Clay-HHK/claude-config
Personal Claude Code harness configuration: agents, commands, rules, hooks, skills, and docs
ARCHETYPE
YOLO Cowboy
Permissions? Never heard of 'em. Ships at the speed of `--dangerously-skip-permissions`.
Copy this rig
# review before running: this installs third-party code $ npx degit Clay-HHK/claude-config/agents ./rig-claude-config/agents $ npx degit Clay-HHK/claude-config/commands ./rig-claude-config/commands $ npx degit Clay-HHK/claude-config/skills ./rig-claude-config/skills $ npx degit Clay-HHK/claude-config/hooks ./rig-claude-config/hooks
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit Clay-HHK/claude-config/skills/agent-identifier .claude/skills/agent-identifier $ npx degit Clay-HHK/claude-config/skills/algorithmic-art .claude/skills/algorithmic-art $ npx degit Clay-HHK/claude-config/skills/architecture-design .claude/skills/architecture-design $ npx degit Clay-HHK/claude-config/skills/arxiv-database .claude/skills/arxiv-database $ npx degit Clay-HHK/claude-config/skills/brand-guidelines .claude/skills/brand-guidelines $ npx degit Clay-HHK/claude-config/skills/bug-detective .claude/skills/bug-detective $ npx degit Clay-HHK/claude-config/skills/canvas-design .claude/skills/canvas-design $ npx degit Clay-HHK/claude-config/skills/citation-management .claude/skills/citation-management $ npx degit Clay-HHK/claude-config/skills/citation-verification .claude/skills/citation-verification $ npx degit Clay-HHK/claude-config/skills/code-review-excellence .claude/skills/code-review-excellence $ npx degit Clay-HHK/claude-config/skills/command-development .claude/skills/command-development $ npx degit Clay-HHK/claude-config/skills/command-name .claude/skills/command-name $ npx degit Clay-HHK/claude-config/skills/daily-coding .claude/skills/daily-coding $ npx degit Clay-HHK/claude-config/skills/daily-paper-generator .claude/skills/daily-paper-generator $ npx degit Clay-HHK/claude-config/skills/dask .claude/skills/dask $ npx degit Clay-HHK/claude-config/skills/doc-coauthoring .claude/skills/doc-coauthoring $ npx degit Clay-HHK/claude-config/skills/docx .claude/skills/docx $ npx degit Clay-HHK/claude-config/skills/exploratory-data-analysis .claude/skills/exploratory-data-analysis $ npx degit Clay-HHK/claude-config/skills/frontend-design .claude/skills/frontend-design $ npx degit Clay-HHK/claude-config/skills/git-workflow .claude/skills/git-workflow $ npx degit Clay-HHK/claude-config/skills/hook-development .claude/skills/hook-development $ npx degit Clay-HHK/claude-config/skills/humanizer .claude/skills/humanizer $ npx degit Clay-HHK/claude-config/skills/infographics .claude/skills/infographics $ npx degit Clay-HHK/claude-config/skills/internal-comms .claude/skills/internal-comms $ npx degit Clay-HHK/claude-config/skills/kaggle-learner .claude/skills/kaggle-learner $ npx degit Clay-HHK/claude-config/skills/latex-conference-template-organizer .claude/skills/latex-conference-template-organizer $ npx degit Clay-HHK/claude-config/skills/latex-posters .claude/skills/latex-posters $ npx degit Clay-HHK/claude-config/skills/literature-review .claude/skills/literature-review $ npx degit Clay-HHK/claude-config/skills/markdown-mermaid-writing .claude/skills/markdown-mermaid-writing $ npx degit Clay-HHK/claude-config/skills/matplotlib .claude/skills/matplotlib $ npx degit Clay-HHK/claude-config/skills/mcp-builder .claude/skills/mcp-builder $ npx degit Clay-HHK/claude-config/skills/mcp-integration .claude/skills/mcp-integration $ npx degit Clay-HHK/claude-config/skills/mean-reviewer .claude/skills/mean-reviewer $ npx degit Clay-HHK/claude-config/skills/ml-paper-writing .claude/skills/ml-paper-writing $ npx degit Clay-HHK/claude-config/skills/networkx .claude/skills/networkx $ npx degit Clay-HHK/claude-config/skills/paper-self-review .claude/skills/paper-self-review $ npx degit Clay-HHK/claude-config/skills/pdf .claude/skills/pdf $ npx degit Clay-HHK/claude-config/skills/peer-review .claude/skills/peer-review $ npx degit Clay-HHK/claude-config/skills/planning-with-files .claude/skills/planning-with-files $ npx degit Clay-HHK/claude-config/skills/plotly .claude/skills/plotly
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/bug-analyzer.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/bug-analyzer.md $ curl -fsSL --create-dirs -o .claude/agents/build-error-resolver.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/build-error-resolver.md $ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/code-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/data-analyst.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/data-analyst.md $ curl -fsSL --create-dirs -o .claude/agents/dev-planner.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/dev-planner.md $ curl -fsSL --create-dirs -o .claude/agents/harness-auditor.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/harness-auditor.md $ curl -fsSL --create-dirs -o .claude/agents/kaggle-miner.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/kaggle-miner.md $ curl -fsSL --create-dirs -o .claude/agents/literature-reviewer.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/literature-reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/paper-miner.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/paper-miner.md $ curl -fsSL --create-dirs -o .claude/agents/rebuttal-writer.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/rebuttal-writer.md $ curl -fsSL --create-dirs -o .claude/agents/refactor-cleaner.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/refactor-cleaner.md $ curl -fsSL --create-dirs -o .claude/agents/story-generator.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/story-generator.md $ curl -fsSL --create-dirs -o .claude/agents/tdd-guide.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/tdd-guide.md $ curl -fsSL --create-dirs -o .claude/agents/ui-sketcher.md https://raw.githubusercontent.com/Clay-HHK/claude-config/main/agents/ui-sketcher.md
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (78)
Agent Developmentalgorithmic-artarchitecture-designarxiv-databasebrand-guidelinesbug-detectivecanvas-designcitation-managementcitation-verificationcode-review-excellenceCommand DevelopmentPlugin Structuredaily-codingdaily-paper-generatordaskdoc-coauthoringdocxexploratory-data-analysisfrontend-designgit-workflowHook Developmenthumanizerinfographicsinternal-commskaggle-learnerlatex-conference-template-organizerlatex-postersliterature-reviewmarkdown-mermaid-writingmatplotlibmcp-builderMCP Integrationmean-reviewerml-paper-writingnetworkxpaper-self-reviewpdfpeer-reviewplanning-with-filesplotlypolarspost-acceptancepptxpufferlibpyzoteroResearch Ideationresults-analysisreview-responsescientific-brainstormingscientific-critical-thinkingscientific-schematicsscientific-slidesscientific-visualizationscientific-writingscikit-learnseabornshapskill-creatorSkill Developmentskill-improverskill-quality-reviewerslack-gif-creatorstable-baselines3statistical-analysisstatsmodelssympytheme-factorytorch-geometricui-ux-pro-maxumap-learnuv-package-managerverification-loopweb-artifacts-builderweb-design-reviewerwebapp-testingwriting-anti-aixlsxzotero-arxiv-ingest
Subagents (15)
| architect model: opus | ML project architecture specialist for code structure, module design, and pattern consistency. Use PROACTIVELY when modifying code structure, adding new modules, or maintaining architectural patterns. |
| bug-analyzer model: opus | Expert debugger specialized in deep code execution flow analysis and root cause investigation. Use when you need to analyze code execution paths, build execution chain diagrams, trace variable state c |
| build-error-resolver model: opus | Build and Python type error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting th |
| code-reviewer model: opus | Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes. |
| data-analyst model: inherit | Use this agent when the user asks to "analyze experimental results", "generate statistical analysis", "create results visualization", "compare model performance", or mentions analyzing ML/AI experimen |
| dev-planner model: sonnet | Expert development planner that breaks down user stories and requirements into detailed, actionable development plans. Specializes in task decomposition, dependency analysis, timeline estimation, and |
| harness-auditor model: sonnet | > |
| kaggle-miner model: inherit | Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples: |
| literature-reviewer model: inherit | Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research proje |
| paper-miner model: inherit | Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to "learn from NeurIPS papers", "extract writing patterns from this paper", "analyze paper structure", "study acade |
| rebuttal-writer model: inherit | Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebutt |
| refactor-cleaner model: opus | Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (vulture, pip-audit, pyflakes) to identify dead code and safe |
| story-generator model: inherit | Use this agent when you need to generate user stories with acceptance criteria from various inputs like git diffs, conversation history, PRD documents, or any requirements that need to be structured i |
| tdd-guide model: opus | Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage. |
| ui-sketcher model: inherit | Universal UI Blueprint Engineer that transforms any functional requirement into visual ASCII interface designs, user stories, and interaction specifications. Excels at converting brief descriptions in |
Hooks (7)
| event | matcher | runs |
|---|---|---|
| Notification | * | afplay /System/Library/Sounds/Glass.aiff |
| Notification | * | /Applications/cmux.app/Contents/Resources/bin/cmux notify --title 'Claude Code' --subtitle '需要你的输入' --body "$(date '+%H:%M:%S')" |
| PostToolUseFailure | * | afplay /System/Library/Sounds/Basso.aiff |
| PostToolUseFailure | * | /Applications/cmux.app/Contents/Resources/bin/cmux notify --title 'Claude Code' --subtitle '工具执行失败' --body "$(date '+%H:%M:%S')" |
| Stop | * | afplay /System/Library/Sounds/Hero.aiff |
| Stop | * | pkill -9 -f 'Wolfram Engine.*wolfram' 2>/dev/null; pkill -9 -f 'MathLink|XML.exe' 2>/dev/null; true |
| Stop | * | /Applications/cmux.app/Contents/Resources/bin/cmux notify --title 'Claude Code' --subtitle '任务完成' --body "$(date '+%H:%M:%S')" |
Slash commands (56)
/analyze-results/build-fix/check-experiments/checkpoint/code-review/commit/create_project/harness-feedback/harness-health/harness-report/learn/paper-edit/plan/poster/presentation/promote/rebuttal/refactor-clean/research-init/sc/agent/sc/analyze/sc/brainstorm/sc/build/sc/business-panel/sc/cleanup/sc/design/sc/document/sc/estimate/sc/explain/sc/git/sc/help/sc/implement/sc/improve/sc/index-repo/sc/load/sc/pm/sc/recommend/sc/reflect/sc/research/sc/save/sc/sc/sc/select-tool/sc/spawn/sc/spec-panel/sc/task/sc/test/sc/troubleshoot/sc/workflow/setup-pm/tdd/update-github/update-memory/update-readme/verify/zotero-notes/zotero-review
Plugins (3)
codex@openai-codexscientific-skills@claude-scientific-skillssuperpowers@claude-plugins-official
Similar rigs
Galaxy-Dawn/claude-scholar
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.
Orchestrator 5.4k tok ·
aiskillstore/marketplace
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Skill Collector 2.6k tok ·
thevibeworks/claude-code-docs
Everything Anthropic ships for builders, archived and updated 4× daily. 3,900+ files. 12 sources. API, Claude Code, MCP, docs, cookbooks, skills, plugins.
Skill Collector 12.3k tok ·
LeastBit/Claude_skills_zh-CN
Anthropics/skills中文学习版本 来自：https://github.com/anthropics/skills
Skill Collector 608 tok ·