- 📁 agents/
- 📁 references/
- 📄 SKILL.md
Semantic code search, regex pattern search, and symbol lookup across a local repository. Returns ranked markdown codeblocks with file path, line range, content, and optional symbol info. Use `vera search` for conceptual/behavioral queries (how a feature works, where logic lives, exploring unfamiliar code). Use `vera grep` for exact strings, regex patterns, imports, and TODOs. Use `vera references` to trace callers/callees. Use rg only for bulk find-and-replace or files outside the index.
- 📁 .claude/
- 📁 .github/
- 📁 .playwright-mcp/
- 📄 .gitignore
- 📄 .pre-commit-config.yaml
- 📄 .python-version
A skill
- 📁 agents/
- 📁 references/
- 📄 SKILL.md
规范化 Excalidraw 图，确保后续可维护编辑、绑定关系安全、编辑器辅助重排和夜间模式安全导出。处理 `.excalidraw` 架构图、拓扑图、流程图或系统图，并且需要修复 container/binding、重排几何布局、清理连接线或导出透明 PNG 到文档时使用。
- 📁 agents/
- 📁 examples/
- 📁 references/
- 📄 .editorconfig
- 📄 .gitattributes
- 📄 .gitignore
当用户希望用《毛泽东选集》/教员的方法分析现实问题、把毛选中的方法论转成现代分析框架，或明确提出“用毛选帮我分析”“用教员的方法帮我分析 xxx”“用新青年帮我分析”“按新青年的方法拆一下”“按主要矛盾/阶段判断/统一战线/实践检验的方法分析”时使用。适用于工作推进、复杂协作、关系边界、学习成长、生活决策、团队治理等结构性问题；一旦触发，就默认按复杂结构题处理。澄清是所有任务的硬前提：先锁目标，再持续澄清到关键结构基本清楚，之后才进入分析。澄清题默认使用带 A/B/C/D 和“其他”的选项式追问。正式输出前再确认用户要文字版还是 HTML 版。
- 📁 .github/
- 📁 agents/
- 📁 docs/
- 📄 .gitignore
- 📄 paper-fetch-en.png
- 📄 README.md
Use when the user wants to download a paper PDF from a DOI, title, or URL via legal open-access sources. Tries Unpaywall, arXiv, bioRxiv/medRxiv, PubMed Central, and Semantic Scholar in order. Never uses Sci-Hub or paywall bypass.
- 📁 references/
- 📁 scripts/
- 📄 README.md
- 📄 SKILL.md
Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.
- 📄 examples.md
- 📄 reference.md
- 📄 SKILL.md
Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces. Creates kernel config YAMLs, discovers kernels in a project, and queries GPU specs. Use when the user mentions Magpie, kernel analyze or compare, HIP/CUDA kernel evaluation, vLLM/SGLang benchmark, gap analysis, TraceLens, creating kernel configs, or discovering GPU kernels.
- 📁 bin/
- 📁 docs/
- 📁 evaluations/
- 📄 .gitignore
- 📄 EVALUATION.md
- 📄 LICENSE
Structured B2B software vendor evaluation for buyers. Researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions, and produces a comparative recommendation with evidence transparency. Use when asked to evaluate, compare, or research B2B software vendors.
The Balanced Coupling model for software design. Use when: designing modular architectures, evaluating coupling between components, reviewing code modularity, deciding whether to split or merge modules/services, assessing integration patterns, classifying coupling as balanced or unbalanced, applying DDD strategic and tactical patterns, reasoning about cohesion vs coupling trade-offs, identifying distributed monolith risks, or explaining why a system is hard to change. Provides the three-dimensional framework (integration strength, distance, volatility) and the balance rule for making coupling decisions.
Post-task learning capture and knowledge promotion. Auto-invoke when a task or sprint is completed, when the user says "done", "finished", "wrap up", or when all acceptance criteria are checked off. Do NOT invoke when user says "ship it" — that triggers /ship-test-ensure instead.
Use after implementing features, before claiming a phase is complete, when reviewing AI-generated code, or when code feels overly complex. Also use when you notice repeated patterns across files, a function exceeds 40 lines, nesting exceeds 3 levels, or an abstraction has only one implementation. Covers duplication, dead code, over-engineering, and AI-specific bloat patterns like verbose error handling and redundant type checks.
Semantic code and documentation search by meaning. Use codebase_peek to find WHERE code is (saves tokens), codebase_search to see actual code. For exact identifiers, use grep instead. Search local codebase before using websearch for code/library/API/example questions.
