agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Campaign sequencer

    0xjitsu/jitsu-skills/skills/campaign-sequencer Skill

    1★ repo

    Multi-channel drip sequence orchestrator that builds and executes outbound campaigns across email, Slack, and direct messages. Triggers when the user asks to set up an outbound campaign, drip sequence, multi-channel outreach, or creator outreach program. Coordinates Clay enrichment, Gmail drafts, Slack DMs, and scheduled follow-ups with full state tracking in Supabase. Enforces send limits, opt-out compliance, and batch confirmation before any messages go out.

  • Global agent framework

    wemwi/skill-library/global-agent-framework Skill

    no license1★ repo

    Build-Time-Framework zum Bauen, Konfigurieren, Deployen und Debuggen von Claude Managed Agents (Claude Platform / Anthropic Console) in diesem Stack — Anleitung für die Arbeit AM Agenten, kein Skill der einem laufenden Agent angehängt wird. IMMER laden, sobald ein Managed Agent erstellt, konfiguriert, verdrahtet, deployed, versioniert oder gedebuggt wird — auch wenn das Wort Skill nicht fällt. Trigger u.a.: Managed Agent anlegen, Agent-Config (system/tools/mcp_servers/skills), Session starten, Scheduled Deployment / Cron-Trigger, Webhook-Brücke zum Starten von Sessions, Vault für Agent-Secrets, Permission-Policy, Least-Privilege, Allowlist/ Denylist, Tool-Oberfläche minimieren, enabled:false vs permission_policy, Agent- Version bumpen, Agent debuggen, neuen Agent ins Portfolio aufnehmen. Gilt für jeden Managed Agent in diesem Stack.

  • Skill observability monitoring

    zavora-ai/skill-observability-monitoring Skill

    no license1★

    Orchestrate full-stack observability — query logs, search traces, monitor metrics, manage alerts, handle incidents, track SLOs, and execute runbooks. Use when debugging errors, investigating latency, checking service health, managing alerts, responding to incidents, reviewing SLO burn rate, or finding runbooks.

  • Project to resume

    ChenxDeng/project-to-resume Skill

    1★

    将刚完成的项目总结为简历项目经历。当用户完成一个项目(开发、设计、研究等)并希望将其写入简历时使用此技能。触发词包括:写简历、总结项目、简历项目、项目经历、portfolio、写进简历、加到简历。即使用户只是说"这个项目不错,想放到简历里"也应触发。

  • Ab test setup

    t0ddharris/compound-marketing/.claude/skills/ab-test-setup Skill

    no license1★ repo

    When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," or "how long should I run this test." Use this whenever someone is comparing two approaches and wants to measure which performs better. For tracking implementation, see tracking-setup. For page-level conversion optimization, see page-cro.

  • Claude students

    josuebustosn/claude-students/skills/claude-students Skill

    1★ repo

    Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz, flashcards). Usar este skill SIEMPRE que el usuario diga "tengo parcial de X", "ayúdame con este parcial", "armame el material de estudio", "convierte estos archivos en un HTML estudiable", "transforma esta carpeta en material de parcial", "pásame esta carpeta a HTML interactivo", o simplemente comparta una carpeta con archivos de materia universitaria. También activar cuando aparezcan archivos tipo "GUIA PARCIAL", "TEMA X", "CamScanner", "WhatsApp Ptt", "Parcial.pdf", "Acumulativo" en el contexto. El skill replica un patrón validado en múltiples entregas reales — no preguntar metodología antes de empezar, arrancar directo.

  • Orch

    daman8271/the-perfect-orchestrator/plugins/orchestrator/skills/orch Skill

    1★ repo

    Spawn and orchestrate a fleet of autonomous Claude Code workers in tmux. One LEAD Claude (you) spawns N worker sessions, hands each a task brief, coordinates them via a shared message bus, monitors them live, intervenes when they drift, and adversarially verifies results before reporting. Use for parallelizable, multi-target, long-running work (audits, fixes across many modules/platforms, broad sweeps, "do X across all N of these"). Triggers: "spawn a fleet", "orchestrate workers", "delegate this across sessions", "tmux Claude team", "divide this and run it in parallel".

  • Lovable i18n

    globalize-now/lovable-i18n Skill

    1★

    Add multi-language support (i18n) to this Lovable app using Lingui. Use when the user asks to add i18n, internationalization, localization, or translations — "translate my app", "make my app multilingual", "add Spanish/French/German support", "add a language switcher", "support multiple languages", or "connect Globalize". Covers setup (Vite SPA and TanStack Start), wrapping hardcoded text, PO catalogs, a GitHub Action that keeps catalogs in sync, coding rules in AGENTS.md, and connecting the Globalize.now translation platform (via its MCP connector).

    The same file is in 1 other repository

  • Repo scout

    wallmage/repo-scout/repo-scout Skill

    1★ repo

    Use when a user shares a repository URL on any Git host, project website, package-registry page, or install command for a skill, plugin, CLI, library, extension, or application; asks “is this worth installing?”, “is this worth adopting?”, “thoughts?”, or for a comparison; says “install this” or “set it up for me”; uses `/plugin install`; or pastes `curl ... | sh`. It returns an INSTALL / SKIP verdict. Always run Repo Scout before every skill or plugin installation.

  • Dream studio

    iamjosuho/memOrb/skills/core/dream-studio Skill

    no license1★ repo

    夢工廠:每月重播 memorbs/log.md 的時間軸,找出反覆出現的主題,提議新增 Core orb、新增或修訂 Belief orb,更新 Island 現況敘事,最後輪替時間軸。這是 distillation pipeline 最後一步「Evaluate」的唯一執行者,也是 memorbs/HQ/Core/ 的唯一寫入者。觸發詞:做夢、夢工廠、dream studio、重播記憶、整理記憶、我最近變成什麼樣的人、我的信念有變嗎、更新核心記憶、Core orb、盤點信念。距上次執行超過一個月時可主動建議。前置依賴:memorb-conventions。

  • Prompt optimizer

    yorilavi/prompt-optimizer Skill

    no license1★

    Optimizes prompts through an iterative Claude-GPT review process. Use when the user wants to optimize, improve, or refine a prompt. Supports automated review via Codex plugin or manual GPT handoff.

  • Next on vercel perf

    SkillMedev/vercel-platform/skills/next-on-vercel-perf Skill

    1★ repo

    Diagnose and fix Core Web Vitals and page performance of a Next.js app on Vercel - measurement-first. Use when an LCP/INP/CLS score is bad, a page "feels slow", Lighthouse/PageSpeed/Speed Insights is red, the JS bundle is too big, images or fonts are janky, or you want Vercel-specific caching/edge wins. Triggers: "improve Core Web Vitals", "fix LCP", "reduce INP", "stop layout shift", "my Next.js page is slow on Vercel", "shrink my bundle", "next/image optimization", "font is causing CLS", "cache this page". Do NOT use to set up the deploy pipeline or rollbacks - use vercel-deploy-pipeline; for ISR/cache-component semantics and edge runtime choice - use vercel-edge-and-isr; for env/secrets - use vercel-env-management; for model/provider routing - use vercel-ai-gateway; for WAF/bot defense - use vercel-firewall-and-botid.

    The same file is in 1 other repository

  • Rust design review

    nikhil-salgaonkar/rust-design-review Skill

    no license1★

    Conduct a thorough Rust design review of code, functions, modules, or entire crates, covering idioms, design patterns, and anti-patterns. Use this skill whenever the user pastes or points at Rust code and asks for a review, design critique, pattern audit, or says things like "is this idiomatic?", "how would a Rust expert write this?", "review my Rust code", "what patterns am I missing?", "is this good Rust?", "do a design review", or "what am I doing wrong in Rust?". Also trigger for any request to refactor Rust code to be more idiomatic or better structured. Produces a structured review grounded in the rust-unofficial/patterns book (https://rust-unofficial.github.io/patterns/).

  • .template

    dlomibao/dl_skills/skills/.template Skill

    1★ repo

    Replace this with a specific one-line description that tells Claude exactly when to invoke this skill (triggers, keywords, scenarios).

  • Skill

    mattferry/tribunal/skill Skill

    1★ repo

    Use when running or triaging any external coding agent (Grok Build, Codex, a local model endpoint) as a reviewer or QA auditor of code — when asked for a second opinion, external QA, or an independent audit of work, and before reporting externally-audited code as reviewed or ship-ready.

  • Passion

    tomatikii/passion Skill

    1★

    Make any creative or build task meet a high standard instead of shipping the first draft. The "passion engine" — engineer what a worker who cares actually does. Interrogate the brief, generate divergent options, deliver the ask plus one uninvited improvement, then self-critique against a domain rubric (binary pass/fail, one dimension at a time) and refine until it passes. Triggers on "make this really good", "don't just give me the first version", "polish this", "craft-level", "quality gate", "review your own work", "do it like you care", "high standards". Pair with any rubric in references/, or write a new one. Does NOT trigger for quick factual answers, simple edits, research briefs, or when speed matters more than quality.

  • Skill

    bluem-dev/Etta/skill Skill

    1★ repo

    Etta Cognitive OS is a model-agnostic cognitive architecture layer that enhances LLM reasoning quality, continuity, planning, and knowledge management. Use this skill whenever the user asks to run structured reasoning sessions, implement goal-state-decision cognitive loops, manage persistent memory across LLM interactions, apply critic-gated validation before any action, build autonomous agents with structured state, or when the user explicitly mentions "Etta", "cognitive OS", "cognitive layer", "critic loop", "state engine", or "structured reasoning". Also trigger when designing multi-step agent workflows that require auditability, rollback, and deterministic cognitive control on top of any LLM.

  • Skill

    bluem-dev/Grace/skill Skill

    1★ repo

    Grace is a deterministic realization and convergence engine — the execution-side counterpart to Etta Cognitive OS. Use this skill whenever the user asks to convert structured cognitive intent into canonical, verifiable, persistent artifacts; build execution-graph (DAG) based task runners with parallel scheduling; enforce governance/invariant checks before committing state; manage artifact identity, version lineage, and replace semantics; reconcile workspace state against external tool/MCP outputs; or when the user explicitly mentions "Grace", "convergence engine", "execution graph", "canonical artifact", "governance core", or "realization layer". Also trigger when designing the execution/persistence half of an Etta-style cognitive architecture, or any system that must turn LLM-derived intent into deterministic, auditable, governed actions against real tools and storage.

  • Geo content brief

    1marcelserrano/mscreative-skills/skills/geo-content-brief Skill

    no license1★ repo

    Engine de briefing para conteúdo de era-IA — produz briefs que ranqueiam no Google E são citados por AI Overviews, ChatGPT, Perplexity, Gemini e Copilot (GEO/AEO/LLMO). Bimodal: modo ESTRATÉGIA (diagnóstico de intenção + PAA→H2 + edge + brief entregável) e modo PRODUÇÃO (answer block, seções autocontidas, schema/llms.txt, gate de pré-publicação). Use quando o usuário pedir: brief de conteúdo, otimizar para AI Overviews, GEO, AEO, ser citado por IA, ranquear no ChatGPT/Perplexity, content brief, SEO de IA, answer engine optimization, llms.txt, schema para IA, aparecer em busca generativa, otimizar artigo para busca, AI search, generative engine optimization, citação de IA, geo brief, content brief para IA. Genérica e vendor-neutral — aplicável a qualquer pessoa, marca ou negócio.

    The same file is in 1 other repository

  • Github skill curator

    xcl2005/github-skill-curator Skill

    1★

    Skill procurement and routing gate for Agent Skills. Use when the user asks to find, compare, install, update, audit, disable, remove, or curate Codex / Claude Code skills; asks for better, latest, high-star, GitHub-recommended, awesome-list, or reusable skills; or when a high-value repeated artifact workflow such as PPTX, DOCX, PDF, spreadsheets, LaTeX, academic writing, resumes, or reports may benefit from a specialized skill beyond built-in capabilities. It checks built-in and installed skills first, searches pinned core skills and curated indexes when useful, scores candidates by relevance, evidence, stars, recency, license, structure, curation quality, and safety, and asks before installing unknown third-party skills.

  • Grafana llmops forge

    alebgl77/grafana-llmops-forge Skill

    1★

    Pilote l'observabilité IA/LLM de bout en bout sur Grafana (OSS, Cloud, Enterprise) avec un seul prérequis — une instance Grafana accessible. Auto-découverte (version, APIs, datasources), détection des signaux LLM présents (OTel GenAI gen_ai.*, LiteLLM, vLLM, TGI, GPU/DCGM), génération et déploiement automatiques de dashboards — FinOps & coûts multi-providers (US/EU/Asie), gateway, tracing agents & RAG, adoption interne, gouvernance EU AI Act, inference self-hosted — alerting SLO, registre de modèles avec pricing, puis contrôle visuel du rendu réel (captures renderer/navigateur inspectées par vision). Utilise ce skill dès que l'utilisateur mentionne Grafana, un dashboard, du monitoring/observabilité IA ou LLM, des coûts de tokens, du FinOps IA, du LLMOps, des agents ou du RAG, l'adoption de modèles, la conformité AI Act, ou Prometheus/Loki/Tempo appliqués à l'IA — même sans le mot « dashboard ». Vaut aussi pour auditer un Grafana existant ou une stack IA qui n'émet encore rien.

  • Vibe coding prod

    mvp-imran/AISkills/vibe-coding-prod Skill

    1★ repo

    Complete production-grade vibe coding skill that transforms any app idea into a fully structured, ship-ready software project. Use this skill whenever someone says "vibe code", "build an app", "I have an app idea", "let's build something", "create a product", "build for production", or asks to go from idea → shipped app. Covers the full pre-build pipeline: PRD → TRD → App Flow → UI/UX Brief → Backend Schema → Implementation Plan. Also triggers on partial requests: "write me a PRD", "create a tech spec", "design the database schema", "plan my app architecture", "create an app flow diagram", or "write an implementation plan". Always use this skill — it prevents half-baked apps from entering production.

  • Reasoning budget router

    firststone-vc/reasoning-pack/skills/reasoning-budget-router Skill

    1★ repo

    Use when a task can mostly be handled by a cheap/fast model but one specific sub-part (multi-step math, a long constraint chain, an edge case) is likely to break it — draft the whole task cheap, detect exactly which chunk hit the ceiling, and escalate ONLY that chunk to a stronger model instead of re-running everything on it.

  • Bookmark Ninja

    SamaritanOC/Bookmark-Ninja Skill

    1★

    Converts browser bookmark HTML exports (Chrome, Firefox, Edge, Brave) into structured JSON or CSV indexes for agent consumption. Use whenever the user asks to parse, convert, organize, index, merge, deduplicate, or verify bookmarks, or when they want to turn a bookmark export into a queryable knowledge base. Supports incremental merging with conflict resolution and optional URL liveness checking.

  • Earth online

    lexielin99-code/earth_online Skill

    no license1★

    地球 Online 技能面板——以 RPG 技能树形式记录个人成长。用于查看面板、记录学习/健身/阅读/自媒体的进展、管理旅行时间轴与成就点。只在用户主动调用 /earth-online 时触发。

  • Due diligence briefer

    mloki23/due-diligence-briefer Skill

    1★

    Use when a business owner or investor wants to evaluate a business before buying it. Triggers on: "due diligence on [business]", "should I buy this business", "evaluate this acquisition", "what's wrong with this business", "red flag check", "buying a business checklist". Researches financial health, industry benchmarks, red flags, and negotiation leverage — then delivers a structured briefing with a buy/caution/pass verdict. No API keys or paid tools required — works with web search alone.

  • Aidress skill find verified language translation agent

    Aidress-ai/aidress-skill-find-verified-language-translation-agent Skill

    1★

    Find a Verified Language Translation Agent. Agent discovery, trust verification, and capability routing powered by Aidress — the coordination registry for autonomous AI agents. Use for content agent discovery, trust verification, and capability routing — via Aidress (https://api.aidress.ai).

  • Skill device fleet management

    zavora-ai/skill-device-fleet-management Skill

    no license1★

    Manage device fleets — get device info, check security posture, list applications, collect diagnostics, run health checks, and create remediation tasks. Use when checking device health, auditing security posture, listing installed apps, collecting diagnostics, or remediating compliance issues.

  • Skill creator pro

    zwbao/skill-creator-pro Skill

    1★

    Use when creating new skills, iterating on existing skills, auditing skill quality, bumping skill versions, or optimizing skill trigger descriptions. Pro-grade lifecycle covering scaffold, baseline testing, evals, lint, semver, CHANGELOG, and description optimization. Triggers on "create a skill", "new skill", "迭代 skill", "优化 skill", "skill 版本", "skill lint", "review this skill", "write a skill for X", "turn this into a skill", or whenever the user starts or edits a SKILL.md.

  • Skill package dependency management

    zavora-ai/skill-package-dependency-management Skill

    no license1★

    Manage package dependencies — lookup packages, check versions, review changelogs, assess compatibility, analyze lockfiles, and propose upgrades. Use when updating dependencies, checking for outdated packages, planning major upgrades, reviewing changelogs, or auditing dependency health.

  • T3d grill me

    coolsocket/t3d/skills/t3d-grill-me Skill

    1★ repo

    Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use BEFORE writing code on any non-trivial feature — bounded context selection, aggregate boundaries, invariants, ubiquitous language. The harness assumes you grill-me first.

  • Git github workflow

    ivogabriel19/git-github-workflow-skill/skills/git-github-workflow Skill

    1★ repo

    Professional Git and GitHub workflow conventions, including CI configuration. Use this skill for every version control or repository operation — staging changes, writing commit messages, creating or switching branches, opening pull requests, rewriting history, tagging releases, setting up branch protection, authoring or reviewing GitHub Actions workflows, or any `git` command. Apply these rules mechanically to keep `main` deployable, commits atomic and conventional, history navigable, PRs reviewable in under thirty minutes, and CI fast and reliable. Trigger this whenever you're about to commit, push, open or merge a PR, run `rebase`, `reset`, `cherry-pick`, write a `.github/workflows/*.yml` file, or configure repository settings — even for trivial one-line changes.

  • Check

    christophecapel/claude-mechanisms-tools/skills/check Skill

    1★ repo

    Session-close audit — session-scoped manifest, two-section open items, decisive close signal. Runs the `/check` audit defined in `check.md`. Use when the user says "check", "audit this session", "close the session", "definition of done", or wants a clean-vs-blocked verdict before ending a session.

  • Carbon decision memos

    MalamaLabs/Carbon-Market-Skills-Pack/skills/carbon-decision-memos Skill

    1★ repo

    Write structured decision memos for carbon project choices — registry selection, methodology selection, measurement architecture tradeoffs (estimation vs. in-situ), buyer/offtake structure, and other consequential project decisions where the tradeoffs need to be documented before locking in. Use whenever the user is weighing a carbon-project-specific decision and wants it written up formally, or says things like "help me think through whether to use X or Y methodology/registry," "document why we chose," or "write up the tradeoffs." Trigger proactively when other skills in this pack (pdd-generator, carbon-project-timeline) flag an unresolved decision blocking progress.

  • Camera and photos

    heyimjames/ios-design-skills/plugins/heyimjames/skills/camera-and-photos Skill

    1★ repo

    Design and build best-in-class native iOS camera, photo-capture, and photo-editing apps with the polish of Halide, Kino, Lapse, VSCO, and Apple Photos. Use this skill whenever the user is building, reviewing, or refining a SwiftUI/UIKit app that involves the camera, photo library, video capture, image editing, filters, scanning, AR effects, AI photo features, or anything backed by AVFoundation, PhotoKit, Vision, VisionKit, Core Image, ImageCaptureCore, ARKit, RoomPlan, or LiDAR. Triggers on: camera, viewfinder, shutter button, AVCaptureSession, AVCapturePhotoOutput, PHPicker, PhotoKit, photo library, photo grid, photo edit, filter, crop, presets, LUT, Cinematic mode, Portrait mode, ProRAW, ProRes, Live Photos, HDR, depth, LiDAR, subject lifting, VisionKit, Live Text, document scanner, QR scanner, magic eraser, object removal, AI photo, Core ML, Vision framework, ARKit face tracking, manual camera controls, Camera Control button, volume button shutter, spatial photo, spatial video, Apple Vision Pro.

  • Test drive

    glichtenthal/test-drive Skill

    1★

    Use when the user has a plausible but untested idea, belief, thesis, strategy, decision, prompt, skill, message, artifact, or AI output and asks how to validate it, test it, try it, de-risk it, gather evidence, run analysis, run a regression, dry-run it, evaluate it before shipping, identify needed connectors, or turn judgment into evidence-seeking action.

  • Agency request intake router

    afelipeg/Anthropic-Skills-for-enterprise-marketing-os/skills/agency-request-intake-router Skill

    1★ repo

    Classifies agency client requests and routes them to the correct operating workflow. Use when a user shares a new brief, client request, campaign ask, scope change, media request, CRM request, reporting request, QBR request, or asks "what workflow should this trigger?" or "where does this go?" or "who owns this?" Also trigger when someone pastes an email from a client asking for something, shares a vague operational ask that needs routing, mentions a new deliverable, or asks about commercial impact of an incoming request. Even casual phrasing like "the client wants X", "just got this brief", "can we do this?", or "is this in scope?" should activate this skill.

  • 21st dev builder v2

    NafisRayan/100x-Agent-Toolkit/skills/21st-dev-builder-v2 Skill

    no license1★ repo

    Build websites and web apps using 21st.dev — the largest marketplace of shadcn/ui-based React Tailwind components with 1400+ components. Use when user mentions "21st.dev", "21st", "ใช้ 21st", "จาก 21st", "build with 21st", "21st component", "21st magic MCP", or references the 21st.dev component registry in any language. Covers building complete sites (landing pages, dashboards, portfolios, e-commerce storefronts, auth pages), browsing and installing individual 21st.dev components into existing projects, and setting up the 21st.dev MCP server. Also trigger when user wants premium UI components specifically from the 21st.dev registry. Do NOT trigger for general web development, standard shadcn/ui, plain Tailwind CSS, React Native, API development, testing, deployment, or any task that doesn't explicitly reference 21st or 21st.dev.

  • Advisor

    roozbeh-bahrami/claude-code-advisor/advisor Skill

    1★ repo

    Turn this session into my read-only, brutally honest advisor. It reviews my working sessions' output — plans, claims, files, decisions — verifies them with its own eyes (read-only, never changes anything), separates PROVEN from CLAIMED, catches traps (re-litigation, churn, over-engineering, scope drift, "impossible" without checking), and tells me plainly whether it's right and the exact text to paste next. Talks short and casual like a sharp friend, not a corporate report. Use whenever I paste a working session's output for review, ask "is this right / on track / can I trust this", want a second honest opinion before I greenlight or build, or say "be my advisor."

  • Nuggetindex

    searchsim-org/nuggetindex-skill/skills/nuggetindex Skill

    1★ repo

    Use when a RAG pipeline or knowledge base returns stale, outdated, or conflicting facts, or when the user mentions temporal drift, fact governance, contested answers, time-aware retrieval, fact freshness, entity renames (Twitter/X), or nuggetindex. Audits retrieved passages for stale and contested facts, maintains a governed time-aware fact ledger, and escalates to the nuggetindex pip package at corpus scale. Zero install for the common case.

  • Claude session smasher

    adi17-netizen/Claude-session-smasher Skill

    1★

    Compacts an entire chat into a dense markdown summary that restores ~80% of context when pasted into a new chat. Trigger on: 'summarise this chat', 'save this session', 'session smash', '/session-smasher-as-v2', 'wrap this up', 'save our progress', 'compact this chat', 'continue this later', 'create a handoff', 'context is getting long', 'running out of credits', chat is too slow or too long, or wanting to start fresh without losing context.

  • Claudecode skill html screenshot

    bluei98/claudecode-skill-html-screenshot Skill

    no license1★

    HTML 파일/폴더 → PC & Mobile 렌더링 스크린샷 PNG/JPEG export. 로컬 HTTP 서버로 안전하게 렌더링. Trigger: /html-screenshot, 'HTML 스크린샷', 'HTML 캡처', 'HTML 캡쳐', '웹페이지 캡처', 'PC/모바일 캡처', 'html screenshot', 'render HTML', 'webpage capture', 'PC mobile capture', 'HTML スクリーンショット', 'HTML キャプチャ', 'ウェブページ キャプチャ', 'PC・モバイル キャプチャ'

  • Ppt to notes

    rutulpatel07/ppt-to-notes Skill

    1★

    Generates comprehensive university exam study notes from lecture PPT/PPTX files. Use this skill immediately whenever a user attaches or mentions a PPT, PPTX, or lecture slides and wants notes, study material, revision material, cheat sheet, Q&A, exam prep, or study guide. Also triggers when user says "generate notes", "make notes from this", "study material", "exam notes", "notes from slides", or anything related to converting lecture presentations into structured study content. Do NOT wait for explicit instructions — if a PPT is attached, use this skill automatically.

  • Skill a

    wxs777/cc-radar/tests/fixtures/home_claude/skills/skill-a Skill

    no license1★ repo

    Does thing A

  • Assumptions and dependencies

    timothyhoughton/pm-delivery-skills/pm-scoping/skills/assumptions-and-dependencies Skill

    1★ repo

    Stress-test the Assumptions and Dependencies sections of a Scope of Work — the load-bearing paragraphs that save the PM at week four. Use when you've drafted a SoW and want to pressure-test what you've assumed, what the client is on the hook for, and what would trigger a change request. Triggers: 'stress-test assumptions', 'pressure-test dependencies', 'what am I assuming', 'which assumptions would hurt if wrong'.

  • Brand positioning

    KEITH-GJINO/Marketing-Skills/brand-positioning Skill

    1★ repo

    Use this skill whenever the user wants help with brand strategy, positioning, messaging, ICP (ideal customer profile) definition, value proposition development, category design, competitive differentiation, brand voice, or naming. Trigger on phrases like "positioning," "what's our angle," "who are we," "differentiate from competitors," "value proposition," "elevator pitch," "brand voice," "ideal customer," "target audience," "messaging framework," "tagline," "what do we stand for," and any work involving how a brand is perceived in market. Also trigger when a user describes their business and asks how they should describe it, or shares competitor messaging and asks how to stand out.

  • Skill workflow orchestration

    zavora-ai/skill-workflow-orchestration Skill

    no license1★

    Orchestrate multi-step workflows with approval gates, state machines, and conditional branching. Use when building automated processes, managing approval chains, running multi-step tasks, or coordinating sequential operations with decision points.

  • Skill cicd pipeline management

    zavora-ai/skill-cicd-pipeline-management Skill

    no license1★

    Orchestrate CI/CD pipelines — check build status, view logs, download artifacts, rerun workflows, trigger deployments, and manage release gates. Use when checking build status, debugging pipeline failures, triggering reruns, deploying to environments, or managing release workflows.

  • Adr writer

    imtiazrayhan/agentscamp-library/skills/adr-writer Skill

    1★ repo

    Write an Architecture Decision Record capturing a decision the user describes, in Michael Nygard ADR format (Status, Context, Decision, Consequences) with an added Considered Alternatives section. Use when recording a significant architectural or technology choice.

  • Pbt hypothesis

    alialavia/pbt-skills/skills/pbt-hypothesis Skill

    1★ repo

    Hypothesis-specific patterns for property-based testing in Python — strategies, RuleBasedStateMachine, settings, and Hypothesis ecosystem gotchas. Use this skill whenever the task involves Hypothesis tests, the `hypothesis` package, `@given`, `st.` strategies, `RuleBasedStateMachine`, `@example`, or any Python property-based testing work. This skill pairs with the core `property-based-testing` skill, which handles property discovery and design — load both together for any Hypothesis task. This skill does not re-derive the workflow; it assumes the core skill is loaded and only covers Hypothesis syntax, idioms, and library-specific patterns.

  • Architect codebase review

    sirius-zuo/architect-skills/architect-codebase-review Skill

    1★ repo

    Use when an existing codebase needs an architecture review. Explores the codebase, generates current-state architecture diagrams using Mermaid.js, evaluates against architecture principles, proposes recommended improvements with revised diagrams, and saves an HTML report to docs/architecture/review/.

  • First skill template

    knack-run/knack-starter-pack/skills/first-skill-template Skill

    1★ repo

    Scaffold a new Claude Code skill at `.claude/skills/<name>/SKILL.md` with the canonical Knack body pattern (frontmatter, when-to-use, inputs, steps, output format, worked-example pointer, don'ts). Triggers on "scaffold a skill called X", "make me a new skill", "create a SKILL.md for X", "I want to write my first Claude Code skill". Refuses to overwrite an existing file; refuses to invent skill content the user hasn't supplied.

  • Sql sentinel

    takeaseatventure/sql-sentinel/skills/sql-sentinel Skill

    1★ repo

    Audit SQL for the cost & performance anti-patterns that burn warehouse credits. Catches SELECT *, full-table scans, non-sargable predicates, Cartesian joins, NULL-trap NOT IN, and 17 more rules. Scores warehouse health 0-100 and outputs a prioritized cost-reduction plan for BigQuery, Snowflake, Redshift, and Postgres.

  • Triteme

    quanvu309/triteme/plugins/triteme/skills/triteme Skill

    1★ repo

    Use this skill whenever the user wants to write, draft, reply to, or improve a professional message for WhatsApp, email, Slack, or any work communication. Trigger on phrases like "draft a message", "reply to this", "help me write", "make this more professional", "follow up with", "how should I respond", or when the user shares a conversation thread and needs help composing a response. Also trigger when the user asks about professional communication style, tone, or etiquette. This skill covers client communication, project updates, meeting coordination, payment discussions, proposals, pushback handling, status updates, and any business messaging where clarity, momentum, and relationships matter. Do NOT use for long-form content (articles, reports, essays), code, or whole documents. This skill is for messages and short business communications only. Produces a ready-to-send message in the requested channel's format, plus the key choices behind it.

  • Cdm 2015 check

    Jody09-dotcom/constructionx-skills/skills/cdm-2015-check Skill

    1★ repo

    Check a UK construction project against CDM 2015 duty-holder requirements and determine F10 notifiability. Use when the user asks about "CDM 2015", "CDM check", "F10", "notifiable project", "duty holders", or is scoping a new project and needs the CDM picture. Outputs duty-holder roles, F10 y/n with reasoning, pre-construction info checklist, construction phase plan checklist.

  • Useforgekit

    Dragoon0x/useforgekit Skill

    no license1★

    Generate optimal Claude Code configuration for any project. Creates CLAUDE.md, settings.json, skills, hooks, agents, and commands tailored to your stack. Run /forge to start.

    The same file is in 1 other repository

  • Dungeon master assistant

    dorian-akhs/dungeon-master-assistant Skill

    1★

    Co-DM assistant for tabletop RPG campaigns. Use this skill whenever a DM or GM mentions session recaps, session debriefs, processing a session transcript, updating campaign notes, NPC tracking, world-building, lore consistency, session prep, campaign arcs, adventure planning, faction tracking, location discovery, or timeline management. Also trigger for any mention of D&D, Pathfinder, Call of Cthulhu, Blades in the Dark, Shadowdark, Mörk Borg, or any other tabletop RPG system in the context of managing campaign content. English trigger phrases: "debrief my session", "process my transcript", "update my campaign files", "create an NPC profile", "plan next session", "check lore consistency", "build my world bible", "what happened last session", "check continuity". French trigger phrases: "débriefe ma session", "compte-rendu de session", "résumé de séance", "traite ma transcription", "mets à jour mes notes de campagne", "crée un profil de PNJ", "prépare la prochaine séance", "vérifie la cohérence du lore", "vérifie la continuité", "construis ma bible du monde", "qu'est-ce qui s'est passé la dernière séance", "jeu de rôle", "maître du jeu", "MJ". Spanish trigger phrases: "resumen de sesión", "debriefing de sesión", "procesa mi transcripción", "actualiza mis notas de campaña", "crea un perfil de PNJ", "planifica la próxima sesión", "verifica la consistencia del lore", "comprueba la continuidad", "construye mi biblia del mundo", "qué pasó en la última sesión", "juego de rol", "máster", "director de juego", "DJ". Italian trigger phrases: "resoconto della sessione", "debriefa la mia sessione", "elabora la mia trascrizione", "aggiorna le mie note di campagna", "crea un profilo PNG", "pianifica la prossima sessione", "verifica la coerenza del lore", "controlla la continuità", "costruisci la mia bibbia del mondo", "cosa è successo nell'ultima sessione", "gioco di ruolo", "master", "narratore". German trigger phrases: "Sitzungszusammenfassung", "debriefe meine Sitzung", "verarbeite mein Transkript", "aktualisiere meine Kampagnendateien", "erstelle ein NSC-Profil", "plane die nächste Sitzung", "überprüfe die Lore-Konsistenz", "überprüfe die Kontinuität", "erstelle meine Weltbibel", "was ist in der letzten Sitzung passiert", "Rollenspiel", "Spielleiter", "SL". Use this skill even if the user doesn't explicitly call it a "campaign" — if someone is running a game and wants to document or plan it, this skill applies.

  • Product dev workflow

    diablofong/product-dev-workflow Skill

    1★

    Product Dev Workflow — a branch-per-task development assistant. Single slash command /pdw with seven sub-flows. Use /pdw alone to see the menu, or /pdw [sub] [args] for a specific flow. Sub-commands are init, talk, dev, hotfix, done, status. Also accepts natural language ("/pdw I want to build a login page") and auto-routes.

  • Claude fullstack ai builder

    LX-Director/claude_fullstack-ai-builder Skill

    no license1★

    全栈AI应用快速搭建方法论。帮助非技术背景的创始人、效率工具创造者、企业内部系统搭建者,在没有后端工程师的情况下,快速从想法到上线一个完整的AI驱动全栈应用。 核心价值:端到端完整路径(需求分析→技术方案→前端→后端→AI集成→部署上线) 适用场景: - "我有个想法,想快速做一个web应用/工具" - "怎么快速搭建一个内部系统" - "想集成AI能力,但不知道怎么开始" - "需要一个简单的数据库系统" - "如何快速部署前端页面" - "想做一个能处理用户上传文件的应用" - "如何集成DeepSeek/通义千问/Gemini等AI API" - 用户描述了一个完整的应用场景,询问技术方案

  • Handoff

    SpoiledMilkLabs/skills/skills/handoff Skill

    1★ repo

    Capture session state at end of a coding session so a future Claude Code session can resume cold, or resume from a prior handoff. Trigger PROACTIVELY when the user signals end of session — "wrapping up", "call it for tonight", "let's stop here", "I need to go", "continue tomorrow", "pick this up later", "save where we are", "done for now" — and also on explicit /handoff. For resume, trigger when user says "resume", "pick up where we left off", "continue from yesterday", "what was I working on", or /handoff resume.