agentsclimarketplace

The catalog

611,178 rows, by stacks then stars

  • Pocketbase best practices

    greendesertsnow/pocketbase-skills/skills/pocketbase-best-practices Skill

    14★ repo

    Pocketbase Skills for Claude Code

    The same file is in 3 other repositories

  • Storyboard lite

    towardsyoung/video-agent-skills/skills/storyboard-lite Skill

    no license14★ repo
  • Fp option either

    whatiskadudoing/fp-ts-skills/skills/fp-option-either Skill

    no license14★ repo

    Practical fp-ts skills for AI agents. No jargon, just patterns that work. Install with: npx skills add whatiskadudoing/fp-ts-skills

  • Google ads ad extension audit

    eliasmalmsandberg/google-ads-skills/skills/google-ads-ad-extension-audit Skill

    14★ repo
  • Renef

    vichhka-git/renef-skills/skills/renef Skill

    14★ repo

    Agent Skill for operating renef.io — Android ARM64 dynamic instrumentation: hook native/Java, patch memory, trace syscalls, bypass SSL pinning/root detection; port Frida & GameGuardian scripts to renef Lua.

  • Playwright cli

    gandazgul/dotopencode/skills/playwright-cli Skill

    14★ repo

    My opencode configuration, agents, skills, commands, etc

  • Video editing

    adriiita/vertical-video-editing-skill/skills/video-editing Skill

    14★ repo

    Claude skill: turn a script + talking-head media into a polished, creator-grade vertical 9:16 short with HyperFrames — editorial look, A-roll/B-roll cutting, eased camera moves, themed motion graphics, SFX, and a render verification gate.

    The same file is in 1 other repository

  • Server side swift

    melissa-pereira-deel/claude-code-server-side-swift-skills/skills/server-side-swift Skill

    13★ repo

    Server-side Swift development with Vapor and Hummingbird. Covers project setup, routing, Fluent ORM, authentication, deployment, and shared client-server code. Use when building backends or APIs in Swift.

    The same file is in 1 other repository

  • Agent manager

    d3x293/code-crew/skills/agent-manager Skill

    13★ repo

    Creates, lists, and removes custom project-specific agents. Custom agents are stored in .claude/crew-agents/ and registered in crew-team.json for routing.

  • Feature radar archive

    runkids/feature-radar/skills/feature-radar-archive Skill

    13★ repo

    Archive a completed, rejected, or covered feature into .feature-radar/archive/ with mandatory learning extraction. MUST use this skill whenever a feature reaches a terminal state — done, rejected, covered, deferred, or N/A. Even casual mentions like "we shipped X" or "X is done" should trigger this. The skill extracts learnings, derives new opportunities, and updates refs. Use when the user: - Says "we shipped X", "X is done", "X is complete", "we just finished X" - Rejects a feature: "we decided not to build X", "reject this", "doesn't fit" - Defers: "defer X", "postpone this", "revisit later", "not now" - Closes an opportunity: "close this opportunity", "mark as done", "archive this" - Mentions any feature reaching Done/Covered/Rejected/Deferred status Do NOT use for discovering new features — that's feature-radar-scan's job.

  • Advanced alchemy

    litestar-org/litestar-skills/plugins/litestar/skills/advanced-alchemy Skill

    13★ repo

    Auto-activate for advanced_alchemy imports, alembic/, SQLAlchemyAsyncRepositoryService, SQLAlchemyAsyncConfig, repository_type, service_class, filters, or storage. Not for raw SQLAlchemy without Advanced Alchemy — use SQLAlchemy guidance.

  • Archive

    serbanghita/claude-code-plan-critique/skills/archive Skill

    13★ repo

    Archive a completed or abandoned plan for future reference

  • Experts

    2389-research/review-squad/skills/experts Skill

    13★ repo

    Use when a project needs multi-perspective review — pre-launch audit, post-refactor check, inherited codebase assessment, or periodic health check. Dispatches parallel expert reviewer agents with persona framing.

  • Semantic compressor

    claude-world/skills-optimizer/.claude/skills/semantic-compressor Skill

    13★ repo

    Safely reduce Claude Code skill and agent Markdown while preserving behavior, frontmatter, commands, tools, triggers, security rules, errors, paths, and numerical constraints. Use only when the user explicitly invokes /semantic-compressor to scan, draft, verify, apply, benchmark, or restore a compression run.

  • Human copywrite

    forint573/human-copywrite/human-copywrite Skill

    13★ repo

    Write, finalize, or clean up reader-facing marketing and long-form copy (landing pages, sales pages, e-books, reports, case studies, product and email copy, founder notes) so it reads like a specific human wrote it and says something worth reading. Use when asked to humanize, de-slop, make less AI-sounding, rewrite naturally, tighten, polish, sharpen, clean up, or finalize copy, when asked to write the website, homepage, or landing-page copy for something built or discussed in the session, and proactively when finalizing a copy deliverable. Supports per-project voice: on 'set up my voice' or a setup argument it interviews the user and writes MY_OWN_VOICE.md, then matches it. Writes from product facts and never outputs chat history as copy, keeps the user's facts and voice, never invents proof or makes a claim more certain than the source supports. Not for code, data, changelogs, release notes, legal terms, technical reference docs, or casual chat.

  • Ieee acm paper writing

    huguryildiz/ieee-acm-paper-writing/skills/ieee-acm-paper-writing Skill

    13★ repo

    Draft, rewrite, compress, structure, calibrate, humanize, or audit engineering manuscripts for IEEE and ACM Transactions, journals, and conferences, with optional self-contained HTML audit maps. Use for abstracts, introductions, related work, system models, mathematical formulations, algorithms, experimental methods, results, discussions, conclusions, contribution lists, notation and claim audits, evidence-grounded peer-review reports, venue adaptation, machine-idiom humanization of AI-flavored prose, or landmark-paper calibration in communications, signal processing, energy systems, robotics, optimization, simulation, ML-assisted engineering, and computer systems. Do not use for general documentation, grant proposals, marketing copy, or editorial accept/reject advocacy detached from manuscript evidence.

  • Doc standards

    JuanMarchetto/doc-standards-skill/doc-standards Skill

    13★ repo

    Documentation writing-quality standards — controlled language (ASD-STE100), Google/Microsoft style guide rules, ISO 24495 plain language, AI/agent readability (llms.txt, self-contained sections), and a machine-checkable lint gate. Use whenever writing or reviewing ANY documentation prose — README, API reference, tutorial, how-to, changelog, error message, code comment blocks, llms.txt — even if the user only says "write docs", "document this", "improve the README", "docs smell like AI", or "make the docs clearer". Structure/coverage questions (which doc types exist) belong to a Diátaxis-structure skill if one is installed; THIS skill governs how each sentence and section is written, and provides the lint gate to verify it.

  • Hands on labs

    timwukp/agent-skills-best-practice/skills-workshop/hands-on-labs Skill

    13★ repo

    35 portable agent skills (Agent Skills spec) for Kiro & Claude Code: Scrum DevSecOps roles, PCI-DSS/MAS TRM compliance, AWS Well-Architected reviews — each with evals and a 4-layer tested methodology

  • Benchmarking

    rusel95/ios-agent-skills/scripts/benchmarking Skill

    13★ repo

    Run skill benchmarks with discriminating-only assertions against evals.json for any model and any AI agent. Use when benchmarking a skill against a model not yet tested, running with_skill/without_skill eval pairs, producing benchmark-<model>.json, re-grading an existing run, adding Phase 2 model comparison results, reviewing results in the eval viewer, updating README benchmark tables, or cleaning non-discriminating assertions from evals.json. Enforces strict grader isolation (the context that generates responses never grades them) and evidence-only passing (assertions pass only on explicit content, never on implication or charity). Works with Claude Code, Gemini CLI, GitHub Copilot, Cursor, and any other AI coding assistant.

  • Arcgram

    jovesun-lab/arcgram Skill

    13★

    Generate an interactive node-and-edge diagram as a single standalone HTML file (Arcgram v2). Triggers on: arcgram, interactive/architectural diagram, topology, node graph, flow diagram, system map, dependency graph, workflow diagram, knowledge map, 'show me how X connects to Y', 'visualize this workflow', 'make this a topology', 'build a diagram of this'. Prefer for any system map, dependency graph, topology, or workflow picture even if interactivity wasn't asked for; on a follow-up 'make it inline' / 'show me' / 'render in chat', stay within Arcgram (Mode 1/2), don't switch tools.

  • Segment rollup

    JeffBrines/openfpa/examples/foxfactory/skills/generated/segment-rollup Skill

    13★ repo

    Use when modeling a multi-segment company that discloses segment net sales and segment Adjusted EBITDA (ASU 2023-07) but not segment COGS or operating income - rolls segment P&Ls into a consolidated forecast and reconciles total segment Adjusted EBITDA to the disclosed total. Generated for Fox Factory (PVG/AAG/SSG).

  • Gamma watermark remover skill

    gammaremover/gamma-watermark-remover-skill Skill

    13★

    Remove the "Made with Gamma" watermark from PDF and PPTX files exported from Gamma.app. Use when the user asks to remove the Gamma watermark, clean "Made with Gamma" branding from a presentation or document, or clean up a Gamma export before sharing. Works on files the user created; structural and lossless.

  • Experiment report skill

    lyzbcy/experiment-report-skill Skill

    13★

    Create a complete experiment report workflow with frontend visualization and structured markdown report. Supports any experiment type — just describe your experiment, and it handles the rest: implementation, interactive frontend, screenshots, and a docx-ready report. Use whenever the user mentions 实验报告、experiment report、前端展示、可视化报告, or wants a full report workflow that waits for visual confirmation before writing the final markdown.

  • Writing intelligence

    antonio0720/writing-intelligence Skill

    13★

    Writing Intelligence v3.0 — Sovereign Writing Operating System. 11-pass governed compiler, 12 engines, 12 specialist agents, 11 machine-readable schemas, epistemic ledger, voice fingerprinting, genre stacking, storyworld memory, arena delivery, benchmark regression. 27 domain packs (fiction, dialogue, thriller, transmedia, grant/NOFO, sermon, technical docs, social media, YouTube, newsletter, real estate, loan officer, church leadership, small business, journalism, resume, academic, sales, email, speech, pitch, government brief, medical, legal, patent, cinematic). Trigger on: write, rewrite, edit, draft, revise, ghostwrite, compile, audit, score, grade, redline, voice fingerprint, voice drift, genre stack, epistemic ledger, architecture graph, scene graph, delivery bundle, benchmark, prose, chapter, sermon, speech, pitch, memo, narrative, dialogue, scene, thriller, anti-slop, AI detection, grant writing, NOFO, resume, journalism, novel, screenplay, fiction writing.

  • Think like me

    kakha13/think-like-me Skill

    no license13★

    Personal engineering rules and reasoning patterns the user has curated over time. Consult BEFORE writing, modifying, debugging, or designing any technical feature — rules often cover domain-specific gotchas (e.g., mobile audio timers need background mode) that generic answers miss. Also triggers on `/learn-this`, "learn this", "remember this", or `/new-rule` to capture new rules, and on detected corrections to previously proposed code.

  • Fathom

    ma-ziwei/fathom-mode-for-claude/plugin/skills/fathom Skill

    13★ repo

    Enter Fathom Mode — a planning session where Claude pauses execution and helps the user build shared understanding through structured dialogue. Activate this whenever the user says "fathom", "fathom mode", "let's plan this", or asks to think through a complex task before acting. Stay in Fathom Mode until the user plans or exits.

  • Rails llm integration

    nagstler/rails-llm-integration Skill

    13★

    Production-grade LLM integration patterns for Ruby on Rails applications. USE THIS SKILL when the user needs to: integrate OpenAI, Claude, or any LLM API into a Rails app; use ruby_llm gem or langchain-rb gem in Rails; build AI-powered features in Rails; manage prompts as templates; route between LLM models for cost optimization; run LLM calls as background jobs; set up Braintrust evals; use LiteLLM or Portkey as a proxy; track LLM costs; test AI features; audit LLM usage patterns; build RAG pipelines in Rails with langchain-rb; add classification, summarization, extraction, or generation features to Rails; manage LLM API keys and budgets; handle LLM errors and retries; or adopt conventions for LLM service objects similar to ActionMailer or ActiveJob patterns. Triggers on: LLM in Rails, OpenAI Rails integration, Claude API Ruby, Anthropic SDK Rails, AI features Rails, prompt engineering Ruby, model routing, LLM cost optimization, Braintrust Rails, eval pipeline Ruby, background LLM jobs, async AI calls, LLM service objects, prompt templates Rails, ruby-openai gem, anthropic-rb gem, ruby-llm gem, ruby_llm gem, langchain-rb gem, langchainrb, faraday LLM, LLM anti-patterns Rails, audit LLM calls, AI service objects, Rails AI conventions, RAG Rails, vector search Rails, pgvector Rails.

  • Senzing entity resolution

    Senzing/senzing-mcp-skill/senzing-entity-resolution Skill

    no license13★ repo

    Guides AI agents through Senzing entity resolution workflows using the Senzing MCP server. Covers data mapping to Senzing format, SDK code generation (Python, Java, C#, Rust, TypeScript/Node.js), documentation search, error troubleshooting, sample data access, reporting and visualization, SDK setup guides, and V3-to-V4 migration. Use when working with entity resolution, record matching, record linkage, deduplication, Senzing SDK integration, data mapping for Senzing ingestion, or troubleshooting Senzing error codes. Also use when the user mentions matching records across data sources, finding duplicate entities, identity resolution, master data management, or needs to resolve who is who across datasets.

  • Si coder agent

    rahmanef63/si-coder-agent Skill

    13★

    Zero human involvement full-stack deployment. Umbrella skill that points to modular sc-* sub-skills (sc-all, sc-dokploy, sc-convex, sc-convex-cloud, sc-vercel, sc-git, sc-onboarding) plus the legacy monolithic deploy.js. Two deploy paths share one flow shape: self-hosted (Dokploy app + self-hosted Convex) and online (Vercel frontend + Convex Cloud). The user can invoke /sc-all for end-to-end (--target dokploy|vercel), /sc-convex/-cloud, /sc-vercel, or /sc-dokploy for narrower domain ops, /sc-git for GitHub repo/Actions ops, or /sc-onboarding to set up credentials.

  • Audit

    Marcel-Bich/marcel-bich-claude-marketplace/plugins/credo/skills/audit Skill

    13★ repo

    Read-only quality gate that audits already-built work against its stated requirement and Definition of Done before it is allowed to move to 2_done/. Produces a severity-ranked decision proposal (BLOCKER/MAJOR/MINOR/NIT) with evidence, never a fix. Use when an item is claimed complete, before moving anything to 2_done/, when asked to audit or review finished work for completeness against requirements, or when acting as the dedicated post-completion review subagent. This gate is mandatory in every session mode. Not for diagnosing why something is broken (use diag) and not for verifying rendered UI behavior (use verify).

  • Shellbrain usage review

    cucupac/shellbrain/onboarding_assets/claude/skills/shellbrain-usage-review Skill

    no license13★ repo

    ShellBrain. Long-term memory for AI.

  • Geo tracking

    Thibaultbm/claude-seo-geo/skills/geo-tracking Skill

    13★ repo

    Measure AI visibility without paid tools or API keys. Input: your site (GA4 and server logs) and a buyer prompt panel. Output: GA4 AI-traffic reporting (custom channel group plus referrer regex above Referral), monthly brand mention rate, citation rate, and share of voice versus competitors across ChatGPT, Perplexity, AI Overviews, Claude, and Gemini, plus verified AI-crawler hits from logs. Repo reference for measurement. Use to track AI traffic, monitor brand mentions, run prompt tracking, compute share of voice, or build a monthly GEO report.

  • Caption writer th

    PiNocPie/thai-claude-skills/skills/content/caption-writer-th Skill

    no license13★ repo

    caption IG/FB หลาย tone + CTA | สำหรับ นักเขียน คอนเทนต์ครีเอเตอร์ หร. Triggers when user says (Thai/EN): 'caption', 'แคปชั่น'

  • Giasip dispatch

    GiaSip/giasip-skills/locales/zh/skills/giasip-dispatch Skill

    13★ repo

    多模型调用器 — 把任务或 prompt 派发给其他 AI 模型(Codex / Gemini / Kimi / DeepSeek / 豆包 / Qwen / GLM / MiniMax)执行并取回结果。当你想用某个或某几个其他模型跑任务、需要多模型交叉对比验证、或想用更便宜的模型省钱时触发。提供两类调用通道:API 直调(只需 API key)和 CLI 调用(需本地装对应 CLI)。触发信号:「用 Kimi/Codex/Gemini 跑一下」「交给其他 AI」「换个模型试试」「让几个模型都看看」「这个不用最贵的模型」。

  • Design thinking skills

    rastian/design-thinking-skills Skill

    no license13★

    Guide any team through the Design Thinking methodology — empathize, define, ideate, prototype, test, and implement. Core audiences: product & design teams (product designers, UX researchers, UI designers, service designers, product managers), entrepreneurs & startups (idea validation, customer discovery, lean prototyping), and business & strategy leaders (innovation workshops, service redesign, customer journey mapping, business model innovation). Trigger on: design sprint, HMW question, how might we, empathy map, affinity diagram, point of view statement, design brief, user journey, service blueprint, jobs to be done, usability test, problem statement, customer discovery, lean validation, innovation workshop, or when user describes a user problem and wants to explore human-centered solutions.

  • Brochure generator

    plushyta/Awesome-Marketing-Skills/.agents/skills/brochure-generator Skill

    no license13★ repo

    Generates premium, multi-page, mobile-optimized (1:1 aspect ratio) PDF marketing brochures for exclusive retreats, workshops, luxury events, or any high-end product/service offering. Use this skill whenever a user asks to create a brochure, marketing PDF, event flyer, WhatsApp marketing material, social media brochure, or design a multi-page promotion document. Also trigger when users mention wanting to promote an experience, product, or service and need visual marketing material. Even if the user just says "make a brochure for my event" or "I need a PDF for my product," use this skill.

  • Architecture

    DojoCodingLabs/code-sensei/skills/architecture Skill

    13★ repo

    Software architecture, design patterns, and system design concepts. Activated for Blue Belt and above when Claude makes significant architectural decisions.

    The same file is in 2 other repositories

  • Edu role play

    minicoursegenerator/skills-for-course-creators/skills/edu-role-play Skill

    13★ repo

    Create interactive AI role-play training activities as self-contained HTML. Use when the user asks to generate a role-play, persona practice, sales simulation, customer conversation drill, compliance scenario, or any learner-vs-AI-character training exercise.

  • Architecting

    VidyFoo/antigravity-skill-engine/.agent/skills/1-dev/architecting Skill

    13★ repo

    Architects new features through the full lifecycle. Use when designing, planning, implementing, or extending features. Triggers on 'new feature', 'design', 'plan', 'implement', 'architect', 'prd', 'spec'.

  • Dsgvo auth and logging

    wuemaikblume/dsgvo-skills/claude/skills/dsgvo-auth-and-logging Skill

    no license13★ repo

    Use whenever code touches authentication, login, session management, audit logging, or application logging — even if the user's prompt doesn't mention DSGVO, GDPR, privacy, or "personal data". Triggers on bcrypt/argon2/scrypt, jsonwebtoken/jose, passport/next-auth/Auth.js/authjs/lucia, express-session/iron-session, cookie-session, set-cookie headers, login/logout/signup/register endpoints, password reset flows, refresh-token rotation, console.log of user data, Express middleware that logs req/res, Next.js middleware logging, audit-log table schemas, IP-Adress-Speicherung, X-Forwarded-For handling, OAuth 2.0 / OIDC Authorization Code + PKCE flows (authorization_code, code_verifier, code_challenge, redirect_uri, state, nonce, openid-client, oauth4webapi), OAuth callback routes, magic-link login URLs. ALSO triggers on these specific setup tasks (treat as auth/logging even when phrased as a pure tech question) — (a) Error-/Application-Monitoring-Setup: Sentry, Sentry Setup, Sentry Wizard, `npx @sentry/wizard`, Sentry für Next.js / React / Node / Express einrichten, `Sentry.init`, `beforeSend`, `beforeBreadcrumb`, `sendDefaultPii`, `tracesSampleRate`, Datadog, LogRocket, Pino, Winston, Bunyan, morgan setup; (b) Brute-Force / Rate-Limit / Account-Lockout — auch wenn als reine Security-Frage gestellt: Brute-Force-Schutz mit IP-Tracking, Login-Lockout, Failed-Login-Counter, express-rate-limit, rate-limiter-flexible, `app.set('trust proxy', ...)` (IP-Tracking ist immer personenbezogen — DSGVO-Layer ergänzt OWASP); (c) Multi-Factor / 2FA / TOTP / WebAuthn / Passkeys: TOTP einbauen, 2FA Setup, MFA für Admin / Admin-Login, authenticator app, otplib, speakeasy, `authenticator.generateSecret`, `authenticator.verify`, recovery codes, backup codes, WebAuthn registration, `navigator.credentials.create`, FIDO2. Also triggers on phrases like "log the user in", "store IP", "audit trail", "wer hat sich wann eingeloggt", "Login-Versuche tracken", "Sentry konfigurieren". Covers DSGVO Art. 5 (Zweckbindung, Speicherbegrenzung), Art. 6 (Rechtsgrundlage), Art. 32 (Sicherheit der Verarbeitung — Hashing, MFA, Rate-Limit, Cookie-Flags), Art. 25 (Privacy by Design in Logs), EuGH/BGH-Rechtsprechung zu IP-Adressen als personenbezogenes Datum, typische Aufbewahrungsfristen für Auth-/Sicherheits-Logs (DSK-Orientierungshilfe, BfDI-Richtwerte). Complementary to `owasp-security`: this skill adds the DSGVO layer (purpose limitation, retention, pseudonymization, lawful basis) — load it even if `owasp-security` is already active. Cross-Link: Drittland-Auth-Provider und Cookie-Tracking → dsgvo-third-country-transfer.

  • Gtm audit

    adaptico/adaptico-os/src/core/skills/gtm-audit Skill

    13★ repo

    Full go-to-market marketing audit for /gtm audit <target>. Runs up to 5 parallel audit subagents with machine-validated outputs and produces a scored, date-stamped report that leads with what changed since the last audit - and never invents a number. Use when the user wants a full marketing/GTM audit, an overall website marketing review, or a composite GTM score. Also trigger for "audit my site", "review my marketing", "how's my GTM", "full marketing teardown", or "score my website".

  • Dotnet techne code review

    Metalnib/dotnet-episteme-skills/skills/dotnet-techne-code-review Skill

    13★ repo

    Use when reviewing PRs/diffs/branches/documents for .NET quality, correctness, performance, security, data access, messaging, and observability. Includes adversarial critical-thinking mode for skeptical/cynical review requests. Keywords: code review, review PR, review diff, critical review, cynical review, adversarial review, production readiness, low GC, AOT, security review.

  • Russian abbreviations

    Halfofthesky/claude-russian-editor/skills/russian-abbreviations Skill

    no license13★ repo

    Правила сокращений в русском тексте по справочнику Мильчина и Чельцовой. Используй при работе с любым русским текстом, где встречаются или могут потребоваться сокращения: графические (т. е., и др., г.), аббревиатуры (РФ, МГУ, ГОСТ), сложносокращённые слова (завкафедрой). Используй для проверки: нужна ли точка, как склоняется аббревиатура, допустимо ли сокращение в данном контексте, как правильно написать сокращение во множественном числе. Обязательно применяй при редактировании научных, деловых, справочных текстов на русском языке.

    The same file is in 2 other repositories

  • Add tests

    tykisgod/quick-question/skills/add-tests Skill

    13★ repo

    Author Unity EditMode, PlayMode, or regression tests for the current change without conflating that with test execution.

  • Api and interface design

    kevinnft/ai-agent-skills/skills/addyosmani/api-and-interface-design Skill

    13★ repo

    Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.

  • Pushing creation

    PUSHINGSQUARES/pushing-creation/.claude/skills/pushing-creation Skill

    13★ repo

    Cinematic prompt methodology for AI image and video generation. Activates when the user mentions cinematic projects, shot lists, shoot briefs, storyboards, style packs, or visual generation workflows.

  • Add dials parameter

    tidymodels/skills/developers/add-dials-parameter Skill

    no license13★ repo

    Guide for creating new dials parameters for hyperparameter tuning. Use when a developer needs to define custom tuning parameters for models, recipes, or workflows, including quantitative parameters (continuous/integer), qualitative parameters (categorical), parameters with transformations, and data-dependent parameters requiring finalization.

  • Upkeep audit

    wei18/Upkeep/skills/upkeep-audit Skill

    13★ repo

    Run the Upkeep repo audit locally against any repository path. Use when asked to audit a repo, check docs/spec/asset drift, or run upkeep without GitHub Actions.

  • Find skill

    oleksbard/claude-find-skill/find-skill Skill

    13★ repo

    Use when the user wants to find or discover a Claude Code skill that is NOT already installed — e.g. "is there a skill for X", "find me a skill that…", "what skills exist for…", or "/find-skill <topic>". Searches the official plugin marketplace, GitHub, and curated awesome-lists for community skills matching a need, removes anything already installed, and recommends the top 5 with links. Do NOT use this to create or edit skills (that is skill authoring), or to pick among skills you already have.

  • Aviationstack

    shlomsh/hermes-travel-skills/skills/aviationstack Skill

    13★ repo

    Live flight status — gate, terminal, boarding, delay, baggage belt. Same-day only.

  • Notebook video

    hyt315/notebook-video Skill

    13★

    Create complete Chinese 2K warm-ivory engineering-notebook explainer and promotional videos with React, TypeScript and Remotion. The default visual route is lecture composition: multi-zone scenes drawn entirely with code (SVG diagrams, mascots, progressive checklists, annotation stickers) synchronized frame-accurately to Chinese TTS word timing, so production never depends on an image-generation model; image generation is an optional add-on offered to the user for concrete hero scenes. Includes native-30fps motion, active-scene mounting, complete exits, declarative audio, H.264/AAC rendering, provenance manifests and automated QA. Use when the user asks to 做科普视频, 手账风视频, 定格动画, AI 视频, 产品宣传片, 介绍一个概念, 讲解产品或技能, 制作 30 秒到数分钟视频, 网站动画转 MP4, 加中文配音/字幕/音效, 快速生成 2K 视频, or combine animated text and diagrams without producing a moving slide deck.

  • Backfilling sources

    buildinternet/releases/.claude/skills/backfilling-sources Skill

    13★ repo

    Product release note registry, made for agents

  • Ab scripting feature dev

    mumez/pharo-agentic-browser/skills/ab-scripting-feature-dev Skill

    no license13★ repo

    Generates an AgenticBrowser Scripting DSL orchestration that implements a feature end-to-end — plan (if needed), TDD implementation, tests, and a lint/style-guide review pass — previews it as docs/scripting-features/feature-<name>.scripting.md, and on user approval runs it via st-eval. Use this whenever the user wants to build or automate a feature "using the scripting DSL", asks to orchestrate coding agents (claude/codex/etc.) to implement something in an AgenticBrowser-based repo, or asks for a multi-agent orchestration script (`AgenticBrowser runBy:` / `scriptBy:` / `groupRunBy:`) for feature development. Trigger on phrases like “Implement it using the scripting DSL,” “Create an orchestration script,” “Create a feature-xxx.scripting.md file”, "scripting DSLで実装して", "オーケストレーションスクリプトを作って", "feature-xxx.scripting.mdを作って", even if the user doesn't say "skill" explicitly.

  • Apostle antislop

    kaile9/apostle-skills/skills/apostle-antislop Skill

    13★ repo

    Edit existing English or Chinese prose when the language has become model-shaped rather than subject-shaped: inflated significance, vague authority, answer scaffolding, repeated conclusions, template paragraphs, flattened voices, or English-shaped Chinese. Use for AI味/模型腔/机翻腔/套话/slop. Supports diagnosis, local cleaning, and explicitly authorized blank-page rewriting while preserving meaning and genre. Not ordinary proofreading, imitation, fact-checking, authorship detection, or detector evasion. Pure translation belongs to `apostle-translation`.

  • Agent governance

    mouadja02/skills/skills/agent-design/agent-governance Skill

    no license13★ repo

    Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)

  • Mao zedong perspective

    hkfrank996/mao-zedong-perspective Skill

    13★

    毛泽东的思维框架与表达方式。基于公开著作、访谈与历史决策资料提炼,用于分析组织、战略、动员、矛盾与路线问题;当用户提到“用毛泽东的视角”“毛泽东会怎么看”“切换到毛泽东”等表达时使用。

  • Go development

    netresearch/go-development-skill/skills/go-development Skill

    no license13★ repo

    Agent Skill: Enterprise Go development patterns - resilient services, testing | Claude Code compatible

  • Dotnet analyzer config

    Postpartum-genushyacinthus29/dotnet-skills/skills/dotnet-analyzer-config Skill

    13★ repo

    Use a repo-root `.editorconfig` to configure free .NET analyzer and style rules. Use when a .NET repo needs rule severity, code-style options, section layout, or analyzer ownership made explicit. Nested `.editorconfig` files are allowed when they serve a clear subtree-specific purpose.

  • Antimatter code quality review

    CheckPickerUpper/skills/skills/engineering/antimatter-code-quality-review Skill

    13★ repo

    Total annihilation: no finding survives unless it survives refutation. An unusually strict maintainability and structural-quality audit of a diff — review frame, intent/spec fit, repo standards, abstraction quality, cohesion, type/boundary cleanliness, duplication, control-flow tangles, and correct-by-construction opportunities. Use for a deep code-quality audit, a harsh pre-merge review, or to determine what structural change makes a class of bug impossible rather than merely caught. Stricter than a conventional review because every finding must survive an adversarial refutation pass, ship with a concrete before→after, and prove it preserves behavior. Severity theater is prohibited: only provable findings are reported.

  • Ab testing design

    Dragoon0x/everything-design-taste/skills/ab-testing-design Skill

    13★ repo

    A/B test design, experiment setup, variant design, and statistical analysis for designers.