Engineering
98,648 rows, by stacks then stars
allanbian1017/backend-codebase-navigator Skill
no license1★Sequentially reverse-engineers, analyzes, and documents unfamiliar backend codebases to extract architectural context, dependencies, and operational workflows.
Create equivalence class table
xhubio/nanook-skill/skills/create-equivalence-class-table Skill
no license1★ repoCreates formatted Excel files with Nanook Decision Tables for any test object (pages, APIs, forms). Includes color formatting, formulas, correct marker logic, CASCADE pattern, and 100% coverage. Trigger: "create equivalence class table", "decision table", "equivalence class table", "test data table", "nanook table"
kuc-arc-f/agent_skills_2ex/skill-gemini-1/.claude/skills/duckdb_init Skill
no license1★ repoローカルに、duckdbファイル作成する。
choutos/agent-skills-spec/examples/api-integration Skill
1★ repoIntegrate with the Acme API for file management operations. Use when uploading, downloading, listing, or managing files via the Acme platform. Triggers on: acme, file upload, file management, acme API.
kiakun-collab/kiakun-skills Skill
no license1★Kiakun 的 AI Agent Skills 集合。包含小红书自动化、B站视频总结、文件夹向量化知识库、中文优先对话、Claude Code 第三方 API 配置、GPT Image 2 异步容错 API 生图、图片型 PPT 可编辑复刻、PPT 重构工作流、游戏 UI 资产流水线、玩家互动设计、纯净交付守卫与客户交付物终稿净化。 当用户要求操作小红书、总结 B站视频、整理文件夹为知识库、默认使用简体中文回复、通过 CC Switch 配置 Claude Code API、通过 GPT Image API 生成或编辑图片、将图片/截图型 PPT 复刻为可编辑 PPTX、按参考图或用户修改稿执行分模式 PPT 重构与 QA、生成/切片/验证/导入 Godot 游戏 UI 资产、审查游戏 UI/玩法互动/引导/失败恢复/挑战链路的玩家体验,要求通用防元信息泄漏的"纯净交付",或要求把客户业务材料净化为保真、可直接交付的终稿时触发。
11Yuxuanyang/polanyi-stack/skills/convert-tacit-to-skill Skill
1★ repoConvert tacit knowledge into a reusable agent or Codex skill by extracting cues, scoping the task, defining boundaries, and packaging the workflow into SKILL.md plus tests. Use when the user wants a fixed agent, reusable skill, or repeatable copilot based on expert judgment.
The same file is in 1 other repository
Digidai/mails-skills/skills/openclaw Skill
1★ repoComplete service registrations autonomously by receiving verification codes. Also: send and receive emails, monitor inbox, search by keyword, download attachments, view threads, filter by label, extract structured data, manage mailbox and webhooks.
ch040602/Skills_Paper-summary Skill
no license1★Resolve a paper from title, DOI, paper page URL, or direct PDF URL; fetch available source text; use the latest available frontier subagents for deep method and experiment analysis; then save a comprehensive Korean Markdown summary.
blackwell-systems/agentskills-code-inspector/inspect Skill
no license1★ repoLaunch a code quality inspector agent to audit defined areas of a codebase. Language-agnostic. Applies a fixed check taxonomy — dead symbols, layer violations, scope overload, coverage gaps, silent failures, duplicate semantics, cross-field consistency, missing tests on exported symbols, unwrapped errors, doc drift, interface saturation, unrecovered panics, context propagation breaks, and init side effects — using LSP-first tool strategies with Tier 1A batch analysis via mcp__lsp__get_change_impact. Returns a severity-tiered findings report with per-finding confidence levels and active LSP tier annotation. Supports --json for structured output, --output for persistence, --checks to target specific check types, and --consumer-repos for cross-repo dead symbol verification. Use when auditing files, packages, or cross-cutting concerns for any of these patterns.
allenli178/yuyan-skills/fastmcp-mcp-builder Skill
1★ repoGuide for creating high-quality MCP (Model Context Protocol) servers using FastMCP, the Pythonic MCP framework. Use when building MCP servers to integrate external APIs or services with tools, resources, and prompts using FastMCP decorators. Includes advanced features like structured outputs, tag-based filtering, dependency injection, custom routes, and CLI development workflows.
suibianqugenichenghaole/memory-skill-system/skills/memory-skill Skill
1★ repoUse when work requires recalling, continuing, classifying, or updating memory across ongoing formal work, personal projects, or reusable methods. Helps route memory by permission, domain, anchor, and type while preventing unsafe context mixing.
andreijirohdev-labs/gen-ai-labs/skills/memory-audit Skill
1★ repoRuns Andrei's cross-project memory/backlog audit — reconciling dev work (GitLab.com projects, Alpine Linux aports on gitlab.alpinelinux.org, GitHub), Leaflet.pub blog drafts, Obsidian notes, and Google Drive into a single status report + prioritized action list. Trigger this whenever Andrei explicitly says "run memory audit" (or close variants like "audit my backlog", "memory check-in"), whenever a monthly or quarterly check-in is due or requested, and whenever Andrei mentions specific tracked projects or drafts by name (nixops-config, aports/gh package, Recap Time Squad, Leaflet.pub drafts, homelab/NixOS config work) in a way that implies "where did I leave this?" Do not wait for Andrei to spell out the full routine each time — this skill already knows the sources, the staleness rules, and the output format.
yu-iskw/openspec-skills/.cursor/skills/implementing-agent-skills Skill
no license1★ repoImplements new Agent Skills for the project. Identifies the AI coding tool (Cursor, Claude Code, Gemini CLI), ensures specification compliance, and provides specialized templates. Use when creating, authoring, or adding a new skill, or when the user asks about Agent Skills format or SKILL.md.
The same file is in 1 other repository
Terraform schema inspector skill
quixoticmonk/terraform-schema-inspector-skill Skill
1★Identify Terraform provider support for resources, data sources, actions, list resources, ephemeral resources, and functions. Use when checking provider capabilities, asking "what resources does X provider support", "does provider Y have actions", or querying specific provider features.
ProSkillsMD/avenger-initiative Skill
1★Encrypted GitHub backup and restore for any OpenClaw agent system. Creates branch-per-night backups with smart retention (7 daily, 8 weekly, 12 monthly branches). Backs up openclaw.json (AES-256 encrypted), agent memories, SOUL/IDENTITY files, cron jobs, and custom skills to a private GitHub vault. Each backup auto-generates a human-friendly README.md inside the vault with purpose, full contents table, branch structure, step-by-step restore instructions, and Avenger agent commands. Triggers on phrases like "avenger backup", "backup system", "push to vault", "sync vault", "avenger restore", "restore from vault", "setup avenger", "avenger status", "avenger init", "configure backup", "set up backup". Also auto-runs after any critical config change.
The same file is in 1 other repository
Aliciawque/openclaw-personalized-agent-forge/01-digital-ip-agent Skill
no license1★ repoTurn a public creator, blogger, podcaster, YouTuber, or X/Twitter personality into a deployable OpenClaw agent. Use when the user provides a YouTube URL, X handle, creator name, podcast host, or asks for things like "turn this creator into an agent", "clone this creator's style", "digitalize this KOL", or "generate agent files from this public persona". Produce an OpenClaw persona package centered on `soul.md`, `identity.md`, `memory.md`, and `agents.md`, plus a recommended supporting-skill stack.
dortort/skills/skills/cloudflare-iac Skill
no license1★ repoBest practices for Cloudflare infrastructure as code using Terraform and Wrangler together. Use this skill whenever the user is setting up Cloudflare Workers, Pages, KV, D1, R2, Queues, or other Wrangler-managed resources alongside Terraform — especially when they need to pass resource IDs between Terraform and Wrangler, automate deployments via CI/CD, or structure a Cloudflare project for infrastructure as code. Also trigger when the user mentions 'Terraform and Wrangler,' 'Cloudflare IaC,' 'wrangler.toml from Terraform,' 'Cloudflare CI/CD,' or asks how to connect Terraform-managed resources to Workers.
sadiksaifi/skills/snap-agents-md Skill
no license1★ repoCreate, regenerate, or refine AGENTS.md repo instruction scopes. Use for project agent instructions, monorepo instruction layouts, stale AGENTS.md rewrites, instruction aliases, or bootstrap agent context. Trigger on "/snap-agents-md", "snap agents md", "write AGENTS.md", "fix AGENTS.md", "project AI instructions", or equivalent phrasing.
mmtmr/pageindex-rag Skill
no license1★Build reasoning-based RAG systems using PageIndex architecture. Replaces vector databases with hierarchical table-of-contents indices and LLM-driven navigation. Use when (1) implementing RAG for long structured documents (financial reports, legal contracts, technical manuals), (2) improving existing vector-based RAG systems with poor accuracy on structured content, (3) designing document indexing strategies with semantic coherence, (4) explaining PageIndex concepts including reasoning-based retrieval, hierarchical navigation, and cross-reference following, or (5) handling documents with internal references and multi-turn conversations. Focuses on technical architecture, core research insights, and practical implementation patterns rather than using the PageIndex package directly.
jaymay549/ai-model-selector Skill
1★Use when selecting AI models, configuring API parameters, or implementing LLM calls. Covers OpenAI (GPT-5.2, GPT-5.1, GPT-4.1, o3), Anthropic (Claude 4.5), Google (Gemini 2.5/3), DeepSeek (V3.2, R1), and embedding models with specs, gotchas, and code templates.
PeterOla/agentic-workflow-orchestra Skill
1★Orchestrates AI agent work across planning, implementation, integration, QA, and release. Defines phases, gates, handoff logs, startup checklists, and parallel-safety rules for software projects.
nanami7777777/chinese-fullstack-skills/api-error-handling Skill
1★ repoUse this skill when implementing error handling in APIs, backend services, or full-stack applications. It provides decision trees for when to use which HTTP status code, how to structure error responses for Chinese teams, how to handle database errors, third-party API failures, validation errors, and authentication errors with proper logging and user-facing messages.
The same file is in 1 other repository
magallon/testing-toolkit/e2e-testing Skill
1★ repoGenerates and manages end-to-end tests for critical user flows in any web project. Covers test design, Page Object Model, selector strategy, wait patterns, auth state reuse, test data management, network mocking, visual regression, accessibility testing, flaky test diagnosis, and CI/CD pipeline configuration. Stack-agnostic — adapts to Playwright, Cypress, Selenium, Laravel Dusk, Capybara, or any browser automation framework. Use this skill when the user asks to write E2E tests, automate browser tests, test user flows end-to-end, fix flaky tests, set up visual regression testing, configure E2E in CI/CD, debug failing E2E tests, or test across multiple browsers. Also triggers when the user mentions Playwright, Cypress, browser testing, smoke tests, critical path testing, or end-to-end test automation. Works with testing-strategy — use testing-strategy first to decide WHAT to test, then this skill to implement the E2E tests.
kylebrodeur/wordpress-agent-kit/skills/wp-bootstrap Skill
no license1★ repoBootstrap a new or existing WordPress project with the full wp-agent-kit system: monorepo detection, Composer/WPackagist/SatisPress setup, Playground local dev, WP Engine dev/staging/production, CI gate, git hooks, and plugin packaging. Use when setting up a new WordPress project from scratch, onboarding an existing codebase, or wiring up a monorepo with multiple plugins/themes.
broomva/control-metalayer/.skills/agent-consciousness Skill
1★ repoPersistent consciousness architecture for autonomous AI agent development. Synthesizes three substrates — control metalayer (behavioral governance), Obsidian knowledge graph (declarative memory), and conversation log bridge (episodic memory) — into a self-evolving context layer. Use when designing agent memory systems, implementing cross-session context persistence, building knowledge graphs for AI agents, setting up conversation history capture, or architecting feedback loops that let agents learn from prior sessions. Triggers on "agent memory", "session persistence", "knowledge graph", "conversation history", "consciousness stream", "cross-session context", "agent learning", or "self-evolving development".
headlike-oradexon12/skills/esign-automation Skill
1★ repoAutomate document signing workflows and operations using the eSignGlobal platform.
jtmthf/skills/.agents/skills/skill-creator Skill
no license1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
minghinmatthewlam/skills-audit Skill
1★Audit agent skills in a repo against best practices — checks .claude/skills/ and .agents/skills/ for quality, structure, and coverage gaps. Use when the user wants to review, improve, or evaluate their skills, or when they mention skill quality, skill audit, or skill best practices.
michaelwinczuk/swarm-orchestrator Skill
1★Design, build, and debug multi-agent systems and agent swarms. Use this skill whenever the user wants to create a team of AI agents, orchestrate multiple agents working together, design agent architectures, implement agent communication patterns, build agent pipelines, debug multi-agent failures, or optimize agent costs. Also use when the user mentions swarms, agent teams, multi-agent systems, agent orchestration, agent pipelines, chalkboard patterns, or agent-to-agent communication.
oktsec/audit Skill
1★Security audit for AI-built code. Runs 130+ checks across OWASP Top 10, auto-detects your stack, and produces a graded report (A-F) with exact code fixes. Covers secrets, injection, auth, database access control, AI/LLM security, payments, and infrastructure.
duckyman-ai/agent-skills/skills/capcut-editor Skill
1★ repoRead, analyze, and create CapCut desktop (macOS) video editing projects programmatically. Use this skill whenever the user mentions CapCut, video editing with CapCut, reading CapCut projects, creating CapCut-compatible drafts, adding video/audio/text tracks to CapCut, or wants to automate any CapCut desktop workflow. Also use when the user wants to batch-create video projects, insert media into CapCut, or manage CapCut project files.
RandyPen/cdpm/skills/cdpm-agent-sdk Skill
no license1★ repoTypeScript SDK guide for AI agents managing CDPM positions. Defines permission boundaries, operation workflows, automation strategies, and the Scallop and Kai SAV supply/redeem APIs agents share with owners and protocol bots. Use when building automated liquidity management agents.
0rcaaa/icron/icron/skills/cron Skill
1★ repoSchedule reminders and recurring tasks.
The same file is in 1 other repository
d-oit/do-web-doc-resolver/.agents/skills/agent-browser Skill
1★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Betswish/meta-skill-generator Skill
1★Use when users want to create, revise, or scaffold a Codex skill from a plain-language brief. Especially relevant when they ask for a new SKILL.md, want to convert workflow requirements into a reusable skill, or need help defining trigger conditions, structure, bundled resources, or UI metadata for a skill.
xpepper/pr-review-agent-skill/copilot-review-loop Skill
no license1★ repoUse when you want GitHub Copilot to review a PR and automatically address its feedback within the current agent session. For any reviewer (human or bot), use pr-review-loop; for a fresh-context-per-comment approach, use ralph-wiggum-loop.
meirdick/laravel-prod-ready/skills/laravel-prod-ready Skill
1★ repoRun a comprehensive production readiness audit on a Laravel application. Use this skill whenever someone wants to know if their Laravel app is ready to ship, launch, or go live — even if they phrase it as "security check", "pre-launch review", "is this production-ready?", "audit my project", "code review before deploy", "go-live checklist", "deploy checklist", "launch readiness", "is this safe to deploy", or similar. Also trigger when someone asks for help with security vulnerabilities, finding hardcoded secrets, checking their CI/CD setup, evaluating the reliability/scalability of their Laravel backend, or asks "what am I missing before launch". This skill systematically evaluates a Laravel project across 6 dimensions (Security, Scalability, Reliability, Hardening, Code Quality, Operational Readiness) and produces a scored report with actionable, Laravel-specific fixes — not just a list of problems, but a clear picture of what's production-grade and what needs work.
lirantal/skill-creator-extra/skills/skill-creator-extra Skill
1★ repoCreates high-quality agent skills by running the official Claude skill creator plugin and then applying a structured set of enhancement phases covering use-case design, frontmatter completeness, body structure, writing quality, and progressive disclosure architecture. Use this skill when the user wants to create a new skill, improve an existing SKILL.md, or asks "how do I write a good skill", "help me make a skill for X", "review my SKILL.md", or "turn this workflow into a skill". Trigger even if the user just says "let's make a skill" or describes a workflow they want to capture.
The same file is in 3 other repositories
jp-cruz/agent-skills/row-bot-docker-setup Skill
1★ repoAgent Skills
ChindanaiNaKub/neobrutalism-components-skill Skill
no license1★Highly directive, high-agency AI system prompt for generating Neobrutalist websites with adaptive tone control for business, hobby, cute, playful, serious, or default bold interfaces.
theseus-run/theseus/.agents/skills/agent-self-check Skill
1★ repoUse before finishing coding work or after deterministic check failures, including lint/typecheck/test loops, interpreting diagnostics as just-in-time prompts, and deciding whether repeated agent mistakes should become stricter rules.
Siddharth00/agent-revamp-skills/skills/01-audit/codebase-audit Skill
1★ repoProduces AUDIT.md committed to the repo root — a structured seven-section report covering dependencies, dead code, coupling, coverage, performance baselines, CVEs, and implicit contracts — the mandatory input for all Phase 2 strategy decisions.
jeremyknows/x-bookmark-triage Skill
1★Automatically triages X/Twitter bookmarks into structured knowledge cards and posts them to a Discord channel (#knowledge-intake or similar). Captures tweet content via fxtwitter, scores relevance using Claude Haiku, assigns tier (1–10), freshness (evergreen/dated/expired), and topic tags, then optionally unbookmarks after capture. Includes a scheduled poll for new bookmarks, a one-time backlog sweep, and a manual drop handler. Use when: (1) setting up automated bookmark → knowledge card pipeline, (2) draining an existing bookmark backlog, (3) dropping a URL manually for immediate triage, (4) packaging this as a publishable skill for other OpenClaw users. Requires X OAuth 2.0 User Context with bookmark.read scope (+ bookmark.write to unbookmark). Triggers on: "triage my bookmarks", "set up bookmark pipeline", "drain bookmark backlog", "x-bookmark-triage", "knowledge intake".
Gitmaxd/deepagents-cli-codex-skill/templates/skills/deepagents-cli Skill
1★ repoDeep Agents CLI — the LangGraph-based terminal coding agent. Use this skill whenever the user mentions deepagents, deep agents, the deep agents CLI, terminal coding agent, LangGraph agent, or asks about agent memory, agent skills, AGENTS.md, coding assistants in the terminal, or building scripted/CI agent workflows. Covers: interactive and non-interactive sessions, 20+ LLM providers, model configuration, skills, persistent memory, sandboxed execution, subagents, streaming, and the Agent Client Protocol.
The same file is in 3 other repositories
berserkdb/berserk-skills/skills/berserk Skill
1★ repoRun KQL queries against Berserk using the bzrk CLI. Use this skill whenever: (1) Executing KQL queries to search logs, traces, or metrics (2) Investigating issues by querying data around specific timestamps (3) Debugging problems by examining trace data (4) Exploring schema, field distributions, or service topology (5) Correlating logs and traces via traceId/spanId Make sure to use this skill whenever the user mentions querying observability data, searching logs, investigating traces, looking at metrics, debugging production issues, or exploring telemetry data — even if they don't explicitly mention "Berserk" or "bzrk". Triggers: "run bzrk", "query traces", "search logs", "investigate", "look at traces around", "what errors", "check metrics"
xyreinsurance119/agentforge-openclaw Skill
no license1★Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.
NecturaLabs/AgentSkills/skills/agent-context-loader Skill
1★ repoUse at the start of every conversation and after every agent handoff or context switch. Ensures global CLAUDE.md and project AGENTS.md are fully loaded and retained in context at all times.
Metaverse-Cloud/EngageLab-Skills/.agents/skills/skill-creator Skill
1★ repoCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The same file is in 66 other repositories
orthogonalhq/apm/cli/.skills/apm/init Skill
1★ repoAPM skill resolution. Defines how @skill references resolve to installed SKILL.md files.
lunrenyi/ai-agent.sh/.claude/skills/agent-browser Skill
1★ repoBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Phoenixrr2113/agent-harness/defaults/skills/ask-claude Skill
1★ repoDelegate bounded subtasks to the user's local `claude` CLI via bash. Runs on their Claude subscription instead of this harness's API budget.
jeremyknows/silent-failure-triage Skill
1★Use when a batch job silently produces wrong or missing results — "job exited success but records missing," "zero errors logged but output wrong," or tempted to patch the transform before localizing the failure stage. NOT for single-record bugs or UI issues.
marktco/agentic-de-atrophy/skills/design/api-design Skill
1★ repoA Socratic coach for API design that helps you reason through endpoints, resources, versioning, and error handling without designing the API for you.
trsdn/github-copilot-cli/.github/skills/copilot-cli-guide Skill
1★ repoQuick reference for GitHub Copilot CLI features, slash commands, keyboard shortcuts, modes, and advanced usage. Use when the user asks about CLI capabilities, commands, or how to use specific features.
aps08/fullstack-clean-architecture/.agents/skills/api_design Skill
1★ repoGuidelines for RESTful API design, endpoint naming conventions, and standardizing JSON responses.
magallon/refactoring-toolkit/refactoring-audit Skill
1★ repoPerforms a comprehensive 3-phase refactoring audit on any web project, analyzing structure, code quality, and security. Produces a consolidated diagnostic report with severity-rated findings. Use this skill when the user asks to audit a codebase for refactoring opportunities, evaluate technical debt, review code quality, find dead code, detect security issues in server-side logic, or assess overall project health. Triggers on phrases like "audit my code", "find technical debt", "code review the project", "what needs refactoring", "analyze code quality", "find dead code", "check for security issues", or any request to systematically evaluate a codebase before refactoring. This is a read-only diagnostic — it does not modify any files.
cutec-chris/PawLia/skills/automation Skill
no license1★ repoCreate and manage scheduled automations. Use when the user wants something to happen automatically on a schedule (e.g. 'send me a daily report at 16:00', 'check the weather every morning', 'warn me about thunderstorms every hour', 'tell me when my train is delayed').
arc-claw-bot/fulcra-context Skill
no license1★Access user-consented Fulcra context data including biometrics, sleep, activity, calendar, location, and the Fulcra metric catalog through the hosted MCP server or Fulcra CLI. Use for bounded read/context workflows only; use fulcra-annotations for writes.
Nick2bad4u/Github-Security-CodeScanning-Alerts-Skill/skills/github-manage-security-alerts Skill
1★ repoManage GitHub security alerts. Use when the user asks to inspect, triage, summarize, export, or safely update code scanning, Dependabot, malware, or secret scanning findings.
AtlasPA/openclaw-vault Skill
no license1★Credential lifecycle security for agent workspaces. Audit credential exposure, detect misconfigured permissions, inventory all secrets, and identify stale credentials needing rotation. Free alert layer — upgrade to openclaw-vault-pro for automated remediation, credential rotation, and access control.