Search "claude"

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers).

Score basis：Clear source · Low risk signals · Claude

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Score basis：Clear source · High risk signals · Claude

Audit and improve CLAUDE.md files in repositories.

Score basis：Clear source · Risk needs review · Claude

Run Claude Code tasks in headless mode with `claude -p` through the local `cc-task-runner.sh` wrapper, including model switching, JSON output capture, structured schema checks, multi-file artifact validation, and glob ma

Score basis：Clear source · High risk signals · Claude

Reduce Anthropic API costs (cache read, compaction, context bloat) for OpenClaw agents.

Score basis：Clear source · High risk signals · Claude

进化版统一记忆系统，融合Claude Code的5层记忆架构+Token预算管理+智能成本追踪。当用户要求记忆跨会话信息、智能管理Token预算、优化AI调用成本、构建个人知识库、跨项目学习进化时使用。

Score basis：Clear source · High risk signals · Claude

Running Claude Code Via Litellm Copilot skill from xixu-me/skills.

Score basis：Clear source · Low risk signals · Claude

Automatically execute tasks from checklist.md with state management and scheduled checking

Score basis：Clear source · High risk signals · Claude

Use when the user wants to customize Claude Code keybindings, rebind shortcuts, add chords, or edit `~/.claude/keybindings.json` safely.

Score basis：Clear source · High risk signals · Claude

Web Artifacts Builder skill from anthropics/skills.

Score basis：Clear source · Low risk signals · Claude

Mcp Builder skill from anthropics/skills.

Score basis：Clear source · Low risk signals · Claude

Canvas Design skill from anthropics/skills.

Score basis：Clear source · Low risk signals · Claude

Pdf skill from anthropics/skills.

Score basis：Clear source · Low risk signals · Claude

Frontend Design skill from anthropics/skills.

Score basis：Clear source · Low risk signals · Claude

Agent Development skill from anthropics/claude-code.

Score basis：Clear source · High risk signals · Claude

Skill Development skill from anthropics/claude-code.

Score basis：Clear source · High risk signals · Claude

Doc Coauthoring skill from anthropics/skills.

Score basis：Clear source · Risk needs review · Claude

This skill should be used when the user asks to "demonstrate skills", "show skill format", "create a skill template", or discusses skill development patterns.

Score basis：Clear source · Low risk signals · Claude

Generate tailored sales assets (landing pages, decks, one-pagers, workflow demos) from your deal context.

Score basis：Clear source · Low risk signals · Claude

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions.

Score basis：Clear source · Low risk signals · Claude

Review PyTorch pull requests for code quality, test coverage, security, and backward compatibility.

Score basis：Clear source · Low risk signals · Claude

Debug AOTInductor (AOTI) errors and crashes.

Score basis：Clear source · Low risk signals · Claude

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros.

Score basis：Clear source · Low risk signals · Claude