发现 编程开发 相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。
CWF knowledge repository providing plan structure, tasklist format, checkpoint definitions, amendment rules, and validation requirements. Load this skill when: (1) executing CWF commands like /write-plan, /impl...
This skill should be used when creating new RFC 2119-conformant specification documents, iterating on specification drafts, choosing keywords (MUST/SHOULD/MAY/MUST NOT) while writing, structuring sections, or p...
Use for guided Fizzy.do workflows: "set up Fizzy", "configure Fizzy for this project", "sync my work to Fizzy", "review my Fizzy progress", "end of session cleanup". Provides step-by-step guidance for common op...
Pedantic backend pre-commit + atomic-commit skill for Django/Optimo repos that enforces local repo rules, pre-commit hooks, and security helpers (no AI signatures in commit messages).
Generate weekly code-review digest docs from PR review comments for any GitHub repo, capturing themes, repeated issues, and concrete takeaways.
Generate comprehensive, reviewer-friendly PR descriptions with diagrams, summary tables, collapsible sections, and structured test plans.
Create and manage ClickUp tickets directly from Claude Code or Codex. Supports multi-org workspaces, interactive ticket creation, subtasks, backlog management, and intelligent caching of your ClickUp workspace...
Generate comprehensive API docs from Bruno (.bru) files by mapping requests to a Django implementation (DRF/Django Ninja), including auth, multi-tenant filtering, schemas, and code references.
Pedantic backend PR workflow skill enforcing ClickUp-linked branch/PR naming, PR hygiene, safe Django migrations, and downtime-safe schema changes.
Create or update a structured plan directory with a PLAN.md index and numbered task files (001-*.md) containing checklists, tests, and completion criteria.
Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects (PLAN.md, task files, and RALPH-PROMPT.md).
Mixpanel analytics tracking implementation + review skill for Django optimo_analytics: add events and audit for PII safety, schema design, and code quality.
Upsert a single PR comment that serves as an AI session ledger (human steering, deltas, tests) across Codex + Claude Code. Not a PR description.
Hyper-pedantic Django code review skill emulating Monty's correctness-first, multi-tenant-safe review style.
Expert guidance for building production MCP servers using MXCP (Model Context Protocol eXtension Platform), an enterprise framework with SQL and Python endpoints, security, testing, and deployment. Use when: (1...
Intelligent single-file document ingestion into MXCP servers. Supports Excel (.xlsx, .xls, .csv) and Word (.docx) files. Analyzes content to determine if queries will be needed (DuckDB) or semantic search (RAG...
Provide architecture-specific GPU optimization advice for NVIDIA GPUs (Ampere, Hopper, Ada). Use when discussing GPU architecture features, compute capability, or hardware-specific optimizations.
Optimize CUDA kernels and GPU code for performance. Use when reviewing CUDA code, analyzing performance, or suggesting GPU optimizations.
Sets up a new Rust/Python hybrid library project using maturin and uv. Creates project structure with PyO3 bindings, installs dev dependencies, and optionally configures git remote. Use when the user wants to i...
Deploy dimtensor to PyPI. Use when releasing a new version.
Review dimtensor code for correctness, dimensional safety, and adherence to patterns. Use when reviewing new code or during consolidation phases.
Design new unit modules for dimtensor. Use when creating astronomy, chemistry, engineering, or other domain-specific units.
Scaffold FastMCP tool implementations with database integration, error handling, and test session support. Generates production-ready MCP tools.
Generate comprehensive pytest integration tests for MCP tools and FastAPI endpoints. Includes fixtures, edge cases, and validation tests.
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。