tldr-code
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
浏览 namesreallyblank 维护的已发布 AI 技能,比较用途与说明,并通过来源仓库了解安装方式。
已收录技能
35收录技能的仓库 Stars 合计
47仓库 Forks
0平均每个技能的仓库 Stars
1同一仓库中的多个技能可能共享 Stars,合计包含重复仓库数据。
Token-efficient code analysis via 5-layer stack (AST, Call Graph, CFG, DFG, PDG). 95% token savings.
Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging
Git Commit Rules
Search library documentation and code examples via Nia
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Search GitHub code, repositories, issues, and PRs via MCP
Research agent for external documentation, best practices, and library APIs via MCP tools
Automated accessibility testing via Playwright MCP and axe-core
Browser automation via Playwright MCP - screenshots, interactions, DOM inspection
Web performance testing via Playwright MCP - Core Web Vitals, Lighthouse
Review UI code for Web Interface Guidelines compliance - accessibility, forms, animation, performance
Fast codebase search via WarpGrep (20x faster than grep)
Implement technical plans from thoughts/shared/plans with verification
Unified math capabilities - computation, solving, and explanation. I route to the right tool.
Choose the right search tool for each query type
Create and configure Claude Code sub-agents with custom prompts, tools, and models
MANDATORY - Load this skill first. Routes to bootstrap + domain rules.
Manage Clorch configuration (Braintrust, API keys, features)
Problem-solving strategies for proof theory in mathematical logic
Implementation agent that executes a single task and creates handoff on completion
External research workflow for docs, web, APIs - NOT codebase exploration
Guide to the math cognitive stack - what tools exist and when to use each
Claude Code CLI commands, flags, headless mode, and automation patterns
Deterministic router for math cognitive stack - maps user intent to exact CLI commands
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。