Engineering
98,234 rows, by stacks then stars
NasserAlbusaidi/ship-gate/skills/deploy-ceremony Skill
0★ repoDeploy the Rihla Firebase backend (Cloud Functions + Firestore rules + indexes) to prod and keep the deploy state honest. Shows the merged-but-undeployed delta first (pending_deploy.sh), runs the commit-bound deploy + prod-state verify, advances the `backend-deployed` source-of-truth tag, then records the deploy in docs/DEPLOY-LEDGER.md and clears stale "⚠️ NOT deployed" flags. Use when asked to "deploy the backend", "run the deploy ceremony", "ship the functions", or after merging a Functions/rules PR.
ccpowerpack/claude-code-skills/skills/api-design Skill
0★ repoDesign or review an HTTP/RPC API surface before any handler code exists — resource model, error contract, pagination, versioning, batch semantics. Use when asked to "design an API", "add an endpoint", "review this API", "what should this route return", or before implementing any new public interface. Refuses to write handlers until the contract survives an alternatives comparison and every endpoint has its failure responses designed.
GongziTANG/persona-vault/skills/build-persona-vault Skill
0★ repoBuild and maintain one verified, cross-platform knowledge vault for a public person or creator from WeChat public-account and Weibo archives, with full-first then incremental synchronization, stable source IDs, provenance, unavailable-state evidence, Markdown/JSONL exports, and verification. Use when Codex, Claude, or WorkBuddy is asked to 建立人物知识库、汇总某个人的公众号和微博、跨平台归档创作者内容、持续增量更新人物语料、合并 MPVault 与微博 Markdown, or operate PersonaVault.
Ansvar-Systems/agent-affect-skills/skills/agent-cringe Skill
no license0★ repoUse at the end of UX-touching, copy-touching, or user-facing changes to surface things that work but shouldn't ship — scolding errors, empty states that explain nothing, buttons that don't say what they do, dark patterns. Picture a specific person using it. Produces one finding (or one explicit null) recorded in the affect log and the end-of-turn summary.
AmanKrSahu/zeroday-auditor/skills/code-quality-review Skill
0★ repoUse when the user wants a focused code-quality / maintainability review — 'review code quality', 'assess maintainability', 'find code smells', 'check SOLID/DRY adherence', 'is this codebase clean?', 'where's the dead code / duplication / bad error handling', 'refactoring opportunities', 'do we have enough tests?'. Produces a single evidence-backed report (code-quality-review.md) covering maintainability, consistency, smells, error handling, and test coverage. For a full multi-dimension audit use zeroday-auditor instead. Analysis only; never modifies source.
zreed3/codex-conductor/skills/codex Skill
0★ repoDrive the OpenAI Codex CLI (`codex`) as a delegate worker on coding projects — implementing features, fixing bugs, running code reviews, or getting a second-model opinion — using the user's OpenAI subscription tokens. Use this whenever the user mentions Codex, GPT-5, OpenAI, "second opinion from another model", wants to delegate work to another agent, or wants to parallelize work across model providers. Also use it when the user asks to "have codex do it", "ask codex", or compare Claude's and Codex's approaches.
nubasu/Pseudo-Fable-Framework/.claude/skills/agent-framework-setup Skill
0★ repoGuided initial installation of the pseudo-fable framework family into a target project — inspect the target first, interview for a configuration, enforce the exclusivity rules, assemble CLAUDE.md / AGENTS.md / skills / hooks in the correct order with idempotent signature checks, then verify with agent-framework-doctor. Use when asked to install, set up, or add the agent framework (the pseudo-fable family, or any of its frameworks/modules) to a new or existing project.
surendranb/loadout/template Skill
0★ repoOne sentence on WHAT this skill does, then WHEN to use it (situations and trigger phrases). Both halves matter — the description is how the agent decides to invoke the skill. Keep it a single concrete line. No angle brackets and no YAML folded scalars in frontmatter (it enters the system prompt).
sumitake/agent-collab/plugins/agent-collab/skills/agent-runtime-status Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
ldenson1120/job-search-os/skills/handoff Skill
0★ repoThis skill should be used when the user says "create a handoff", "make a handoff doc", "I need to start a fresh chat", "summarize this so I can continue elsewhere", or otherwise signals a long conversation needs to carry forward into a new session without losing context.
vistabylara-dev/vista-claude-skills/skills/cloudflare-workers-audit Skill
0★ repoFree Claude Skills for AI developers, Shopify experts, marketers, and businesses. Built by Vista by Lara.
JohnRothan/Anthropic-Java-Skills/skills/alibaba-java-coding-guidelines/zh Skill
no license0★ repo阿里巴巴《Java 开发手册(黄山版)》编码规约。在编写、审查、重构或评审任何 Java 代码时都应使用本技能——包括命名风格、常量定义、代码格式、OOP 规约、日期时间、集合处理、 并发与多线程、控制语句、注释、异常处理、日志、单元测试、安全规约、MySQL 建表/索引/SQL/ORM、 以及应用分层等工程结构。无论用户是否明确提到“阿里规范 / P3C / 黄山版 / 开发手册”,只要任务涉及 Java 代码的产出或质量把关(如“写个 Java 类 / Service / DAO”“review 这段 Java”“这段代码符合规范吗” “建一张 MySQL 表”“帮我命名”“处理一下异常和日志”),都要主动参考本技能给出的规则与等级。
soreavis/claude-audit-skills/plugins/audit/skills/all Skill
0★ repoOrchestrator that runs the bundled audit skills (security, deep, deps, compliance, tech-stack, forms, a11y, seo, deploy, responsive, hallucination) in sequence against a project and merges their reports into one combined scorecard. All sibling audits ship in this same plugin — nothing else to install. Use when the user wants to run "all audits" / "the full audit suite" / "every pre-launch check" before shipping.
supermodo/skills/skills/config Skill
0★ repoKeeper of a project's supermodo configuration (skills.config.json) and docs scaffold. Use whenever the user wants to view, check, change, fix, or upgrade the supermodo config, set up or onboard a project onto the supermodo skills, start a new supermodo project, or whenever another supermodo skill reports a missing or invalid skills.config.json. Trigger on 'supermodo config', 'set up supermodo', 'configure supermodo', 'bootstrap supermodo', 'change the coverage target', 'edit the config', 'add a command to the config' — even when the word 'config' itself is not used.
tamasbege/staff-engineer-skills/plugins/staff-engineer-skills/skills/auth-flow-architect Skill
0★ repoDesign authentication and authorization architectures - OAuth2/OIDC flow selection, JWT vs opaque tokens, refresh token rotation with reuse detection, session management and revocation, token storage rules per client type (SPA, mobile, server, M2M), the BFF pattern, RBAC/scopes/permissions modeling, and multi-tenant claims. Use when building or reviewing login/auth for an app, choosing between sessions and JWTs, integrating an identity provider (Auth0, Keycloak, Entra ID, Cognito), securing an SPA or mobile app, designing API-to-API auth, fixing token expiry/refresh bugs, or when the user asks how to do auth properly.
processcube-io/ProcessCube.Agent.Skills/skills/release-process Skill
no license0★ repoErstellt Releases (Stable, Insiders, Development) mit Single-Branch-Workflow (nur main). Nutze diesen Skill wenn der Benutzer eine Version erstellen oder releasen möchte.
muhammederem/chief/.claude/skills/backend/fastapi Skill
no license0★ repoWasDavidOliveira/irracional-skills/critical-thinking Skill
no license0★ repoUse when revisar ou refatorar código com responsabilidades mistas, nomes abreviados ou opacos, literais mágicos, fluxo via try/catch, aninhamento profundo, cheiros de performance (N+1, Big-O alto), abstrações sem ganho claro, dívida técnica acumulada ou “code slop”; ou quando o pedido pede manutenibilidade e clareza sem overengineering corporativo.
deyil/gh-aw-skills/skills/gh-aw-workflow-maintenance Skill
0★ repoEdit, fix, debug, update, and upgrade existing Github Agentic Workflows (gh-aw) with the correct recompile behavior, strict validation, run-analysis workflow, and factory-baseline comparisons when relevant.
jovd83/junit5-skill/analysis Skill
0★ repoUse when Codex needs to derive JUnit 5 test scenarios from requirements, code, or existing test case definitions such as TDD, BDD, and plain-text specifications.
hashwnath/microsoft-cape-mcp-skills/skills/database_query Skill
0★ repoExecute SQL queries against enterprise databases via MCP
javalenciacai/develop-skills/.agents/skills/architect Skill
0★ repoSoftware Architect. Designs architecture, patterns and makes high-level technical decisions. Reports to TL. Use when: (1) Designing software architecture or system design, (2) Defining architectural patterns (microservices, MVC, event-driven), (3) High-level technical decisions or technology evaluation, (4) API design or service integration architecture, (5) Scalability, performance or reliability design, (6) Writing ADRs (Architecture Decision Records), (7) Database schema design or data architecture.
peanutsee/skills/skills/blueprint-architect-expert Skill
0★ repoRepository of skills I use
Jeelislive/SkillPack/.agents/skills/vercel-cli-with-tokens Skill
0★ repoDeploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login - e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
badass-courses/a11y-agent/.claude/skills/a11y-agent Skill
no license0★ repoAccessibility expertise for building inclusive web interfaces. Covers semantic HTML, ARIA, keyboard interaction, screen reader support, color contrast, focus management, responsive zoom, motion safety, automated testing, and organizational culture. Use when building or reviewing any web UI to ensure it works for everyone.
LoogacyStudio/skills/.agents/skills/create-subagent Skill
0★ repoUse when an agent must decide whether a task should stay single-agent or be compiled into a reusable multi-agent topology with explicit subagent roles, context boundaries, orchestration contracts, and provider-specific implementation overlays.
alexleekt/agents/skills/my-agent-file-conventions Skill
no license0★ repo**ALWAYS use when:** creating, editing, or reviewing AGENT.md or claude.md files. **ALWAYS use when:** deciding what belongs in agent configuration vs project docs. **ALWAYS use when:** the user says "agent file", "agent config", "behavioral rules", "claude.md", "AGENT.md", "what goes in agent files", or "agent guidelines". **DO NOT use for:** tech stack recommendations (@skills/my-tech-stack) or VCS workflows. Defines the boundary: behavioral rules (agent files) vs documentation (README, ARCHITECTURE). Covers file locations, templates, common mistakes, and the "does this belong?" decision tree.
MadaraUchiha-314/sherma/skills/sherma Skill
0★ repoBuild LLM-powered agents with sherma — declarative YAML or programmatic Python, with multi-agent orchestration, skills, hooks, and A2A integration.
topcoder1/jz_skills/skills/pricing-optimization Skill
0★ repoFind the revenue-maximizing pricing/tier grid for a SaaS or data product and PROVE the ranking is robust — not just assert it. Builds a competitor-anchored willingness-to-pay model, sweeps a grid search for the optimum, then verifies with Monte Carlo sensitivity, adversarial falsification, and anchor break-point analysis. Use when asked to "optimize pricing", "what price maximizes revenue", "which tier grid is best", "price these tiers", "maximize total value/ARR", "should we charge X or Y", or to evaluate/compare candidate pricing proposals. Proactively suggest when a user is deciding between pricing options for a product.
guillempuche/ai-standards/.claude/skills/release Skill
0★ repoDetect changes in skills/agents, ask about version bumps, update frontmatter versions, and deploy individual repos to GitHub.
BartWaardenburg/isagentready-skills/ai-content-discovery Skill
0★ repoFixes AI content discovery issues — creates and optimizes robots.txt, AI crawler directives, XML sitemaps, llms.txt, meta robots tags, and content freshness signals so AI systems can find, crawl, and understand website content. Use when asked to "fix robots.txt", "add llms.txt", "create a sitemap", "allow AI crawlers", "fix AI discoverability", "improve AI content discovery score", "make site crawlable by AI", "add dateModified", "fix content freshness", or any robots.txt, sitemap, or llms.txt task.
yangshu2087/Codex/.agents/skills/architecture-decision-review Skill
no license0★ repoUse when a task involves architecture decisions, migrations, rollout planning, system boundaries, technical tradeoffs, or rollback risk.
ninjaproger/skills/skills/gemini-agent Skill
no license0★ repoDelegate complex, multi-step coding tasks to the Google Gemini CLI agent running in the background. Use when the user wants to offload autonomous coding work to gemini — including TCA feature development (new reducer/view/tests in a modular iOS app) and iOS Simulator automation (build, install, navigate, inspect). Gemini runs non-interactively via `gemini "prompt"`, handles tool calls and file edits autonomously, and returns a final summary. Use for tasks that benefit from background execution: "implement X feature using gemini", "have gemini add tests for Y", "use gemini to navigate the simulator and verify Z", "run gemini in the background to build this".
Crawlio-app/crawlio-plugin/skills/crawl-site Skill
0★ repoUse this skill when the user asks to "crawl a site", "download a website", "mirror a site", "scrape a site", or wants to download web pages for offline access or analysis. Configures Crawlio settings based on site type, starts the crawl, monitors progress, and reports results.
javicasper/memory-forge/.opencode/skill/memory-forge Skill
0★ repoCLI-agnostic continuous learning for AI coding agents. Supports Claude Code, OpenCode, Codex, Cursor. Monorepo-ready with distributed docs and skills.
The same file is in 5 other repositories
RileyCornelius/Code-Skills/skills/code-debugging Skill
0★ repoInvestigate bugs, failing tests, broken builds, performance regressions, and unexpected behavior by finding root cause before fixing. Use when something is failing or unclear, especially after unsuccessful fix attempts or when the cause is not yet proven.
WhizZest/agent-logger/skills/log-memory-searcher Skill
no license0★ repo智能日志回忆与搜索助手 - 当需要回忆过去事件、查找历史记录或整理某段时间的工作时使用。通过元数据索引快速定位相关日志文件。支持做梦模式,模拟人类做梦整理记忆的效果。支持入梦提示集管理,维护可复用的分析视角和一次性续梦提示。
airweave-ai/cursor-plugin/skills/airweave-setup Skill
no license0★ repoSet up and integrate Airweave into applications. Use when the user wants to install Airweave, create collections, connect data sources, configure MCP servers, or set up the SDK to integrate Airweave into their app. For developers building with Airweave.
up1/demo-api-testing-with-playwright-skill/.agents/skills/playwright-skill/ci Skill
no license0★ repoProduction-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.
The same file is in 1 other repository
lx-wnk/skills/skills/agent-context-update Skill
0★ repoUpdate Agent-Context to the latest version — refreshes shared infrastructure files while preserving all project-specific configuration, memory, and skills. Use this skill whenever the user asks to update Agent-Context, upgrade Agent-Context, sync Agent-Context, or says things like "update agent-context", "get latest agent-context", "refresh context files", "sync agent infrastructure". Also use when the user wants to check if a newer Agent-Context version is available.
neumie/almanac/skills/agents-md/agents-md-map Skill
0★ repoUse when mapping where CLAUDE.md or AGENTS.md files should exist. Scans for non-obvious complexity, evaluates existing files, identifies gaps. Run before agents-md-audit on each flagged file.
Acceptance criteria to test cases
jovd83/test-design-orchestrator/acceptance-criteria-to-test-cases Skill
0★ repoUse this skill when Codex needs to convert user stories or acceptance criteria into traceable behavior-focused scenarios or structured test cases.
konecty/skills/skills/konecty-data Skill
0★ repoAll Konecty CRM data operations through the Konecty user MCP server: find/search/filter records, cross-module queries and aggregations, create records, update records (fetch-first with _updatedAt), delete records (preview + confirm), upload/download/delete files, session login, and module/field discovery. Use when user wants to: buscar registros, pesquisar, listar, filtrar dados, criar registro, inserir dado, criar contato/oportunidade/atividade, atualizar, editar, modificar registro, deletar, remover, apagar registro, fazer upload, anexar arquivo, enviar imagem, listar módulos, descobrir campos, consultar o CRM, search records, create record, update, delete, upload file, discover fields, query CRM data. Requires the konecty MCP server connected (see konecty-setup). Do NOT use for metadata/schema ops (documents, lists, views, access, hooks, namespace) — use konecty-meta; do NOT use for connecting/configuring the MCP server — use konecty-setup.
Anoxxx/skillcache/examples/mcp-builder Skill
no license0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Dotnet backend clean architecture
luismpenholato/maurao-skills/skills/dotnet-backend-clean-architecture Skill
0★ repoClean Architecture + CQRS (MediatR) for .NET 10 backend APIs. Builds and maintains APIs with vertical slice (Features), Commands/Queries, handlers, validators, repositories, FluentMigrator, Refit integrations. Use when creating or refactoring .NET APIs, adding endpoints, commands, queries, entities, or when the user mentions Clean Architecture, CQRS, or MediatR.
pessini/aria/backend/agents/n8n_agent/skills/n8n-code-python Skill
0★ repoWrite Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes.
The same file is in 4 other repositories
rulebased-io/harness/rulebased-harness/skills/eval-log Skill
0★ repoEvaluates a Claude Code conversation log against harness compliance — measures human intervention, agent autonomy, tool usage, and session patterns
The same file is in 1 other repository
iceflower/agent-skills/api-design Skill
0★ repoREST API design principles including URL design, HTTP methods, status codes, pagination, versioning, security, and OpenAPI documentation. Use when designing or implementing REST APIs.
taujiong/skills/skills/git-commit Skill
no license0★ repoGuide to automate the git commit workflow. Use when users want to commit changes, stage and commit, generate a commit message, or finalize an editing session with a commit. Also triggers when users mention commit my changes, help me commit, ok commit it, or looks good commit.
ahostbr/LiteCLI/packages/litecli-pack/skills/coding-agent Skill
0★ repoDelegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
The same file is in 1 other repository
gdebenedetti/skills/skills/mcp-builder Skill
0★ repoGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
bensonmaxai/minis-coding-success-skills/skills/deployment-verification Skill
no license0★ repoUse when code works locally but you need to verify it will also work after deployment, packaging, or environment changes. Optimized for Minis on iOS: compare local vs target assumptions, check config/assets/startup paths, verify environment-sensitive behavior, and catch deployment-only failures before or after release.
jovd83/Cypress-skill/analysis Skill
0★ repoRequirements-analysis skill for Cypress planning and implementation. Use when Codex needs to extract testable behaviors, acceptance criteria, risks, dependencies, or open questions from tickets, specs, markdown docs, or other requirement sources before writing tests or coverage plans.
rulebased-io/claude-plugin/packages/harness/skills/eval-log Skill
0★ repoEvaluates a Claude Code conversation log against harness compliance — measures human intervention, agent autonomy, tool usage, and session patterns
The same file is in 1 other repository
markab21/voluum-cli/plugins/voluum-cli-assistant/skills/voluum-setup-install Skill
0★ repoInstall and configure voluum-cli on Linux/macOS, with Windows support via WSL.
kpatryk/skills/skills/bun Skill
0★ repoBun is an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use this skill whenever the user needs to work with Bun — whether running TypeScript/JSX files, managing packages, bundling applications, or running tests. This includes questions about bun run, bun install, bun build, bun test, bunx, .env loading, or any Bun-specific features. Even if the user doesn't explicitly mention Bun, use this skill when they're working with JavaScript/TypeScript projects and Bun could be a suitable alternative to Node.js/npm/Webpack/Jest workflows. Key capabilities: Execute JS/TS/JSX natively (no build step), install packages with bun.lockb, bundle for browser/node/bun targets, run Jest-compatible tests, auto-load .env files, serve HTTP with Bun.serve(), access Bun-specific APIs (Bun.file, Bun.spawn, bun:sqlite, Bun.redis), and use bunx to run package binaries.
namikazebadri/basic-programming-skill/skills/apply-software-patterns Skill
no license0★ repoChoose, reject, explain, review, and incrementally apply software design patterns and architecture patterns with strong attention to readability, maintainability, testability, explicit dependencies, and overengineering risk. Use when Codex needs to decide whether a pattern fits a codebase, compare alternatives, review code for human-readable structure, refactor toward clearer boundaries, explain patterns to a teammate, or recommend architecture direction for a growing system.
devcsde/oatda-openclaw-skills/skills/oatda-compare-models Skill
no license0★ repoCompare multiple LLM models (GPT-5, Claude Sonnet 4.5, Gemini 3, DeepSeek v4-pro, Grok 4, etc.) side-by-side in one parallel request via OATDA's unified AI gateway. Triggers when the user wants to benchmark models, evaluate quality differences, pick the best LLM for a task, run "gpt vs claude vs gemini" comparisons, do multi-model evaluation, or find the cheapest/best/fastest answer. Returns each model's output plus token usage and cost per model.
airRnot1106/skills/skills/next-bundle-analyzer Skill
0★ repoAnalyze and quality-check this project's Next.js 16 (Turbopack) bundle sizes using `pnpm analyze:output` (i.e. `next experimental-analyze --output`). Use when the user wants to: inspect bundle sizes, find large dependencies, detect duplicate modules, quality-check production builds, or get optimization recommendations. Triggers on requests like "analyze the bundle", "check bundle size", "find large packages", "bundle quality check", "バンドル分析", "バンドルサイズ確認", or when the user mentions `next experimental-analyze`.
HyunKN/harness-kit/skills/harness-bootstrap Skill
0★ repoUse when a repository needs the reusable docs harness installed or refreshed. Trigger when the user wants issue tracking docs, learning-note templates, playbooks, or role-based documentation folders added to a new or existing Codex project.