chess
Run a personal chess learning loop with Maia-3 practice games, sparse chat-mediated coaching, durable progress, and post-game review.
Skill by Skarian
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/skarian-chess
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/chess
What's inside
- Skill name
chess- Description
- Run a personal chess learning loop with Maia-3 practice games, sparse chat-mediated coaching, durable progress, and post-game review.
- License
- unknown
- Instructions
- 50 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (33)
- .gitignore
- README.md
- RETIREMENT.md
- ROADMAP.md
- SKILL.md
- package-lock.json
- package.json
- .gitignore · prototype/maia3/
- README.md · prototype/maia3/
- maia3-probe.mjs · prototype/maia3/
- app.js · public/
- index.html · public/
- styles.css · public/
- AGENDA.md · research/
- COACHING_MODEL.md · research/
- ENGINE_ALTERNATIVES.md · research/
- LEVELING_SYSTEM.md · research/
- LEVEL_TARGETS.md · research/
- MAIA3_FEASIBILITY.md · research/
- MODES.md · research/
- OPPONENT_MODEL.md · research/
- PROGRESS_MODEL.md · research/
- RATING_CONVERSION.md · research/
- THESIS.md · research/
- TRANSFER_EVIDENCE.md · research/
- profile.mjs · scripts/
- progress.mjs · scripts/
- setup-maia.mjs · scripts/
- smoke-test.mjs · scripts/
- data.mjs · src/
- maia.mjs · src/
- server.mjs · src/
- stockfish.mjs · src/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Skarian/skills
- 0.561score
relay
Skarian
Use the Relay MCP tool when a local app or UI needs the agent to wait, receive app context, reply, and return control without building a custom agent loop.
SkillAFreshness: AClaude Code +9 - 0.538score
execplan
Skarian
Use when the user wants to create, revise, execute, review, or archive an ExecPlan.
SkillAFreshness: AClaude Code +9 - 0.533score
chatgpt-pro-review
Skarian
Use when the user explicitly asks Codex to consult ChatGPT Pro through the Codex app browser.
SkillAFreshness: AClaude Code +9 - 0.533score
friend
Skarian
Use when the user asks to call a friend or get a CLI-backed second opinion from Claude or Codex.
SkillAFreshness: AClaude Code +9 - 0.528score
mac-screenshot
Skarian
Use when the user asks to inspect, review, compare, or reason from a macOS screenshot without providing a path.
SkillAFreshness: AClaude Code +9 - 0.528score
scratch
Skarian
Use when the user wants to start a scratch file, draft, or temporary working surface in the repo root.
SkillAFreshness: AClaude Code +9 - 0.469score
discussion
Skarian
Use when a response will have more than three blocking decisions, risks, or questions that must be discussed with the user.
SkillCFreshness: CClaude Code +9 - 0.469score
precommit-review
Skarian
Use when the user requests a phased pre-commit review of the worktree.
SkillCFreshness: CClaude Code +9 - 0.467score
continuity
Skarian
Use for durable handoff on nontrivial project work.
SkillCFreshness: CClaude Code +9 - 0.466score
reference-module
Skarian
Use when researching another Git repository
SkillCFreshness: CClaude Code +9 - 0.461score
consensus
Skarian
Use when user requests "waves of reviewer subagents"
SkillCFreshness: CClaude Code +9 - 0.440score
skill-research
Skarian
Use when the user asks to look back over recent work and identify repeated workflows worth packaging as skills, subagents, automations, extensions, or skips.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 13, 2026 (15 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/Skarian/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Skarian
- 0.561score
relay
Skarian
Use the Relay MCP tool when a local app or UI needs the agent to wait, receive app context, reply, and return control without building a custom agent loop.
SkillAFreshness: AClaude Code +9 - 0.538score
execplan
Skarian
Use when the user wants to create, revise, execute, review, or archive an ExecPlan.
SkillAFreshness: AClaude Code +9 - 0.533score
chatgpt-pro-review
Skarian
Use when the user explicitly asks Codex to consult ChatGPT Pro through the Codex app browser.
SkillAFreshness: AClaude Code +9 - 0.533score
friend
Skarian
Use when the user asks to call a friend or get a CLI-backed second opinion from Claude or Codex.
SkillAFreshness: AClaude Code +9 - 0.528score
mac-screenshot
Skarian
Use when the user asks to inspect, review, compare, or reason from a macOS screenshot without providing a path.
SkillAFreshness: AClaude Code +9 - 0.528score
scratch
Skarian
Use when the user wants to start a scratch file, draft, or temporary working surface in the repo root.
SkillAFreshness: AClaude Code +9
Cite this page
chess skill. Agent Mart. https://agentmart.dev/skills/skarian-chess (last updated 2026-10-24)