Development Claude Skills
8 673 development skills from 759 authors. They write and change code. Half of them fit into 1 830 tokens or less — that is what one costs your context window when the agent loads it. 1 213 ship runnable scripts rather than instructions alone. 42 of them cannot work without an MCP server, most often rube. We also found 1 239 copies of these same skills sitting in other people's repositories — counted once here, not 1 239 times.
8 673 unique 759 authors 10 updated this month 1 368 from vendors
| Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts for a different LM", or whenever a brittle hand-crafted prompt pipeline needs to be turned into a *compiled*, measurable, swappable program. Do NOT activate for one-shot prompt tweaks, no-metric exploratory work, or pipelines where prompts must remain human-authored verbatim — use raw prompting or LangChain templates instead.
| Decision protocol for wrapping a REST / GraphQL / RPC API as a tool an LLM LM-friendly subset of the *API surface* — one tool per user intent, not one per endpoint. Activates when a coder agent must expose an external HTTP API to a model (function calling, tool_use, MCP, LangChain `@tool`, CrewAI `BaseTool`). Encodes the *what to surface, how to name, how to shape, how to fail* — not any single framework's API. ~80% of agent tools in production are HTTP wrappers; this is the SOP for getting them right.
| Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers, agents), or pick LlamaIndex vs LangChain / Haystack / raw vector store for a coding task. Encodes the 5-layer mental model (Documents → Nodes → Indices → Retrievers → Query Engines / Response Synthesizers), the canonical RAG bootstrap SOP from baseline `VectorStoreIndex` through hybrid + reranker + eval-loop hardening, the official 13-failure-mode checklist, and 5 dilemma cases distilled from docs, GitHub issues, and 2025 production post-mortems.
| Re-ingest-correctness SOP for production RAG. Activate when a calling agent builds, reviews, or debugs an ingestion pipeline that runs more than once over a changing corpus — scheduled re-index, incremental updates, CI re-ingest, or a "retrieval has duplicates / shows deleted docs" bug. Encodes the rule — insert/update/skip, so re-running over unchanged docs is a no-op** — plus the docstore + doc-hash upsert machinery (LlamaIndex `IngestionPipeline` + `DocstoreStrategy`), the delete-propagation problem, and cross-framework equivalents (LangChain `index()` + `RecordManager`, manual hash table). ENHANCE the re-ingest-correctness contract is not surfaced.
| Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable graph. LangGraph is positioned by its maintainers as a "low-level orchestration framework for building, managing, and deploying long-running, stateful agents" — this skill encodes the *when* and *why*, not the API.
>- ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.
>- Decomposed, multi-criteria metric design for LLM pipelines. The metric IS the model — change the metric and the optimizer changes behavior. Decompose by default; bool during LLM-as-judge, llm as judge, eval metric, evaluation score, scoring function, rubric, RAGAS, G-Eval, judge bias, verbosity bias, how to evaluate LLM output.
| the framework sent to the model, before changing anything else. Activate when an LM call produced an unexpected output (wrong answer, schema violation, refusal, truncation, cost spike, latency spike, infinite loop, "model got dumber after upgrade"). The skill enforces a 30-second inspect step BEFORE any prompt edit, model swap, retry, or temperature CrewAI `step_callback`, LangChain `set_debug`/`set_verbose`, Aider `/diff`+`--verbose`, raw OpenAI/Anthropic via `OPENAI_LOG=debug`/`ANTHROPIC_LOG=debug` or HTTPX event hooks. Do NOT activate for first-time prompt authoring, exploratory prompt design, or non-LM bugs.
>- A 5-minute gate the coder runs at project kickoff (and again whenever the repo shape changes). Classifies the workspace into Greenfield / Brownfield-large / Mid-size-familiar / Library-SDK, then maps the state to an agent strategy (autonomy, context primitive, tool choice). Use BEFORE picking Cursor vs Claude Code vs Aider, BEFORE turning on repo-map, BEFORE writing the first prompt. Skip only if the same repo was gated within the last day codebase, project setup strategy, legacy codebase agent, where to start a coding agent.
>- Decide where to enforce structured LM output (constrain at decode time with Outlines vs validate-and-retry with Instructor vs grammar with Guidance) and which failure stance to take (Assert/hard-fail vs Suggest/soft-retry). Use when an LM's output is parsed or typed by downstream code and you must pick one enforcement library plus its failure handling, when malformed output is burning tokens on retries, or when choosing between decode-time vs validation-time constraints for local vs API models.
>- Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a `dspy.Signature`, and how do I name/describe its fields so the optimizer and the lines; the LM output is consumed by code (parsed, branched on, stored) rather than read by a human; the same prompt is reused across >1 call site; or a teammate asks "should this be a Signature?". Do NOT activate for one-shot throwaway prompts, or for HOW-TO questions about DSPy modules /optimizers/compile — defer those to the [[dspy]] skill and the Signature, prompt as a function, prompt contract, when to formalize a prompt.
| Tool skill for declaring reducers on LangGraph state keys so parallel writes merge instead of crashing. Activates whenever a coder agent designs a StateGraph with parallel branches, fan-out via Send, multi-agent topologies, one value per step`. Encodes the rule "every state key is single-writer or has a reducer — nothing in between."
基于日志记录驱动的轻量级项目开发和管理方案，是新项目的缺省管理方案
存档当前的失败尝试分支，并安全回退到特定历史提交
通过 markdown.new API 将网页、整站或搜索结果转换为干净的 Markdown
PMP 风格的结构化迭代开发流程，确保清晰、高效且有据可查。
审计代码库中的命名，确保符合既定的术语和规范
Engagement fieldbook for Forward Deployed Engineers. Use when the human says @fde or asks about client memory, debrief, prep, receipts, trust, hygiene, or sponsor status — route and run the local fde CLI; never ask them to type fde commands. Do not use for ordinary code edits, unit tests, refactors, or git commits.
REST/GraphQL/gRPC API design best practices. Use when designing APIs, defining contracts, handling versioning. Covers OpenAPI 3.2, GraphQL Federation, gRPC streaming.
Ask Grok or Gemini via opencli (browser-session based, no API cost). Use when the user says "问 grok", "问 gemini", "ask grok", "ask gemini", "用 grok 查", "grok 怎么看", "让 gemini 分析", or wants a second opinion from Grok/Gemini without paying API tokens. Routes to opencli which drives the already-logged-in Chrome session.
Generate or update repository-specific AGENTS.md instruction files from real repo evidence. Use when asked to create, design, scaffold, split, or improve root or scoped AGENTS.md files for Codex/Claude/agent workflows, especially when a repo needs directory-specific rules, validation commands, generated-file boundaries, or a short agent onboarding router.
Design architecture foundations before implementation. Use when asked to design or refactor architecture, choose Rust/Go crate, package, module, runtime, workflow, or service boundaries, compare mature project architecture, prevent stacked one-off PRs, audit migration debt in existing repos, or produce a spec before coding.
Helps write high-quality, idiomatic Rust code following Microsoft Pragmatic Rust Guidelines. Use when writing, reviewing, optimizing Rust code, or dealing with lifetimes, borrow checker, memory safety, cargo, and async Rust.
查看指定进程的代理线路。通过 Mihomo API 查询当前活跃连接，显示进程匹配的规则和代理链路。用于确认某个进程（如 claude、chrome）走的是哪条订阅线路
全面代码库审计 — 自适应并行深度分析（前后端契约、数据完整性、异常处理/安全、架构/技术债、配置/缓存），结构化 findings + 对抗验证 + 基线对比，输出按严重程度排序的统一报告和修复路线图。支持 quick 快速体检模式。Use when user asks to audit, analyze, or review an entire codebase for design issues, find hidden bugs, check architecture health, or asks '全面审查', '代码库审计', '分析设计问题', 'audit codebase', 'health check', '有哪些问题', '快速体检'. Also trigger when user asks to find silent degradation, data flow breakpoints, type mismatches between frontend and backend, or wants to understand technical debt across a project.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing
Extract Figma designs and generate production-ready React/Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy. Use when a user provides a Figma URL or asks to convert Figma designs to code.
Generates meaningful, conventional commit messages automatically. Use when committing code changes. Analyzes diff to create descriptive commits following best practices.
Use when the user wants to extract Figma designs into production-ready React or Next.js components with TypeScript, Tailwind CSS, and pixel-perfect accuracy.
GitHub Trending 探索与分析。用于发现热门开源项目、技术趋势、开发者偏好，帮助理解技术社区的兴趣走向。使用场景包括“看看今天 GitHub 什么火了”、“Rust 最近热门项目”、“AI 领域趋势日报”、“这个方向有没有值得关注的开源项目”、“帮我做个 GitHub trending 分析”。
Modern Go Web application architecture guide. Use when creating new Go web projects, APIs, or microservices. Covers project structure, tech stack selection, and best practices based on Go standards.
HarmonyOS application development expert. Use when building HarmonyOS apps with ArkTS, ArkUI, Stage model, and distributed capabilities. Covers HarmonyOS NEXT (API 12+) best practices.
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.
Modern Python project architecture guide for 2025. Use when creating Python projects (APIs, CLI, data pipelines). Covers uv, Ruff, Pydantic, FastAPI, and async patterns.
React and Next.js performance playbook distilled from Vercel Engineering guidance. Use when building, reviewing, or refactoring React/Next.js code for waterfalls, bundle size, rendering cost, and client/server data flow.
Provides React patterns for hooks, effects, refs, and component design. Covers escape hatches, anti-patterns, and correct effect usage. Use when reading or writing React components with hooks or effects.
Scaffold or standardize a production-ready repository structure with specs, source layout, tests, CI, agent context, config examples, release notes, and operational docs. Use when starting a new repo, turning a prototype into a maintainable project, adding missing repository foundations, or creating a repo skeleton before implementation. For AGENTS.md-only context scaffolding, use agentsmd-scaffold.
Audit and recommend improvements for a repository's agent-readable context, including AGENTS.md, CLAUDE.md, WARP.md, CONTRIBUTING.md, .agents/skills, and specs/ PRODUCT.md and TECH.md contracts. Use when asked to review, score, assess, or standardize repo instructions, agent onboarding, spec workflows, or cross-repo agent-context conventions. Use agentsmd-scaffold instead when the user wants to generate or apply root/scoped AGENTS.md files.
Use when writing, modifying, or reviewing Rust code. ALWAYS invoke before Rust edits; covers Microsoft Pragmatic Rust guidance for error handling, API design, performance, and idiomatic patterns.
Modern Rust project architecture guide for 2025. Use when creating Rust projects (CLI, web services, libraries). Covers workspace structure, error handling, async patterns, and idiomatic Rust best practices.
Design, audit, or implement application structured logging architecture from repository evidence. Use when a user asks whether or where to add logs, how to choose or migrate a logger, how to standardize events/fields/levels/redaction, how to add HTTP access or panic logs, or why production logs cannot answer an incident question. Do not use merely to tail platform logs or to design a full metrics, tracing, SLO, and incident-management program.
Modern TypeScript project architecture guide for 2025. Use when creating new TS projects, setting up configurations, or designing project structure. Covers tech stack selection, layered architecture, and best practices.
Diagnose slow or freezing VS Code-compatible editors with evidence-first, zero-hardcoded-assumption workflow. Use when the user reports editor lag, typing delay, UI freezes, extension host stalls, file watcher noise, high editor CPU/RSS, uses VS Code/Cursor as a file browser over a large folder, or wants a safe editor performance audit.
当用户要求生成 om-generator 指定日期范围周报时使用；整合 Git 提交、Claude Code 会话、Codex 会话和可选本机记忆记录。
Modern Zig project architecture guide. Use when creating Zig projects (systems programming, CLI tools, game dev, high-performance services). Covers explicit allocators, comptime, error handling, and build system.
Investigate a failing integration test from a GitHub issue. Downloads logs/artifacts, analyzes the failure, examines relevant skills, and suggests fixes. TRIGGERS: investigate integration test, debug integration test, failing integration test, test failure investigation, diagnose test failure, analyze test issue
Query the integration-test storage account to find why a specific skill's tests are failing. Reads blob-stored test result files and surfaces error details. TRIGGERS: why is skill failing, skill test failures, debug skill tests, skill failing tests, analyze skill failures, why are tests failing for skill, skill test errors, investigate skill issues. DO NOT USE FOR: analyzing a GitHub Actions run report or comparing test runs across runs (use analyze-test-run).
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).