Engineering
98,276 rows, by stacks then stars
nahuelsoria/prod-playwright-audit Skill
no license0★Audita flujos críticos de una app web ya desplegada (producción o preview) manejando un navegador real con Playwright, de forma SEGURA: nunca ejecuta acciones irreversibles/de dinero contra producción (abre confirmaciones y cancela, con un cinturón de seguridad a nivel de red que aborta los endpoints de mutación). Cubre, además, dimensiones read-only de auditoría: accesibilidad, responsive/mobile, performance y errores de consola, y flujos multi-usuario por rol. Genérico, multi-proyecto. Usar cuando el usuario pida "auditá/validá en producción con Playwright", "probá los flujos críticos en prod", "smoke test de prod", auditar accesibilidad/mobile/ performance de una URL real, o validar un fix recién desplegado.
TheophilusChinomona/idev/skills/api-contract-validation Skill
0★ repoVerifies frontend API calls match backend endpoints (URL paths, HTTP methods, request/response types). Use after creating or modifying API endpoints, service functions, or DTOs, or when asked to validate API alignment, check FE-BE contracts, or generate API contract docs.
Alexisgt01/skill-architect/skills/skill-architect Skill
0★ repoArchitecte de bibliothèques de skills pour agents IA. Utiliser AVANT toute rédaction dès que l'utilisateur veut créer un ou plusieurs skills, transformer une expertise métier ou des prompts en skills, structurer un "socle commun" avec des déclinaisons (ex. marketing global + cold call + cold email), ou qu'il ne sait pas s'il faut un seul skill ou plusieurs. Utiliser AUSSI pour faire évoluer une bibliothèque existante - ajouter un skill à un plugin ou namespace existant (ex. /company:*), modifier, fusionner ou redécouper des skills en place, diagnostiquer un skill qui ne se déclenche jamais, ou préparer une bibliothèque à accueillir de futurs domaines. Déclencher dès qu'un domaine large (vente, support, contenu, juridique, RH...) doit devenir des skills, même sans le mot "architecture". Ne pas utiliser si l'architecture est déjà claire et qu'il ne reste qu'à rédiger un skill unique bien défini - utiliser directement skill-creator.
Deocracy/github-boards-skill/skills/github-boards Skill
0★ repoManage a GitHub Projects v2 Kanban board in natural language. Use when the user wants to put tasks or issues on a board, see what they (the human) need to work on versus what the AI is working on, move cards between lanes, route work as agent-actionable or human-actionable, reject with learnings, summarize what changed on the board, promote mapped backlog onto the board, sync TODOs or other skills' plans onto the board, check or heal ledger drift, browse board history, or undo recent board changes. Also use when ANOTHER skill needs to record tasks onto the board after research or planning. Reads and edits the board via the gh CLI and GitHub GraphQL, always previewing changes before writing and reporting back. Trigger phrases: put this on the board, add to kanban, what's on my plate, what is Claude working on, move card, update the board, show board status, reject with learnings, promote the backlog, sync my TODOs onto the board, heal the ledger, what changed this week, what did the board look like before, undo what happened since.
polrai-bg/polr-ai-skills/plugins/agentic-os/skills/add-new-agent Skill
0★ repoInterview the principal one question at a time to build a new specialist agent: produces a complete AGENT.md, updates the roster, and wires the Chief of Staff routing table. Triggers on "add an agent", "hire a [role]", "create a new agent for X", or when the Chief of Staff finds a request shape no existing agent covers.
mike623/agent-skills/skills/boardgame-rag-bot Skill
no license0★ repoCreate public-safe board-game rules agents from a BGG link plus user-provided rulebooks, using private semantic RAG, lexical fallback, and page citations.
superchaospc/xray-relay-deploy Skill
0★Install and remotely operate the user's xray-relay one-click VLESS+REALITY relay script (superchaospc/xray-relay, xray_deploy.sh) on a VPS over SSH. Use whenever the user wants to deploy, set up, or manage a VLESS/REALITY relay or 中转节点 on a VPS; add/delete/rename relay nodes (residential SOCKS5 or VPS direct, single or batch); view relay status, traffic stats, or run diagnostics; change a node's port; update or restart Xray; configure monitoring/email alerts; or uninstall. Trigger on phrases like "在 <vps> 上装一下中转脚本", "给 japan 加几个直连节点", "看下 vps1 的流量", "部署 xray 中转", "批量加住宅节点", even when the script name isn't mentioned. This skill drives the script's interactive menu non-interactively via SSH; it does NOT reimplement the relay logic.
zakarya526/fable-skill/skills/fable-skill Skill
no license0★ repoSurvey any codebase as a senior advisor (powered by Fable 5) and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
marcelolebre/anti-slopper Skill
0★Write like a human and avoid AI slop. Use this skill whenever you are producing prose for a person to read: PR descriptions, commit messages, docs, READMEs, comments, design notes, Slack/email replies, blog posts, tweets and X/LinkedIn posts, launch announcements, release notes, or any explanatory text. It gives proactive rules for drafting natural writing the first time, plus a fast self-audit to catch AI tells (inflated significance, promotional tone, -ing padding, rule of three, em dashes, copula avoidance, hedging, signposting, generic conclusions, buried ledes and engagement bait in social posts, and negate-then-correct lines like "this isn't X, it's Y") before you ship. Includes a banned-phrase list. Based on Wikipedia's "Signs of AI writing".
breakthrough-edu/meeting-scribe/meeting-scribe Skill
no license0★ repoTurn meeting audio into three artifacts (a corrected transcript, an HTML visual canvas, and a Markdown summary with AI insights), transcribing locally and cross-platform with Whisper (no cloud, no external transcription app). Runs on Apple Silicon mac via whisperkit-cli, on Intel mac / Windows / Linux via faster-whisper, or via whisper.cpp. MUST trigger when the user mentions a meeting transcript or recording, the audio drop-zone folder, processing / correcting / cleaning / fixing a transcript, transcribing an audio file, Whisper output, or generating meeting notes from a recording. Also trigger on Chinese phrasings: 处理 transcript, 整理会议纪要, 修正 transcript, 清理 transcript, 修订 transcript, 转录纠错, 会议转写, 帮我做个会议总结, 把会议 transcript 处理一下, 处理一下昨天会议, 整理今天会议, 会议纪要, 转写文本, 把录音转成文字, 处理这个录音, 处理这个音频. Also trigger when the user drops an audio file (.wav / .mp3 / .m4a / .flac / .ogg ...) or a .txt transcript into the configured drop-zone folder. Behavior is driven entirely by a per-user config at ~/.config/meeting-transcripts/config.json (engine, model, paths, output destination, language); the skill runs a one-time first-run setup if that config is absent. Walks six gated phases: transcription, silent bootstrap and file read, classification and context request, context loading, generate all three artifacts straight to the configured destination with no full-text chat echo, and an in-place review and edit loop. Preserves speech features and code-switching in the transcript; canvas and summary follow the configured output language. ALSO trigger for cross-meeting Insights mode, when the user asks to analyze their communication patterns ACROSS meetings rather than process one recording: meeting insights, communication patterns, analyze my meetings, how do I come across in meetings, do I avoid conflict, 分析我的沟通模式, 我开会的表现怎样, 复盘我最近的会议, 跨会议分析, compare my meetings between two periods. Insights mode reads the existing corrected transcripts and writes ONE pattern-analysis report; it skips transcription and the three-artifact pipeline entirely.
cdm227/AgriValue-Tracker/.agents/skills/agrivalue-iq-operator Skill
0★ repoOperates AgriValue Tracker as an interactive AI agent workflow. Use when testing the challenge demo, running value-chain optimization, asking the AI Harvest Advisor, generating Fair-Trade contracts, preparing Copilot MCP prompts, or validating Fabric IQ, Foundry IQ, and Work IQ flows.
Madwr1d/ithildin-agent Skill
no license0★Use to drive Ithildin (a Swiss operations portal) from the terminal — manage sales leads, run a cold-call queue and log outcomes, fill a task planner, and read finance summaries. Use whenever the user wants an agent to operate their Ithildin workspace (add leads, work the dialer, schedule tasks, check net worth) instead of clicking the web UI.
scchearn/loam/skills/loam-ground/loam-initializing-vault Skill
0★ repoScaffold a new Obsidian vault with pre-configured settings, keymaps, and core plugins. Use when the user wants to "set up a new Obsidian vault", "create an Obsidian vault", or "replicate my Obsidian setup".
Madwr1d/safe-multi-session-deploy Skill
0★Use BEFORE committing or deploying any repo that multiple Claude/agent sessions may share (Vercel/Railway/Node web apps). Prevents the three failure modes of concurrent sessions on one working tree — clobbering another session's unsaved work, deploying to the WRONG linked project, and not knowing which session's build is actually live. Stamps a session-tagged build provenance marker and verifies it post-deploy.
alexbanda08/solana-auditor-skill/skill Skill
0★ repoSolana/Anchor program security audit workflow - scope the attack surface, run static analysis (cargo-audit/clippy/deny/geiger), manual vuln review (signer/owner/PDA-bump/PDA-sharing/CPI/overflow/type-confusion/close-revival), dynamic analysis (litesvm PoC, fuzzing), and severity-graded reporting; use when asked to audit, security-review, find vulnerabilities in, or write a findings report for a Solana program.
nichtlegacy/kometa-skill/skills/kometa-config-core Skill
0★ repoUse whenever the user needs `config.yml` created, repaired, or explained, including connectors, library mappings, file blocks, root settings, file schedules, library schedules, overlay scheduling, operations, and root playlist wiring. Use this skill aggressively for any Kometa request that mentions `config.yml` or top-level service setup.
Madwr1d/xxtrade-agent Skill
no license0★Use to read xXTrade (Hyperliquid perps) market and account data from the terminal — top markets by open interest, a coin's mark price, and the open positions / account value for a wallet address. READ-ONLY (no trading). Use when an agent needs live perp prices, funding, OI, or to check a wallet's positions on xXTrade.
g-shevchenko/agentic-quality-skills/skills/agentic-quality-gates Skill
0★ repoUse before non-trivial agentic, coding, workflow, tool, automation, release, or public-surface work, and when the user says quality gate, acceptance gate, red flags, risk gate, architecture gate, decision handoff, side-effecting workflow, contracts first prompts last, prompt-only fix, human gate, or release gate. Classifies risk, defines deterministic acceptance gates, catches red flags, and decides whether to proceed autonomously or ask a human.
glassflow/agent-skills/skills/create-pipeline Skill
0★ repoUse when the user asks to create a GlassFlow ETL pipeline. Walks through source configuration (Kafka or OTLP), optional dedup/filter/transform stages, and ClickHouse sink mapping, then submits the v3 config to the GlassFlow API. Triggers on phrases like "create a pipeline", "set up a Kafka to ClickHouse pipeline", "ingest logs from OTLP into ClickHouse".
knowledgeco/seamkeeper Skill
0★Maintain continuity of design intent across coding sessions and across different AI models or thinking budgets, so a codebase reads as one authored work — "Software Program V1.45" — rather than a stitched-together anthology of fragments by different hands. While authoring, it prevents new "seams"; while auditing, it honestly patches existing ones. Use this whenever writing, editing, refactoring, or auditing code that will be touched across more than one session — ESPECIALLY when the model, thinking budget, or author may change between sessions (a reset, a model swap, a budget-limited run, a "free model today" detour). Seams include: idiom drift, defensive scar tissue at boundaries, the same problem solved two ways, and — most dangerously — latent fault-lines where an implicit contract (e.g. "this input is already validated") died with the reasoning that produced it, compiles fine, passes the happy path, and breaks on the edge nobody had budget to consider. Trigger this when picking up code from a previous session or another model, when auditing or refactoring an unfamiliar codebase, or any time you want the repository itself to carry the "why" so future readers (human or AI) can recover intent instead of guessing — even if the user never says the words "continuity," "seams," or "ledger."
jovd83/skill-vetting-reporter Skill
0★Security & trust vetting for an AgentSkill (folder, SKILL.md, zip, or single script) before it is installed or approved. Runs a mandatory open-source scanner gate (Cisco skill-scanner, NVIDIA SkillSpector, Snyk Agent Scan, sentry/skill-scanner), then static heuristics, and produces a draft review report — file inventory, executable surface, findings by severity, an OWASP Agentic Skills Top 10 (AST01-AST10) coverage map, a red-flag checklist, a suggested review tier (0-3), and reviewer sign-off blocks. Use this whenever someone asks "is this skill safe", "vet/review/scan this skill or SKILL.md or script", "run the vetting on skill X", "should I install this skill", or when a skill must pass the AgentSkills review flow. Also use it to re-vet an updated skill and diff the reports. It assists review and never approves anything on its own.
ucsandman/claude-code-capability-primer/skills/claude-code-agent-sdk Skill
0★ repoUse when building custom AI agents headlessly, embedding Claude Code tools in an app, or running scripted/cron agents—need SDK package names, setup, core API entry points, supported languages, and relation to Claude Code CLI and Messages...
duckysmacky/guitar-setup-skill/skills/guitar-setup Skill
no license0★ repoGuitar and amplifier setup assistant. Activate this skill when the user asks how to set up their guitar or amp to play a specific song or wants to dial in a tone for a particular artist, song, or genre. Triggers on phrases like "how do I set up for [song]", "what are the settings for [artist]", "dial in [song] tone", "I want to play [song] on guitar", "set up my amp for [song]", "guitar settings for [artist/song]", or any request to configure guitar/amp equipment to match a specific sound. Also triggers when the user says the tone "doesn't sound right" or "doesn't sound like the original" and wants help tuning their settings. Always use this skill when a song, artist, or tone target is mentioned alongside guitar or amp setup - even if the phrasing is casual.
calebikhuohon/popperian-reasoning/skills/popperian-reasoning Skill
0★ repoUse Popperian critical rationalism to improve reasoning by falsification, risky tests, competing conjectures, and error elimination. Invoke implicitly in any agent harness when a task involves uncertainty, hypotheses, tradeoffs, claims, explanations, debugging, diagnosis, research evaluation, plan review, design choice, or improving an LLM answer by asking what would break it before asking what supports it. The user does not need to name this skill if the harness supports contextual skill selection.
claudette-agent/agent-handoff-kit Skill
no license0★Lightweight handoff workflow for AI coding/research agents. Captures objective, state, constraints, next action, verification, and risks.
jamieafk/fable-check/skill Skill
0★ repoRun an extensive code review or get advisory input from Claude Fable 5 (Anthropic's most capable model). Use when the user asks for a code review, a fable check, a second opinion on changes, a pre-ship review, an adversarial/deep review of the working tree or a branch — or wants Fable's advice on an architecture choice, design tradeoff, plan, or technical decision about the codebase. Read-only — it never modifies code.
222-glitch/ship-check/ship-check Skill
no license0★ repoAudit a Python script or small project for production-readiness. Use when the user asks "is this ready to ship?", wants a pre-release review, or wants to know what to fix before sharing/selling/deploying their code. Produces a scored report with prioritized fixes.
whyy9527/software-advertising-defense Skill
0★Guard against vendor marketing and SEO drift when choosing software, SaaS, APIs, search providers, frameworks, MCP servers, or developer tools. Use when the user asks what software/tool/API to use, asks to search for options, or a task involves adding external services, fallback providers, paid APIs, or "production-grade" tooling. Prevents adding requirements the user did not ask for after reading vendor pages.
WellDunDun/skills/skills/design-agent-prompt-loop Skill
0★ repoDesigns autonomous prompting loops that let coding agents drive their own next steps, handoffs, reviews, and verification prompts. Use when setting up agent workflows, reducing repeated user prompting, creating self-driving project instructions, designing prompt queues, or coordinating build, review, and handoff loops across agents.
citedy/waitspin/skills/waitspin Skill
0★ repoUse this skill for WaitSpin, the sponsored wait-state ads CLI and API. Trigger when a user wants to create or manage WaitSpin campaigns, buy prepaid impression blocks, inspect the public market, onboard with email OTP keys, install or check earning surfaces for VS Code, Cursor, Devin Desktop, Claude Code, Antigravity CLI, GitHub Copilot CLI, MiMo Code, OpenCode, Grok Code CLI, or Qoder CLI, inspect wallet/ledger/payout status, or reason about WaitSpin public API, trust boundary, privacy, and shipped vs not-shipped capabilities.
MuNeNiCK/agent-workbench/skills/agent-workbench Skill
0★ repoUse when a coding agent needs durable work, design, review, evidence, interruption, recovery, and completion state through the native Agent Workbench CLI.
Nu424/agentic-video-analysis-skill/skills/agentic-video-analysis-skill Skill
no license0★ repo動画をフレームタイル化し、aitool recognize-imageで反復的に解析するためのスキル。 動画解析、見どころ抽出、ハイライト候補探索、ゲーム実況分析、エージェンティックな動画理解を行うときに使用する。
codecraftersautomation/claude-code/plugins/ccp/skills/compact-handoff Skill
no license0★ repoEmergency, fast handoff when the current Claude account is almost out of usage/tokens and there's no time for a full handoff. Use this when the user says they're "about to hit the limit", "running out", "almost out of usage", "quick handoff", "emergency handoff", or needs to switch to the other profile (claude-team <-> claude-max) immediately. Writes a short .claude/ccp/handoff/COMPACT_HANDOFF.md (~1000-1500 words) with objective, state, next 3 steps, risks, and an exact takeover prompt.
TonkaToyXL/cursor-agent-skills/diagnose Skill
0★ repoDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
The same file is in 21 other repositories
mikulgohil/claude-skills/skills/ai-agents/context-engineering Skill
0★ repoUnderstand and optimize how context is structured in agent systems — the components, mechanics, and constraints of an agent's context window. Use when writing or tuning commands, skills, and sub-agent prompts.
264Gaurav/DeepAgents/deepagents/skills/aws Skill
0★ repoAWS cloud expertise. Use when the user asks about AWS services (EC2, S3, Lambda, IAM, DynamoDB, RDS, ECS, EKS, CloudWatch, Bedrock, SageMaker), architecture design on AWS, boto3 / AWS CLI usage, cost optimization, or cloud security best practices. Provides decision frameworks, CLI/boto3 workflows, and worked examples.
deeparchi-ai/deepsight/skills/productivity/session-bootstrap Skill
0★ repoSession 启动协议 — 基于 Anthropic Harness 模式,在每个新 session 开始时自动恢复上下文、读取任务清单、报告当前状态和建议下一步。解决跨 session 状态丢失问题。
taige221/session-handoff-skill/skills/session-handoff Skill
0★ repoUse this skill when the user explicitly wants to summarize, wrap up, or hand off the current AI coding session into a concise Markdown document for a future session. Trigger phrases include: "session handoff", "handoff doc", "generate a handoff document", "summarize this session for the next session", "distill this session into a handoff md". Output to chat by default. Do not create persistent memory, auto-load context, sync sessions, or write files unless explicitly asked.
tommylower/nightcap Skill
0★Nightcap, a nightly agent journal. Reads recent Claude Code and Codex transcripts off disk, skips trivial sessions, and writes one first-person narrative journal entry per real session, like a handwritten end-of-day journal. Use when the user wants an agent session journal, a daily log of AI sessions, transcript summaries, "what did i work on today/this week", to set up or troubleshoot nightcap, or to customize its voice. Triggers: nightcap, journal, session journal, agent journal, daily log, summarize my sessions, what did i do today.
The same file is in 1 other repository
sebastian-software/skills.sebastian-software.com/skills/codebase-improvement Skill
0★ repoAudit, diagnose, plan, and improve software codebases through repository reconnaissance, evidence-backed findings, competing-hypothesis investigation, leverage-based prioritization, executable plans, backlog reconciliation, and proportionate simplification. Use when asked why a defect or surprising behavior occurs, for a read-only root-cause report, to audit a repository, decide what to improve next, simplify code, create or review an implementation plan, reconcile stale work, or implement selected improvements. Do not use for PR-only review, dependency-update-only work, focused test, test-runner, or test-framework diagnosis, architecture-only decisions, or frontend-only diagnosis when a narrower skill applies.
cskwork/clean-code-skill Skill
0★Refactor any codebase using Fowler's catalog (refactoring.guru) — detect the smell, pick the technique, apply in safe behavior-preserving steps. Use when asked to refactor, clean up, simplify, improve readability/maintainability, or reduce code smells.
satishTheLegend/production-readiness-gate Skill
0★Runs one phased go/no-go Production Readiness Review (PRR) gate against a feature or service right before it ships. Scopes the change and blast radius, picks a gate profile (internal tool / public service / paid-or-LLM-backed), then walks five dimension checklists — reliability, security, operability, cost, observability — tuned to the actual detected stack. Runs deterministic static probes over the repo and IaC (committed secrets, exposed/unauthed endpoints, missing healthchecks, irreversible migrations, unbounded-cost paths, missing rollback) so findings are grounded in code, not optimism. Scores each check pass / fail / N-A / risk-accepted, splits launch-blocking from advisory by profile, and emits a dated PRR record with a GO / NO-GO / GO-WITH-RISKS verdict, an owned remediation list, and a risk-acceptance log the next launch diffs. Use whenever the user is about to ship, deploy, launch, release, "go live", cut a release, flip a feature flag to prod, or merge a change touching users, data, money, or an external surface — even if they don't explicitly ask, or they say "ready to ship?", "production-ready?", or "what am I forgetting before prod". This is the launch gate; load sibling skills (sre-slo, well-architected, threat-model-studio, finops) for depth when a gate fails.
dvnc-labs/agent-config-audit Skill
0★Audit Claude Code, Codex, Cursor, MCP, and agent setup files before installing or running a repo. Use for AGENTS.md, CLAUDE.md, .mcp.json, .claude settings, Cursor rules, hooks, tool permissions, and env examples. Not for general app vulnerability testing or broad code security review.
MrBridgeHQ/apify-scraper-builder-claude/skills/apify-scraper-builder Skill
0★ repoUse when building, modifying, or debugging the code and architecture of a scraper Actor on Apify - configuring a no-code Apify scraper, building an AI-extraction Actor, or starting from a Crawlee template (Cheerio / Playwright / Camoufox). Triggers on "build a scraper on Apify", "scrape X with an Actor", "apify create --template ts-crawlee-*", "apify/web-scraper", "apify/cheerio-scraper", "apify/puppeteer-scraper", "apify/playwright-scraper", "apify/ai-web-scraper", Crawlee CheerioCrawler / PlaywrightCrawler / AdaptivePlaywrightCrawler, RequestQueue, RequestList, autoscaledPool, sessionPool, pagination, defensive selectors, KV Store caching for scraped data, scraper Dockerfile, scraper input_schema. Use this skill when the question is about scraper Actor CODE & architecture - anti-bot doctrine and tool ladder, README/schema authoring, and PPE pricing are adjacent concerns this skill cross-references but does not own.
meharajM/context-machine/packages/team-project-memory-skill/skills/team-memory-capture Skill
0★ repoCapture a short reusable project learning after a non-obvious fix, failed approach, setup requirement, decision, or debugging path is verified and likely to save another agent time or tokens.
Melmonster13/antigravity-skills-project/.agents/skills/database-schema-validator Skill
no license0★ repoValidates SQL schema files for compliance with internal safety and naming policies.
PabloViniegra/setup-graphify/skills/setup-graphify Skill
no license0★ repoTrigger: set up graphify, add graphify, configure graphify, integrate graphify. Installs graphifyy, injects a marker-delimited Graphify section into every agent-instruction file present in the project (AGENTS.md always; CLAUDE.md, .github/copilot-instructions.md, GEMINI.md, Cursor rules, and others only if they already exist), adds graphify-out/ to all ignore files, installs post-commit + post-checkout git hooks, and runs the initial knowledge graph build. No hidden hook directories are created. Requires Python 3.12+.
Blackie360/webmcp-skill/webmcp-skill Skill
0★ repoImplements WebMCP (Web Model Context Protocol) on websites using document.modelContext.registerTool. Covers tool design, JSON Schema inputs, security annotations, origin isolation, and Chrome testing. Use when adding WebMCP tools to web apps, exposing page features to browser agents, or when the user mentions WebMCP, modelContext, or agent-ready web tools. Not for server-side MCP servers.
satishTheLegend/docs-product-orchestrator Skill
0★Runs a documentation site like a PRODUCT, not a pile of READMEs: detects the repo's stack and inventories doc gaps, defines reader personas and jobs, designs a Diataxis-correct information architecture (tutorials/how-to/reference/explanation without quadrant-mixing), scaffolds a real docs-as-code toolchain (MkDocs/Docusaurus/Starlight), auto-generates API reference FROM source so it never rots, tests every code sample and link as a hard gate, and installs a CI doc-drift gate that fails when public API/CLI/config changes are undocumented. It sequences these phases in dependency order with a deterministic, script-enforced gate between each, tracked in a ledger file, and delegates toolchain internals to specialist tools rather than reimplementing them. Use whenever the user wants to set up, build, restructure, fix, or maintain a documentation site or developer docs - even if they only say "our docs are a mess / out of date", "set up docs for this repo", "apply Diataxis", "generate API reference from our code / OpenAPI", "stand up MkDocs/Docusaurus/Starlight", or "make docs that don't go stale / catch docs drift in CI" - even if they don't explicitly ask for an orchestrator. Trigger on README sprawl, stale API docs, or a missing docs pipeline.
ditsmod/agent-skills/skills/ditsmod-core-architecture Skill
0★ repoCore concepts of Ditsmod architecture: Modules, Dependency Injection, Metadata Reflector, and Application Lifecycle & Graceful Shutdown. Guidance on module composition, DI hierarchies, providers, scopes, and custom decorator design.
mindcruiser/notta-mcp-skill Skill
no license0★Use Notta MCP to transcribe local audio/video files, check transcription status, retrieve transcript results, search Notta records, and list Notta records or folders through Claude Desktop, Smithery, Codex, or other MCP-capable agent environments.
knowingrohan/ai/skills/context-handoff Skill
0★ repoBefore ending a session or switching agents, produce a structured hand-off note — what was done, what is pending, key decisions made, files changed, and a ready-to-paste resume prompt for the next session or agent. Use when the user says they are wrapping up, switching tools, handing off to a teammate, or starting a new session on the same project.
shanemhamilton/nightshift Skill
0★Audits and hardens recurring automations so they behave like reliable operators instead of stateless prompts — and composes coherent new automation suites per project from an adaptive pattern library — across Codex, Claude Code, Gemini CLI, and Cursor. Adds persistent memory, run ledgers, concurrency locks, tool preflight, change-detection, failure taxonomy, stop rules, a continuation loop that completes multiple bounded work-units per run, multi-agent execution, approval queues, and verified safe-merge closeout; wires new jobs into a coordinated fleet with one merge authority. Use when the user wants to create, review, standardize, optimize, or harden scheduled or recurring jobs — Codex automations (~/.codex/automations/*/automation.toml), Claude scheduled-tasks (~/.claude/scheduled-tasks/*/SKILL.md), Gemini cron jobs, Cursor cloud automations, nightly maintenance loops, repo-hygiene/QA/coverage/security/simplification jobs, integration-rescue jobs, or reminder/monitor prompts — or to propose what automations a project should have, see what's already installed across agents, or set them up to work together. Also triggers on requests to stop an automation duplicating work, make a job idempotent, give an automation memory, add a human-approval gate, or build a nightly automation suite.
satishTheLegend/authz-architect Skill
0★Designs, enforces, and adversarially PROVES an app's authorization and tenant-isolation model — closing IDOR, broken-access-control, privilege-escalation, and cross-tenant data-leak gaps that are OWASP A01, the #1 web vuln. Runs one phase-gated loop, map resources/actors/tenancy, choose RBAC/ABAC/ReBAC, write a policy-as-data matrix (role x resource x action + ownership/tenant predicates) as the single source of truth, refactor every endpoint and query to be object-ownership-checked AND tenant-scoped, BLOCK on a coverage gate, red-team for IDOR / privilege escalation / cross-tenant reads / mass-assignment, then ship a regression suite + attestation. Use whenever the user builds or touches a multi-user / multi-tenant / SaaS app, adds endpoints or CRUD, or mentions authorization, access control, permissions, roles, RBAC/ABAC/ReBAC, row-level security, tenant isolation, "can user A see user B's data", IDOR, broken access control, privilege escalation, or auditing endpoints for missing checks — even if they only say "wire in auth", "add login", "make this multi-tenant", or "review my API". Prefer this over generic auth setup when data belongs to specific users or tenants. Do NOT accept route-level role checks when object-level ownership is required; do NOT attest until probes pass.
satishTheLegend/upgrade-pilot Skill
0★Drives high-risk major-version and framework upgrades across a codebase or monorepo as a dependency-ordered, codemod-first campaign with a per-step green-build gate and a resumable ledger, so the branch is never red for a week and an interrupted upgrade resumes where it stopped. It detects the package manager and monorepo tool, builds the dependency graph, finds the target(s) and every affected package, surfaces peer-dependency conflicts before any change, topologically sequences the bumps (leaves before roots), isolates the work in a worktree, applies official codemods first then hand-fixes, and refuses to advance until install + typecheck + build + tests pass. It records every step DONE or BLOCKED in a ledger and emits a final report of what moved, what is deferred, and remaining risk. Use whenever the user wants to upgrade React, Angular, Vue, Node, Python, Spring, Rails, or Django to a new major; mentions a major version bump, breaking dependency upgrade, framework migration, dependency rot, a forced security upgrade, a codemod, a peer-dependency conflict, or a monorepo upgrade; or says the upgrade branch has been red for days — even if they only paste a single package.json bump or a failing install and do not explicitly ask for sequencing, gating, or a resumable campaign.
Azzaraell/agent-payments-x402/skill Skill
0★ repoThe money layer for AI agents on Solana. Lets an agent PAY for APIs/data/compute and other agents (x402 micropayments in USDC), GET PAID by monetizing its own APIs/MCP tools behind HTTP 402, and SPEND SAFELY behind non-custodial wallets with hard, enforced limits — never a raw god-mode private key. Covers x402 v2 (client + server + facilitator), Squads v4 spending limits, Privy/Turnkey/Coinbase-CDP/Crossmint agent wallets, AP2 mandates, and USDC settlement. Use when building agents that transact, paywalling an API/MCP for agent consumers, or hardening an agent's spending controls.
0xgetz/xi-agent-skills/mcp-skills/airtable-mcp Skill
no license0★ repoUse the Airtable MCP integration to read and write Airtable bases and tables. Activate when the user wants to read and write Airtable bases and tables via Airtable, including discovering the right tool, building parameters, and handling results.
MrBridgeHQ/scraping-expert-claude/skills/scraping-expert Skill
0★ repoSenior-level guidance for designing, building, and debugging web scrapers on any platform - standalone scripts, cron jobs, serverless, web-app backends, or Apify Actors. Use this skill whenever the user wants to build, modify, or debug a scraper; whenever they mention web data extraction, anti-bot bypass (Cloudflare, DataDome, PerimeterX, Akamai, AWS WAF, rate limiting), proxy strategy, browser/TLS fingerprinting, Crawlee, Playwright, Puppeteer, Camoufox, got-scraping, or scraping a specific site. Trigger even when the user only describes a scraping problem - the right architectural choice almost always differs from their first instinct (nine times out of ten, an internal JSON API exists and they're about to scrape HTML for nothing). Also use it for choosing between scraping tools, debugging 403/429 errors, managed scraping APIs (Firecrawl, ZenRows, ScrapFly, ScraperAPI, Bright Data), proxy configuration, caching strategy, or selector breakage. Apply as soon as a target URL or site name appears in a scraping context.
balacodeio/balakit/skills/authoring-skills-and-rules Skill
0★ repoAuthor Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation model, cross-platform mirroring, and the universal craft: progressive disclosure, trigger-rich descriptions (context pointers), leading words, token budget, naming, and what to leave out. Use when the user asks to write, scaffold, refactor, port, or review a Skill, Cursor rule (.mdc), AGENTS.md, copilot-instructions, or prompt file — or to make one Skill/rule work across multiple agents.
AIops-tools/K8s-AIops/skills/k8s-aiops Skill
0★ repoUse this skill whenever the user needs to operate a Kubernetes cluster — list/inspect pods, deployments, statefulsets, daemonsets, replicasets, jobs, cronjobs, services, ingresses, endpoints, configmaps, secrets (names/keys only), PVCs/PVs/storageclasses, nodes, namespaces, and events; read pod logs; describe pods/nodes; pod/node top (metrics); read-only diagnostics / RCA (pod-health, workload-readiness); scale deployments/statefulsets; rollout status/history/undo/pause/resume and set image; delete pods/deployments/jobs; create/delete namespaces; and cordon/uncordon/drain nodes. Works with any kubeconfig-reachable cluster (standard Kubernetes, k3s, EKS, GKE, AKS). Always use this skill for "list k8s pods", "scale deployment", "kubernetes pod logs", "describe pod", "why is my pod crashing", "diagnose pods", "which deployments are unhealthy", "rollout undo", "set image", "top pods", "drain node", "cordon node", "restart deployment", "k3s", or "kubectl"-style tasks when the context is explicitly Kubernetes / a cluster. Do NOT use when the target is not a Kubernetes cluster (hypervisor VM lifecycle, backup products, or cloud-provider consoles are out of scope). Common Kubernetes operations with a built-in governance harness (audit, token budget, undo, risk-tier labels).