Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
45,199 skills from 2,196 repositories · updated 35 minutes ago
5,576 skills
- guardrails-reviewerTestAny-io/testany-agent-skillsReview Project Guardrails, 工程规范评审。Use when: Guardrails 创建或更新后需要作为项目级治理基线做准出,检查触发判定、生成模式、事实标准、下游工作流钩子与规则可执行性。EngineeringNo warnings★ 82↓ —
- account-structure-reviewirinabuht12-oss/marketing-skillsClaude skills for marketing: 49 free marketing skills for Claude Code and claude.ai (Google Ads, Meta Ads, SEO, AI visibility) + the Ryze Google Ads MCP / Meta Ads MCP: claude mcp add ryze --transport http https://connector.get-ryze.ai/mcpEngineeringNo warnings★ 5.8K↓ —
- analyse-agentic-systemzby/commonplaceUse when asked to analyse, review, or refresh an external agent runtime, orchestration system, agent operating layer, agent memory/knowledge/context-engineering system, or narrower model-dependent operational mechanism from inspectable sources.EngineeringNo warnings★ 91↓ —
- api-reviewerTestAny-io/testany-agent-skillsAPI contract review, 接口契约评审。Use when: PRD 完成后、HLD/LLD/实现前需要审查完整契约或既有批准范围内的契约增量,包括 OpenAPI/AsyncAPI/GraphQL/gRPC/WebSocket/SSE/Webhook/SDK/文件格式/IPC-CLI 契约。EngineeringNo warnings★ 82↓ —
- review-prpolyai/adkReview an ADK pull request or local branch against the repo's review checklist (REVIEW.md) and report blocking issues and nits. Use when asked to review a PR in the polyai-adk repo, or to self-review a branch before opening one.EngineeringNo warnings★ 83↓ —
- competitive-pricing-packaging-reviewLMTYdotcom/skillsAnalyze or pressure-test the home product's own pricing and packaging using current competitor offers, recent pricing changes, customer and deal evidence, and company context. Use when the deliverable is a monetization decision - reviewing a pricing change, planning packaging, deciding whether the company should respond to a competitor price move, or asking what market evidence should inform pricing. Not for a live buyer price objection, a pricing-news briefing, or profiling a competitor whose pricing moved.EngineeringNo warnings★ 83↓ —
- abstract-state-analyzerArabelaTso/Skills-4-SEPerforms abstract interpretation over source code to infer possible program states, variable ranges, and data properties without executing the program. Reports potential runtime errors including out-of-bounds accesses, null dereferences, type inconsistencies, division by zero, and integer overflows. Use when analyzing code for potential runtime errors, performing static analysis, checking safety properties, or verifying program behavior without execution.EngineeringNo warnings★ 259↓ —
- daw-cliGoldwaterfung/StratawrightInstructs agents to control Stratawright DAW via the daw-cli command-line IPC interface. Covers session state, transport, track management, gain staging, VST3/AU plugin hosting, signal routing, clips, MIDI timeline editing, and non-visual DSP analysis & audio intelligence. Requires the DAW application to be running.EngineeringNo warnings★ 124↓ —
- agentica-claude-proxyparcadei/Continuous-Claude-v3Guide for integrating Agentica SDK with Claude Code CLI proxyEngineeringNo warnings★ 3.9K↓ —Also in 1 other repo
- demo-skillAdyen/agent-marketplaceagent-marketplace is a command-line tool that installs shared AI agent resources into the AI coding tools you useEngineeringNo warnings★ 74↓ —Also in 3 other repos
- vendor-reviewBevel-Software/HexisEvaluate a vendor — cost analysis, risk assessment, and recommendation. Use when reviewing a new vendor proposal, deciding whether to renew or replace a contract, comparing two vendors side-by-side, or building a TCO breakdown and negotiation points before procurement sign-off.EngineeringNo warnings★ 120↓ —
- testany-executionTestAny-io/testany-agent-skillsTestany execution 观测与管理 - 查看进度、查询历史、刷新状态、取消未开始执行、将失败执行交给 debugEngineeringNo warnings★ 82↓ —
- systematic-debuggingJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- credential-leak-detectorJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- agent-identityJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- instar-sessionJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- knowledge-baseJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- mini-program-debugging-skillNocodeMrLi/mini-program-engineering-skill-suiteDiagnose and fix mini-program failures through reproducible, evidence-driven root-cause analysis across source, state, asynchronous timing, caches, mock data, build versions, platform behavior, devices, cloud calls, and external services. Use when users report white screens, crashes, stale or jumping values, missing data, intermittent behavior, permission failures, performance stalls, device-only defects, API or cloud-function errors, source-versus-build mismatches, or regressions whose cause is not yet established. Freezes the observation environment, ranks competing hypotheses, runs discriminating checks, creates a failing regression test before repair, covers analogous states, and never hides a known failure with longer waits, swallowed errors, forced success, or cosmetic patches.EngineeringNo warnings★ 91↓ —
- lmstudio-apiDesko77/claude-code-skills-1cСправочник по HTTP-API LM Studio (сервер локальных моделей, обычно порт 1234). Используй когда надо программно управлять моделями на LM Studio - узнать что загружено, загрузить или выгрузить модель, задать длину контекста и параллельность, отключить размышления модели, - а также при диагностике: модель thinking/reasoning не отключается, enable_thinking игнорируется, ответ приходит пустым а весь бюджет уходит в reasoning_content, запросы падают с HTTP 500 на холодном старте или при загрузке крупной модели, ошибка Context size has been exceeded, Model is unloaded, эндпоинт отвечает 404 или 200 с телом Unexpected endpoint, неверно определяется длина контекста. Содержит проверенные схемы эндпоинтов v1, параметр reasoning, особенности протокола и замеры на 30-35B.EngineeringNo warnings★ 85↓ —
- 1c-ssl-patternsDesko77/claude-code-skills-1cПрикладные сценарии Библиотеки стандартных подсистем (БСП): КАК решается задача разработчика, каким механизмом библиотеки, в каком порядке и с какими ограничениями. Используй когда нужно СДЕЛАТЬ что-то через БСП - запустить задание по расписанию, выполнить долгую операцию в фоне, напечатать форму, раздать права, обновить данные при переходе на новую версию; когда непонятно, какой механизм библиотеки закрывает задачу; когда нужен рабочий порядок вызовов и перечень антипаттернов. НЕ для вопроса о сигнатуре или существовании метода - там 1c-bsp-api. НЕ для регистрации своих обработок и команд в библиотеке - там 1c-bsp-command и 1c-bsp-registration.EngineeringNo warnings★ 85↓ —
- v8unpack-cfDesko77/claude-code-skills-1cРаспаковка и сборка бинарных файлов 1С (CF/CFE/EPF) через Python-утилиту v8unpack. Используй когда нужно распаковать конфигурацию, расширение или обработку в исходники, или собрать обратно.EngineeringNo warnings★ 85↓ —
- iterative-converging-auditJKHeadley/instarPersistent Claude Code agents with scheduling, sessions, memory, and Telegram.EngineeringNo warnings★ 84↓ —
- 1c-platform-docsDesko77/claude-code-skills-1c1C platform API documentation tools via bsl-platform-help MCP server - search, info, members, constructors. Supports keyword, semantic (embeddings), and hybrid search. Use when checking built-in functions, types, methods, or properties of the 1C platform.EngineeringNo warnings★ 85↓ —
- bmad-agent-devalvin-reyes/better-agentic-ideSenior software engineer who implements stories and code changes. Use when the user asks to talk to Amelia or requests the developer agentEngineeringNo warnings★ 85↓ —Also in 1 other repo