilt / genuine-outplay. Genuine-outplay is allowed to be the answer — but not four times a game.
  3. One habit per week. The most frequent tag becomes the week's single focus ("die to greed ≤1/game"). Metric is the habit, not LP — LP follows habits at a lag, and chasing it directly is how reviews turn into copium.
  4. The tilt protocol, non-negotiable. Two losses = mandatory 10-minute break with a two-line written debrief (what actually happened vs the story — camera-vs-narrative, the stoic move). Third queue after two ragey losses is where accounts lose their week. Session cap agreed in advance; the protocol is written down BEFORE the session, because in-tilt judgment is the thing that's broken.
  5. Fundamentals over highlights. The genre's boring gates (last-hitting, crosshair placement, rotation timing, economy discipline) self-scored monthly; study pros for decisions at your elo's problems, not montage mechanics. Aim training and guides are supplements, not the meal.
Show full SKILL.md (228 more words)Show less

Output Format

## Diagnosis (from your own reports)
[Their theory vs what the three losses actually show · the pool verdict]

## This week's ONE habit
[The habit · why this one · the metric that isn't LP]

## Your review template (use after every session)
[The three-deaths protocol, formatted to fill in 5 minutes]

## Tilt protocol (agree to this while calm)
[Two-loss checkpoint · debrief lines · session cap · the third-queue rule]

## Fundamentals audit — [genre]
| Gate | Self-score /5 | The drill if under 3 |

## Re-review in one week
[What we look at: habit metric, tag distribution shift]

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) 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 otherwise

Anti-Patterns

  • 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
  • Do not fake game-specific authority — patch-current builds and matchup charts change weekly; point at the game's live resources for those and own the method layer
  • Do not let rank be the weekly metric; habit adherence is the metric, rank is the lagging echo
  • Do not skip the tilt section for "mechanically-focused" players — the two-loss checkpoint outranks any aim drill in MMR-per-hour

[[stoic-setback-debrief]] is the tilt protocol's parent; [[deep-work-blocking]] for making practice time real; [[the-gym]]-style arenas for the negotiation kind of ranked.

Example Trigger Phrases

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

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ranked-climb-coach of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Ranked Climb Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ranked Climb Coach compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ranked Climb Coach this skillmohitagw15856/pm-claude-skills1.4k—~1.5kAutomated safety check: PassMIT
Interview Coachsickn33/agentic-awesome-skills47k2 repos~751Automated safety check: PassMIT
Claude Coachalirezarezvani/claude-skills28k—~2.1kAutomated safety check: PassMIT
Reflection Coachpaperclipai/paperclip100k—~3kAutomated safety check: PassMIT
Coachnagisanzenin/engram1.4k—~10kAutomated safety check: PassMIT
Founder Coachalirezarezvani/claude-skills28k1 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Interview Coach

    sickn33/agentic-awesome-skills

    Full job search coaching system — JD decoding, resume, storybank, mock interviews, transcript analysis, comp negotiation.

    47k GitHub starsUsed in 2 repos~751 tokens
    Business, Finance & HRAuto-check passed
  • Claude Coach

    alirezarezvani/claude-skills

    Personal coach that teaches users to become Claude power users.

    28k GitHub stars~2.1k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Reflection Coach

    paperclipai/paperclip

    Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change.

    100k GitHub stars~3k tokensUpdated today
    Sales & SupportAuto-check passed
  • Coach

    nagisanzenin/engram

    Learning telemetry, strategy, and schedule — retention stats, calibration, grader audit, n-of-1 experiments, HTML dashboard.

    1.4k GitHub stars~10k tokensUpdated 1 mo ago
    EducationAuto-check passed
  • Founder Coach

    alirezarezvani/claude-skills

    Personal leadership development for founders and first-time CEOs.

    28k GitHub starsUsed in 1 repo~3.5k tokens
    Productivity & AutomationAuto-check passed
  • Interview Coach

    noamseg/interview-coach-skill

    High-rigor interview coaching skill for job seekers. An agent skill from noamseg/interview-coach-skill.

    2.3k GitHub stars~3.7k tokensUpdated 4 mo ago
    Business, Finance & HRAuto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Ranked Climb Coach

What does Ranked Climb Coach do?

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…. Ranked Climb Coach is an agent skill from mohitagw15856/pm-claude-skills. 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.

When should I use Ranked Climb Coach?

Ranked Climb Coach fits situations like: someone says Im hardstuck; review my gameplay approach; how do I actually improve at ranked.

How do I install Ranked Climb Coach in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill ranked-climb-coach -a claude-code`. Or copy the skill folder (skills/ranked-climb-coach in mohitagw15856/pm-claude-skills) into .claude/skills/ranked-climb-coach in your project. Claude Code loads it when a task matches its description.

How do I install Ranked Climb Coach in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill ranked-climb-coach -a codex`. Or copy the skill folder (skills/ranked-climb-coach in mohitagw15856/pm-claude-skills) into .agents/skills/ranked-climb-coach in your project. Codex loads it when a task matches its description.

Can I use Ranked Climb Coach in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mohitagw15856/pm-claude-skills --skill ranked-climb-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ranked-climb-coach, .gemini/skills/ranked-climb-coach, .github/skills/ranked-climb-coach and .opencode/skills/ranked-climb-coach in your project.

What does Ranked Climb Coach need to run?

SKILL.md names no scripts, command-line tools or credentials: Ranked Climb Coach is instructions for the agent only.

Does Ranked Climb Coach access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ranked Climb Coach safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ranked Climb Coach use?

Ranked Climb Coach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ranked Climb Coach use?

About 1.5k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ranked Climb Coach?

Skills that share tags, products or a category with Ranked Climb Coach: Interview Coach (sickn33/agentic-awesome-skills, 47k stars), Claude Coach (alirezarezvani/claude-skills, 28k stars), Reflection Coach (paperclipai/paperclip, 100k stars) and Coach (nagisanzenin/engram, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ranked Climb Coach?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.