Development Claude Skills
8 676 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 1 172 copies of these same skills sitting in other people's repositories — counted once here, not 1 172 times.
8 676 unique 759 authors 5 250 updated this month 1 369 from vendors
Design and review predictable public APIs for TypeScript, JavaScript, React, and React Native libraries. Use when shaping exported functions, classes, hooks, options objects, event and listener APIs, error behavior, naming, cross-platform abstractions, or JS-only packages. Pair with build-nitro-modules when the library is backed by Nitro.
> (1) Designing epitope-targeted nanobodies or scFvs, (2) Needing CDR design on a fixed framework, (3) Working on antibody-format binders rather than miniproteins. For miniprotein binders, use binder-design (BoltzGen, BindCraft, RFdiffusion, Mosaic). For structure validation, use boltz or chai.
> Structure prediction using Chai-1, a foundation model for molecular structure. (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.
> Generate protein backbones using RFdiffusion, a diffusion-based generative (1) Designing binder scaffolds for a target protein, (2) Generating novel protein backbones from scratch, (3) Scaffolding functional motifs into new proteins, (4) Specifying hotspot residues for interface design, (5) Creating symmetric oligomers. For sequence design after backbone generation, use proteinmpnn. For structure validation, use alphafold or chai. For QC thresholds, use protein-qc.
>- Vibe Coding（用 AI 写代码）开发过程中的避坑与自救——真正翻车大多发生在"开工后"。 当用户说"AI 越改越乱"、"demo 改坏了退不回去"、"AI 老忘记之前说的"、"功能越加越多很乱"、 "AI 说做好了但其实没用"，或者正在用 AI 持续开发一个项目时，主动使用此 Skill。 涵盖：管理 AI 对话（防忘事）、守住范围（防膨胀）、保住能用的版本（防丢失）、让 AI 证明给你看（防轻信）， 以及哪些事必须找真人工程师的「红线」，和把一切串起来的「项目说明书」。 这是 vibe-coding-kit 套件里贯穿整个开发过程的 Skill，建议从第一行代码起就配合使用。
>- 把验证过的 Vibe Coding demo，做成能长期运行、给别人用的正式系统。 当用户说"想上线"、"怎么部署"、"这个 demo 想做成正式的"、"要注意安全吗"、"怎么测试我的项目"， 或者准备把代码开源/公开发布时，使用此 Skill。涵盖开发规范、安全基线、部署、手动验收、文档要求。 这是 vibe-coding-kit 套件里负责"从 demo 到上线"的 Skill。 即使用户没明说"上线"二字，只要 ta 准备把一个能跑的东西交给别人用、或放到服务器/公网上，就应主动用本 Skill。
Run sentence-level traceability verification on a Data2Story blog (verify.py -> verifier.json), then emit the in-page Inspector panel (the reader-facing runnable verifier) + the verify/ artifacts (verify_map.json, run_cells.json, the reproducible notebook, cell_registry.json). Mostly Python; the runnable layer recomputes each computation in-browser from its inlined data and grades it against the published output, while the bundled notebook re-executes from raw data. Use verify.py at Stage 6.4 (after validate.py, before the Critic) and generate_viewer.py at Stage 7 after the Programmer authors the verify/ files and pastes the panel shell. Triggers: a built index.html plus the role JSONs exist, or you need the traceability map / the in-page runnable verifier.
Run sentence-level traceability verification on a blog, then generate viewer.html with interactive evidence panel. No LLM needed — pure Python.
> Security audit and vulnerability scanner for AI agent skills before installation. directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. "check skill before install", "skill security check", "skill vulnerability scan".
Dependency Auditor
A skill to build and manage Home Assistant configurations. Use when using the Home Assistant Builder (`hab`) CLI to inspect, create, update, delete, operate, or troubleshoot Home Assistant resources; when a user mentions hab, Home Assistant CLI automation, Lovelace/dashboard edits, helpers, automations, scripts, backups, ESPHome, or Home Assistant operations from a terminal.
Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the code docs.
A Go security skill for reviewing code
|
| docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Provides structured execution with profile detection, dependency handling, review checkpoints.
| Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
|
| docs/wip plan OR a standalone task (bug fix, GitHub issue, one-off change). Provides structured execution with profile detection, dependency handling, review checkpoints.
| Code review of current git changes with an expert senior-engineer lens. Detects SOLID violations, security risks, and proposes actionable improvements. Use when performing code reviews.
> training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.
> Use when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the planning stage of a prompt → plan → execute → debug pipeline. It decomposes the prompt from first principles (objective, end state, environment, building blocks, tools, packages), breaks the work into PR-sized tasks each tied to a component with its files, tests, and dependencies, orders them topologically, splits each into atomic subtasks, then a separate principal-engineer agent critiques the plan for alignment, coverage, sizing, and executability; it revises until the critique passes, emitting a plan.md layout and a structured tasks.json that a junior engineer or a smaller model can execute correctly. Not for executing, scaffolding, or debugging the plan (those are downstream loops), and not for research proposals or experiment plans.
>- Use when a developer wants to iterate on ONE specific Agent Observability / LLM Obs trace whose output they didn't like — re-running that trace against their LOCAL code, seeing a concise diff of the old vs new output, and looping (change code → replay → diff) until satisfied. Invoked as a trace"; "this trace's output is wrong, fix it and re-run"; "re-run trace <id> with <change>"; pasting a trace id from the Agent Observability UI with a description of what to fix. It fetches the trace via the datadog-llmo MCP or the pup CLI, edits code, re-runs the app to emit a NEW trace, and diffs the two — no local server, no browser. For agents traced with ddtrace / LLM Obs (Python first-class), with JSON-serializable entry agent-observability-replay-experiment), building an experiment from a dataset/CSV, writing evaluators, root-causing failed traces, or RUM/HTTP session replay.
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the Agent Observability SDK", or has `ddtrace` installed and wants idiomatic SDK code.
Bootstrap evaluators from production traces — by default propose online LLM-judge evaluators and, after you confirm, create them in Datadog as disabled drafts (never auto-enabled); on request emit Python SDK code or a framework-agnostic JSON spec instead. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Configure Unified Service Tags and verify Single Step Instrumentation (SSI) injection on Linux hosts — SSI automatically instruments applications for APM without code changes. Only use if the Datadog Agent is already installed.
Guides developers building Datadog Apps with TypeScript, React, the @datadog/apps scaffolder, and @datadog/vite-plugin. Use when a user wants to scaffold, run, debug, upgrade, build, upload, publish, upload without publishing (draft upload), add an upload-no-publish script, set up CI/CD, use OAuth or API/application key auth, trigger/poll Workflow Automation, choose DDSQL or Action Catalog for backend data access, or query app datastores with DDSQL, including backend function troubleshooting.
Diagnose and fix Single Step Instrumentation (SSI) issues on Linux hosts — SSI automatically instruments applications for APM without code changes. Only use if the agent and SSI are configured but traces are missing or instrumentation is not working.
Generate auditor-ready compliance evidence from Datadog Audit Trail for SOC 2 and PCI DSS. Maps framework controls to specific query patterns and produces formatted output.
> Datadog Browser SDK — RUM, Logs, Session Replay, profiling, product analytics, and error tracking setup, configuration, and migration. Use when upgrading Browser SDK versions, setting up RUM or Logs, or troubleshooting browser-side Datadog instrumentation.
> Upgrade Datadog Browser SDK from v4 to v5. Use when encountering removed options like proxyUrl, sampleRate, replaySampleRate, premiumSampleRate, allowedTracingOrigins, or deprecated APIs like addRumGlobalContext, removeUser, or when a project references datadoghq-browser-agent.com CDN with /v4/ paths.
> Upgrade Datadog Browser SDK from v6 to v7. Use when encountering removed options like betaEncodeCookieOptions, allowFallbackToLocalStorage, trackBfcacheViews, usePciIntake, changed APIs like forwardErrorsToLogs, startDurationVital, stopDurationVital, or when a project references datadoghq-browser-agent.com CDN with /v6/ paths.
> Upgrade Datadog Browser SDK from v5 to v6. Use when encountering removed options like useCrossSiteSessionCookie, sendLogsAfterSessionExpiration, or when dropping IE11 support, or when a project references datadoghq-browser-agent.com CDN with /v5/ paths.
Datadog CLI (Rust). OAuth2 auth with token refresh.
| 当系统提示面向编程代理（Coding Agent）场景时调用。适用于构建代码编辑、文件操作、Git 工作流、自动化编程助手的系统提示。不适用于代码解释或教学场景（无文件修改），不适用于 DevOps 基础设施配置（非代码层），不适用于纯对话式代码问答（无工具调用）。
| 当需要为 AI 定义工具接口、设计调用规范、实现工具发现与编排机制时调用此 skill。典型场景包括：设计 AI agent 的工具集、定义 JSON Schema/XML/TypeScript 格式的工具描述、实现工具权限控制与并行调度、设计子代理委托架构。 不适用于：定义 AI 身份（persona-design）、安全规则（safety-guardrails）、记忆存储（memory-system）。 关键 trigger 信号：AI 需要调用外部 API 或服务、工具数量超过 10 个需要发现机制、需要区分工具权限层级、需要子代理并行执行、工具调用涉及敏感操作需要审批。
> Audit, design, and implement AI agent harnesses for any codebase. A harness is the constraints, feedback loops, and verification systems surrounding AI coding agents — improving it is the (set up components), Design (full strategy). Use whenever the user mentions harness engineering, agent guardrails, AI coding quality, AGENTS.md, CLAUDE.md setup, agent feedback loops, entropy management, AI code review, vibe coding quality, harness audit, harness score, AI slop, agent-first engineering. Also trigger when users want to understand why AI agents produce bad code, make their repo work better with AI agents, set up CI/CD for agent workflows, design verification systems, or scale AI-assisted development. Proactively suggest when discussing AI code drift or controlling AI-generated code quality.
> Use this skill whenever working with the Canvas LMS REST API — including creating or updating modules, pages, and files for a course, building sync scripts, managing course structure programmatically, or uploading files and linking them in pages. Trigger this skill any time the user mentions Canvas, LMS, course sync, module pages, or file uploads to Canvas. Also use when writing or debugging any Python script that calls the Canvas API.
> Two-phase code audit workflow for empirical research scripts. Use this skill when the user asks to review, audit, check, validate, or verify R or Python research code — especially code that processes licensed or sensitive data (WRDS, CRSP, WellDatabase, PLIDA). Also use when the user says "check my code", "review this script", "does this look right", or "audit my analysis."
>- Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
>- Reconstruct and narrate the current development context from contextual commits. Run at session start, when resuming work, or when switching branches. Produces a brief, conversational summary of where things stand.
Automate repetitive audio tasks with Python using PyDub for batch processing, format conversion, normalization, and content assembly. Use when: Processing large numbers of audio files consistently; Converting between audio formats at scale; Normalizing loudness across a batch of files; Assembling intros/outros automatically to episodes; Trimming silence or extracting segments programmatically
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
Apply Segmentation, Targeting, and Positioning framework to identify market opportunities and craft differentiated positioning
Think beyond immediate consequences to understand the chain reactions of decisions. Master Howard Marks' investment framework for seeing what others miss. Use when: **Strategic decisions** where long-term consequences matter; **Policy/rule changes** that will trigger behavioral responses; **Competitive moves** to anticipate market reactions; **Product decisions** where user behavior may shift; **Investment analysis** to see past obvious conclusions
Observe and troubleshoot WhatsApp in Kapso: search Logs across API, Meta webhook, workflow, and webhook-delivery events; debug message delivery; inspect webhook retries; triage API errors; and run health checks. Use when investigating production issues, message failures, workflow behavior, or webhook delivery problems.
Build WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, deploy functions, search workflow Logs, and debug automation behavior. Use when automating WhatsApp conversations and event handling.
Use this skill when you need to parse multi-format API definitions and generate Rest Assured Java test classes; triggers include Rest Assured, RestAssured, and Java API automation.
Use this skill when you need to parse multi-format API definitions and generate Rest Assured Java test classes; triggers include Rest Assured、RestAssured and Java API automation.