agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Advisor

    HumanBean17/agent-mindset-skills/advisor Skill

    no license1★ repo

    Use for decisions, comparisons, or understanding where you want a recommendation — analysis only, no changes or artifacts.

  • Ax2012 aos crash triage

    whobat/AI-Agent-skills/skills/ax-retail/ax2012-aos-crash-triage Skill

    1★ repo

    Triage Microsoft Dynamics AX 2012 / R3 AOS (Ax32Serv.exe) crashes and the RPC session-allocation cascade. The bundled script collects, server-side, AOS process crashes (Application 1000 / Ax32Serv.exe), unexpected service terminations (System 7031 / "Object Server"), and the kernel session precursors (Dynamics Server 110 "Session Allocation Failed: already allocated" + 180 "invalid session ID"), then correlates AOS terminations with AX rich-client (Ax32.exe) crashes on the RDS/Citrix farm to expose the "AOS dies -> every client drops at once -> reconnect storm" cascade. Use when an AX AOS service crashed/restarted, users got disconnected en masse, or you see Event 7031/110/180 — e.g. "why did the AOS crash", "AX kicked everyone out", "Ax32Serv keeps restarting". Do NOT use for AX SQL/database slowness (that is ax2012-sql-performance) or generic non-AX event-log triage (that is win-eventlog-triage). Requires PowerShell 7+ and WinRM + an admin credential (always prompted).

  • Skill

    MBCustoms/scs-modding-wiki-skill/skill Skill

    no license1★ repo

    Use when working on ETS2 or ATS mods, asking about SCS unit file formats (.sii, .sui), Blender Tools export/import, Map Editor, Workshop Uploader, sound modding, truck accessories, trailers, cargo, game configuration variables, console commands, or any question about official SCS Software modding documentation.

  • Wdym

    ndisisnd/wdym Skill

    1★

    Prompt rewriter that fires automatically on UserPromptSubmit via a hook-injected <prompt-detect> block. Detects prompt type (code, question, text-gen) and rewrites using 2–3 matched principles; flash mode runs immediately, comprehensive gates for approval. Manage with /wdym --init, --status, --set-mode, --help.

  • Scorm

    studiolxd/skills/scorm-skills/plugins/scorm-skills/skills/scorm Skill

    1★ repo

    Use when integrating SCORM 1.2/2004 in a web app with @studiolxd/scorm — initializing a session, reading/writing CMI data (score, completion, suspend data, interactions, objectives), handling Result errors, or wiring lifecycle/auto-commit across React, Vue, Angular, Svelte, Web Components, or vanilla JS.

  • Agent backup

    quietdaemon/starter-skills/skills/agent-backup Skill

    1★ repo

    Mirror your AI assistant's live config (skills, persona, settings, custom plugins) to a private git remote. Run on a schedule via cron — secrets and runtime state are excluded by an allowlist .gitignore. Use when asked for a manual backup, or when a backup cron fires.

  • Ci fix

    pricklywiggles/fractally-claude-marketplace/plugins/ship-it/skills/ci-fix Skill

    no license1★ repo

    Watch a pull request's CI to completion and fix any failures in its branch, bounded and cause-only. Use when CI is red on a PR or branch and you want it driven to green ("fix the CI on this PR", "CI is failing, sort it out", "watch the checks and fix what breaks"). Acts on a PR number, URL, or branch you name, or the current branch's open PR if you name none. Also called by the ship-it orchestrator's post-PR phase, one watcher per PR. Not for reviewing code quality (use a reviewer) or fixing local errors with no PR/CI (just fix those directly).

  • Gatekeeper

    JayOfemi/claude-toolbox/skills/gatekeeper Skill

    1★ repo

    Scan a repo for secrets and private info before it goes public: API keys, tokens, private keys, connection strings, leaked local paths, and configurable deny terms.

  • Env doctor free

    justhandledlabs/skills/plugins/env-doctor-free/skills/env-doctor-free Skill

    1★ repo

    Diagnose local project environment issues that prevent apps from starting or running. Use when the user says "why won't this run", "check my environment", "env doctor", "diagnose startup issue", "it works on my machine", or asks for help debugging missing dependencies, runtime versions, port conflicts, .env problems, file permissions, or stopped services.

    The same file is in 2 other repositories

  • Ai thumbnail factory

    calebvbi/creator-skills-samples/skills/ai-thumbnail-factory Skill

    no license1★ repo

    AI YouTube thumbnail generator — 3 CTR-optimized concepts in 2 minutes with layout specs, text overlays, color palettes, and ready-to-paste AI image prompts.

  • Claude skills kit

    Abed-Zahed/claude-skills-kit Skill

    1★

    A complete Claude Code skill kit — prompt polishing with auto-routing, 5-phase engineering workflow, web research, knowledge ingestion, advisory board simulation, and multi-agent focus group. Skills work standalone or as an integrated system.

  • Unified token telemetry

    drewid74/unified-token-telemetry Skill

    no license1★

    Use this when: track AI token usage across providers, build unified cost dashboard, how much am I spending on AI, compare model costs, cache hit ratio monitoring, LiteLLM token tracking, GitHub Copilot usage, OpenAI usage API, Anthropic usage API, ChatGPT Plus cost tracking, Claude Pro cost tracking, Gemini Advanced cost, Perplexity Pro cost, Cursor usage, Windsurf usage, multi-provider token telemetry, subscription cost tracking, idempotent token collection, hourly token rollups

  • Design qa

    humbleteam/design-qa Skill

    1★

    Runs a pre-ship design QA gate on a screenshot, URL, or PR HTML/CSS - checks states, WCAG 2.2 contrast, touch targets, breakpoints, and keyboard paths, then returns a pass/fail table and fix list. Trigger phrases - "QA this screen", "is this ready to ship", "check this PR for accessibility issues", "audit before launch". Skip for style critique - use design-review instead; this checks only verifiable gate criteria.

  • Maturity engine

    kamkate/dev-team-maturity-performance-skills/plugins/maturity-engine/skills/maturity-engine Skill

    1★ repo

    Use this skill when the user asks anything about engineering team performance, delivery maturity, sprint analysis, KPI computation, cycle time, roadmap contribution, WIP, epic development time, pattern detection, or intervention recommendations based on Jira data. Triggers on questions like "analyse this team", "compare sprints", "what is our maturity score", "which team needs attention", "show me the trend", or any request involving delivery metrics from uploaded Jira data files.

  • Beebe policy framing

    1beebe/beebe-qualitative-skills/skills/beebe-policy-framing Skill

    1★ repo

    Run anthropological policy-framing analysis on a corpus of contested-policy documents (memos, press, hearings, correspondence). Use when the user asks for framing analysis, metaphor analysis, actor-attributed qualitative coding, anthropology of public policy, or Beebe policy analysis. Produces linked CSVs — actor-attributed statements, a conceptual-metaphor register, frame evolution, positionality flags, and a timeline — suitable for NVivo import.

  • Mr wolf

    limelights-amsterdam/mr-wolf Skill

    1★

    A calm, fast crisis strategist who gets stuck companies moving. Use when an organization or leader is frozen — strategic paralysis, AI anxiety in the boardroom, months of talking without a decision, a market moving faster than the company — or when the user mentions Mr. Wolf, crisis intervention, or asks to get a team unstuck.

  • Findcoworkskills

    Invest-with-AI/findcoworkskills Skill

    1★

    Find skills you can install and use in Claude Cowork for a given topic. Use this skill whenever the user wants to discover existing skills before building their own — triggers include "find cowork skills for X", "what skills exist for X", "is there already a skill for X", "search for skills about X", "find me a skill that does X", or "before I build a skill, what's out there for X". Searches the open skill catalog, reads each result's actual SKILL.md to see which ones declare Cowork / Claude Desktop support, ranks everything by GitHub stars, and writes a single branded HTML report. No account or token needed.

  • Prototype

    TecCat/claude-skills/prototype Skill

    no license1★ repo

    Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".

  • Prompt coach

    goingli0324/prompt-coach Skill

    1★

    Turns a vague, underspecified request into a clearly structured Goal / Constraints / Obstacle breakdown, then produces a ready-to-use structured prompt. Use this whenever the user brings a fuzzy ask ("幫我想辦法...", "有什麼方法可以...", "我不知道怎麼處理..."), asks explicitly to help them "問對問題" or structure their request, or describes a real-world problem/decision they want AI help with but haven't yet specified what success looks like, what can't change, or what the actual blocker is. Trigger this proactively — even without the user naming the skill — any time answering directly would likely produce a generic, "technically correct but not actually usable" answer rather than something tailored to their real situation.

  • Demo gif

    oaklake-studio/oaklake-tools/plugins/demo-gif/skills/demo-gif Skill

    1★ repo

    Use when the user wants a demo GIF / screen recording of a web UI (for a PR, README, changelog, or showcase) in ANY project. Drives a browser through a short scripted flow you define with the user, records one continuous video (headless by default), and converts it to a calm, followable GIF saved under .demo-gifs/ at the project root (auto-added to .gitignore when the root is a git repo). Browser/UI demos only, not terminal/CLI recordings. Assumes a POSIX shell (macOS/Linux; on Windows use WSL or git-bash).

  • Cost lean orchestration

    itzTiru/claude-code-skills-fable5/cost-lean-orchestration Skill

    no license1★ repo

    Token-efficient model routing for complex engineering sessions. The main model (Opus / Fable, high reasoning) never bulk-reads or explores — it delegates all exploration, bulk file reading, codebase search, log scanning, dependency tracing, and documentation reading to Sonnet subagents that return compact structured findings, and it spends its own tokens only on synthesis, architecture, judgment, and final code. Use this skill in EVERY session that involves reading more than a couple of files, exploring or mapping a codebase, investigating a bug, auditing call sites, reviewing a large diff, digesting logs or docs, or any multi-step engineering task — even if the user never mentions cost, tokens, subagents, or delegation. This is a standing operating discipline, not an on-request feature.

  • Design brief

    humbleteam/design-brief Skill

    1★

    Extract a 5-bullet design brief (Problem, Audience, Success metric, Must-haves, Constraints) from messy inputs - transcripts, docs, freetext - with a gap report instead of guessing at missing fields. Trigger phrases - "write a design brief", "turn this transcript into a brief", "what's missing from this brief", "update the brief, now it's B2C". Do not use for visual design tokens (extract-design-tokens) or a dev handoff spec (design-handoff).

  • Wnb compose animation

    wenubey/claude-android-skills/skills/wnb-compose-animation Skill

    1★ repo

    Use this skill when a Jetpack Compose UI is about to gain an animation, or when reviewing existing motion. Enforces the decision-aware gate — first ask "should this UI animate at all?"; only if yes, then pick the smallest API (AnimatedVisibility, animate*AsState, rememberTransition, AnimatedContent, Animatable). Requires every animation to earn its frame budget, carry a label, respect reduce-motion accessibility, and stay off scroll-adjacent recomposition paths. Triggers on "add animation", "animate", "fade in", "make it smooth", "smooth transition", "fancy transition", "AnimatedVisibility", "animate*AsState", "AnimatedContent", "rememberTransition", "Animatable", "Crossfade", "animateContentSize", "should this animate", "reduce motion".

  • Add external skill

    filippolmt/skills/.claude/skills/add-external-skill Skill

    1★ repo

    Add or update external skills in this marketplace as git-subdir entries and keep the README catalog in sync. Usage: /add-external-skill <owner/repo> [path] [name] | /add-external-skill update

  • Ib companion

    grahamlittle/ib-companion/skill/ib-companion Skill

    1★ repo

    Use when a student needs help with any aspect of the International Baccalaureate Diploma Programme — subject content, Internal Assessments, Extended Essay, Theory of Knowledge, exam technique, or study strategy. Invoke for any IB DP question.

  • Proxmox ops

    Enzojol/claude-homelab-skills/skills/proxmox-ops Skill

    1★ repo

    Safe Proxmox VE administration: VM and LXC lifecycle with snapshot-before-write discipline, vzdump backup and migration workflows, storage troubleshooting, task (UPID) polling, qm/pct/pvesm command guidance, API-first with documented SSH fallback. Use for any question about proxmox, pve, vm, lxc, container, vzdump, backup, snapshot, qemu, cluster, storage pool, passthrough, or homelab virtualization.

  • Follow up sequence

    faiz-sayyad/gtm-outreach-skills/skills/follow-up-sequence Skill

    no license1★ repo

    Draft a 3-touch follow-up sequence with distinct angles per touch. Uses the "reply-not-pitch" pattern for touch 2 (30% higher performance in the source data). Use whenever the user asks for a follow-up, sequence, cadence, multi-touch outreach, or wants to know how to re-engage after silence. Also use when the user says "they didn't reply, now what" or asks about persistence in outbound.

  • Agy

    dT-Tb-labs/babel-orchestration/skills/agy Skill

    1★ repo

    Use when user invokes /agy or asks for a second-opinion code review via Google Antigravity CLI (`agy`). Sibling of gemini-cli-review.

  • Mastery learning

    Premansh12/Mastery/skills/mastery-learning Skill

    no license1★ repo

    Use this skill whenever the user wants to learn, master, or get taught a technical or niche topic — especially topics with no formal curriculum or teacher available (e.g. "teach me GNC", "I want to master harness engineering", "help me learn amyloid plaque biology", "I want to understand X like a professional"). Also trigger on requests to build a lesson, study guide, or learning plan for a subject, requests to review/quiz on something already learned, and requests to set up spaced review for material already taught. Do not use this for quick factual questions that don't need a structured lesson — only for requests where the person wants to actually build knowledge over one or more sessions.

  • Html mockup

    humbleteam/html-mockup Skill

    1★

    Builds a pixel-faithful single-file HTML mockup from a reference screenshot by counting colors, photos, items, and states before writing markup. Use when a user says "turn this screenshot into HTML", "build a mockup that matches this design", "code this screen exactly", or pastes an image and asks for a coded version. Do not use for layout exploration with no reference image - use ascii-wireframes instead.

  • Youtube growth engine

    MrBridgeHQ/youtube-growth-engine/.claude/skills/youtube-growth-engine Skill

    1★ repo

    Use this skill when the user wants to promote, grow, audit, optimize, monetize, distribute, or create traffic for a YouTube channel or video. This includes YouTube SEO, thumbnails, titles, Shorts, playlists, collaborations, community posts, external distribution, newsletters, blogs, social media repurposing, paid ads, analytics diagnostics, content calendars, launch plans, and ethical growth strategy.

  • Cdfi peer benchmark

    Jaypatel1511/cdfi-superpowers/skills/cdfi-peer-benchmark Skill

    1★ repo

    Benchmark a bank CDFI against a peer group on FDIC call-report metrics (NIM, ROAA, ROAE, efficiency ratio, Tier 1 capital, loans-to-deposits, NPL ratio, loan-loss coverage). Use when the user says "benchmark this CDFI", wants a "peer comparison", or asks "how does this bank CDFI compare". Bank CDFIs only (FDIC-insured) — no credit unions, no unregulated loan funds. Backed by the audited PyPI package cdfi-benchmark; import name is `cdfibenchmark`.

  • Briefing card

    vincent-wen789/claude-briefing-cards/skills/briefing-card Skill

    1★ repo

    Load this whenever about to report to Vincent — a decision or options to pick, a progress update across projects, or a list of items needing his sign-off — to run the T0–T3 routing and pick the right form. 汇报/进度/决策/选项/确认/拍板 默认走 T2 出卡(2026-06-18 翻转默认)——除非一句话能说清/单一事实/闲聊(降 T0 纯文字)或 2-4 选项一行讲得清(降 T1 选项卡)才降级。Reporting/进度/汇报/决策/确认 a status or asking him to choose IS the trigger — running the routing is the default, plain text is an outcome of it, not a reason to skip the skill. Also on manual triggers 画个决策卡/进度卡/确认卡 / 出个卡, and on callback messages starting with 决策卡「/进度卡「/确认卡「 (apply 接收端守则 first). Skip only for one-sentence answers, single facts, and chit-chat.

  • Github skills

    he8um/github-skills/github-skills Skill

    1★ repo

    professional github repository architecture, governance, automation, security, and troubleshooting for ai agents. use when a user asks to create, scaffold, audit, refactor, document, secure, automate, release, or maintain a github repository; design repository structure, community health files, issue forms, pull request workflows, labels, projects, rulesets, code owners, github actions, releases, dependency automation, security controls, github cli/api plans, migration steps, and machine-readable repository blueprints.

  • Humanize writing

    marian-kamenistak/humanize-writing Skill

    1★

    Use when a draft sounds AI-generated or must not read as AI: 'humanize', 'de-AI', 'make this sound human', 'less AI', 'AI-smooth', 'sounds like ChatGPT', AI-detector concerns, or any external-facing text before delivery. Works as a universal base layer under any personal-voice or brand-voice skill. Language-agnostic.

  • Reading plan mentor

    haorantang97/reading-plan-mentor Skill

    no license1★

    把一份书单变成一个长期的、有导师陪读的每日阅读计划,并自动定时投递(默认邮件,可切换)。 当用户提到"读书计划""共读/陪读""想系统读完这几本书""给一份书单帮我安排""每天给我导读" "长期学习/阅读计划""把读书做成每日推送""读书打卡"等,或上传/列出多本书并问怎么安排时, 都应使用本 skill——即使他们没有明说"skill"或"每日邮件"。本 skill 覆盖:主题识别(含诚实退出)、 按书性质分类(论著/随笔/小说等线性叙事)、按时长的难度加权容量与节奏控制、跨文本钩子、 从日常对话里抓取并压缩用户的思考、进度看板与阶段复盘。 Use whenever a user wants to design or run a multi-day/multi-week reading plan, a daily reading guide, a read-along companion, or wants a booklist turned into a paced schedule with recurring deliveries — even if they don't say "skill" or "daily email".

  • Comps

    hansohn/marketplace-skills/skills/comps Skill

    1★ repo

    Research pricing comparables for a secondhand item using live eBay sold listings and active Facebook Marketplace listings. Use whenever the user wants to know what a used item is worth, find resale comps, check sold prices, price an item for sale on Facebook Marketplace or eBay, or build a pricing recommendation for resale. Trigger on phrases like "what's this worth", "price comps", "sold for", "resale value", "list price for". Always pull live data via browser automation — do not rely on training data for current market prices.

  • Obsidian knowledge net

    aldrick-t/obsidian-knowledge-net-skills/skills/obsidian-knowledge-net Skill

    1★ repo

    Capture, synthesize, retrieve, update, and audit reusable development knowledge in a user-selected Obsidian vault. Use when documenting incidents, workflow failures, release lessons, troubleshooting patterns, runbooks, prior Codex threads, GitHub investigations, or when maintaining linked knowledge notes through the Obsidian CLI.

  • Curated epub audiobook

    annexiao/read-the-best-first/skills/curated-epub-audiobook Skill

    1★ repo

    Use when turning a book EPUB or a collection of articles (blog archive, newsletter, essay site) into a cleaned, inspiration-ranked EPUB and optionally an .m4b audiobook. Triggers on "convert this blog to an epub/audiobook", "make an audiobook from these essays", "rank these articles and package them", "把这本书转成有声书", "把这个博客做成 epub", "按精彩程度排序". Skip for a single article (just read or TTS it directly) and for converting an already-clean, already-ordered book (skip straight to the audiobook stage).

  • Build anything

    kalias/OPC_starter_skills/skills/build-anything Skill

    no license1★ repo

    用「元技能 4 步框架」从零构建任何东西(网站 / 自动化 / AI 系统)。当用户想做一个新产品、面对复杂项目不知道从哪下手、或在「AI 怎么帮我做」上挣扎时使用。

  • Card generation

    tmj-90/gaffer/packages/memory/skills/card-generation Skill

    1★ repo

    Internal skill for onboard's file-card emission pass. Defines how to write one file card from a mechanical structure summary (imports, top-level symbols) plus an optional bounded head snippet — NEVER the whole file. Drives the per-file (or batched) model turn in onboard-analyze.mjs with a versioned prompt_version hash. Not for the ticket delivery flow.

  • Github profile optimizer

    MrBridgeHQ/github-profile-optimizer/.claude/skills/github-profile-optimizer Skill

    1★ repo

    Use when optimizing a GitHub profile or making repositories and skills more discoverable. Covers auditing or rewriting a GitHub profile README, improving the bio, avatar, headline, pinned repositories and developer branding, doing GitHub SEO and repository discoverability work, and preparing to publish and list Agent Skills / Claude Code SKILL.md skills in awesome lists, registries and directories. Triggers on "optimize my GitHub profile", "GitHub profile README", "profile README", "pinned repositories", "developer branding", "GitHub SEO", "repository discoverability", "agent skills publishing", "submit skill to awesome list", "SKILL.md visibility", "Claude skills registry".

  • Igrantio consent records

    L3-iGrant/skills/consent/igrantio-consent-records Skill

    1★ repo

    Record and manage individual consents against a data agreement using the iGrant.io Consent Building Block, given a dataAgreementId and an individualId. Node/TypeScript backend for the individual Consent-Record API: create, read, list, update (allow/withdraw), history, and delete-all (GDPR right to be forgotten). Use when an application must capture and manage a user's consent decisions. Get individualId from igrantio-individuals.

  • Claude squarespace skill

    SipMyBeers/claude-squarespace-skill Skill

    no license1★

    Port a designed static/custom site (Cloudflare Pages, a static build, a Figma-to-code export, etc.) INTO Squarespace 7.1 by pasting markup into Code Blocks and CSS into the Design / Custom CSS panel, and driving the admin via a browser. Use this WHENEVER the task involves editing a Squarespace 7.1 site's Custom CSS or Code Injection, pasting HTML/CSS into a Squarespace Code Block, making a Squarespace site match an existing design, or debugging why a Squarespace page "looks off," has invisible text, a white/blank hero, broken mobile, giant mobile headings, a stuck image carousel, an empty/oversized footer section, or unstyled pasted markup. Also use for Squarespace + WebGL/canvas heroes, native Form Block styling, and "make it match the Cloudflare/worker version." These platform behaviors are non-obvious and have burned real sessions — consult this before hand-editing, not after.

  • Multi model adversarial review

    HamzaYM/reliable-ai-skills/skills/adversarial-review/multi-model-adversarial-review Skill

    1★ repo

    Use before merging any substantive change, or before finalizing a document, plan, or claim, when you want a genuine adversarial pass rather than the same model re-reading its own work. Applies to code diffs, PRs, architecture plans, and prose (specs, memos, claims). Not worth it for trivial one-line changes.

  • Seo translator

    Skillproofdev/seo-translator Skill

    no license1★

    Use when the user asks to translate or localize content — documents, blog posts, marketing copy, website pages, UI strings — into one or more languages, or requests SEO-aware translation for international markets. Handles single texts and batches; detects SEO intent (titles, meta descriptions, keywords) automatically and preserves search-optimized phrasing per target market. Do not trigger for programming-language "translation" or for interpreting spoken conversation.

  • Agent skill auditor

    fevziegeyurtsevenler/llm-security-skills/skills/agent-skill-auditor Skill

    1★ repo

    Statically audit any Agent Skill, MCP server config, or rules file (CLAUDE.md, .cursorrules, AGENTS.md) with the `uncloak` scanner BEFORE installing, enabling, or trusting it — catches invisible-Unicode instruction smuggling, MCP tool-description poisoning, credential/exfil paths, and lethal-trifecta posture. Use whenever you are about to add, copy, or fetch a third-party agent extension.

  • Auth hardening

    AL-JANEF/janefskills/auth-hardening Skill

    1★ repo

    Review, harden, and design authentication and session management for web applications — login, logout, session lifecycle, password storage, token handling, and brute-force protection. Use this skill whenever the user is building or reviewing sign-in / sign-out flows, JWT or session cookies, password hashing, "remember me", refresh tokens, account lockout, OTP/MFA, or password reset — even if they only mention "login" or "auth" casually. Applies to Node.js, Next.js, and similar stacks. Defensive only: this skill hardens auth systems, it does not bypass or attack them.

  • Pdf trust

    shuji-bonji/pdf-trust-skill/skills/pdf-trust Skill

    1★ repo

    PDF の信頼性監査オーケストレーション。受け取った PDF(契約書・請求書・診療文書・申告書・行政文書など)が「本物か・信用してよいか・改ざんされていないか」を、pdf-verify-mcp を軸に pdf-reader-mcp / pdf-spec-mcp / houki 系 MCP を編成して監査し、推奨判定付きの Trust Report を返す。4 値判定は pdf-verify-mcp の evaluate_policy(決定論的ルールエンジン)が下し、Skill は発火ルールの解説・推奨アクション・法令根拠を担う。ユーザーが「この PDF は信用できる?」「署名を確認して」「受入監査して」「改ざんされてない?」「電子署名の有効性」「長期保存(電帳法・PDF/A・LTV)できるか」「取引先から届いた PDF のチェック」などに言及したら、単発のツール呼び出しで済ませず必ずこの Skill を使う。複数 PDF の一括監査にも使う。

  • Slipstream

    wheelhouseatl/slipstream Skill

    1★

    Builds and guides a personalized, self-updating learning curriculum for staying current in a fast-moving field. On first use it interviews the user, researches the current landscape, and generates a tailored plan. On later use it recommends the next study block sized to available time, runs the session, tracks completion, and keeps the curriculum current against new developments. Use this skill whenever the user wants to catch up on or stay current with a field, build a study plan or learning roadmap, asks "what should I learn next", says "slipstream" or "catch-up session" or "briefing", or wants to track progress through self-directed learning. Trigger it even when the user only describes the goal ("I've fallen behind on AI", "help me get up to speed on X") without naming a plan.

  • Hermes skill

    x-name15/gorrent/skills-for-ai/hermes-skill Skill

    1★ repo

    Automates downloading torrents using the local Gorrent daemon via the CLI wrapper.

  • Ooda

    88plug/ooda/skills/ooda Skill

    no license1★ repo

    Use before deciding, acting, iterating, planning, diagnosing, or competing — whenever a move should be driven by a fast adapt-loop rather than a guess. Triggers on "what should we do", "how do we approach", deciding/planning, "let's iterate / ship / pivot", incident and root-cause work, "we're stuck", and competing/beating-an-incumbent. The move: run John Boyd's real OODA loop — Observe (measure, don't assume), Orient (reframe against stale models and bias — the highest-leverage step), Decide (one lever, as a hypothesis), Act (ship a test, re-observe), loop fast at an unpredictable tempo. Boyd-faithful: not a 4-box speed circle, Orient dominates, tempo is rhythm not haste. Reach for it on non-trivial decisions and iterative work; skip mechanical single-answer tasks.

  • Amazon tracker

    ssskay/claude-skills/inbox-catalog/skills/amazon-tracker Skill

    1★ repo

    Use when the user asks about their Amazon purchases and returns — "what did I buy on Amazon", "what can I still return", "track my Amazon returns", "catalog my Amazon orders", "which Amazon items should I evaluate", or how many days are left to return something. Read-only; runs a zero-setup synthetic demo, or reads the user's own Amazon order, shipment, delivery, and return-window emails.

  • Astro mbti

    CharlotteShen/astro-tarot-bazi-divination-skills/astro-mbti Skill

    1★ repo

    Playful folklore game: predicts your MBTI type from your natal chart via a deterministic weighted-heuristic script — explicitly NOT a measurement (astrology→MBTI has no scientific correlation, and the output says so). Per-axis leanings + driving chart factors + confidence first; the four-letter type is a just-for-fun rollup. English/中文. Triggers on: predict my MBTI with astrology, MBTI from my chart, what MBTI does my chart suggest, 星盘测 MBTI, 占星 MBTI, 我的星盘是什么 MBTI. Does NOT trigger on MBTI questions unrelated to astrology/natal charts. Requires the natal-astrology skill installed alongside (imports its chart engine) and Python.

  • Mkpub

    ndisisnd/mkpub/.claude/skills/mkpub Skill

    1★ repo

    Generates and updates a repository's four public-facing docs — README.md, LICENSE.md, SECURITY.md, and llms.txt — from a scan of the repo itself. The README uses a figlet-rendered centered header and badgen badges. Use when the user says "write a README", "generate docs for this repo", "add a license", "add a security policy", "add llms.txt", "/mkpub", or asks to document a repository or skill for release.

  • Cvnizer

    slovozaslovo/cvnizer Skill

    1★

    Use when CV or resume prose needs to read like a strong senior/executive CV - when text sounds conversational, personal, AI-generated, fluffy, or runs long. Works on any CV block (summary, bullets, cover-letter paragraphs). Triggers include "run cvnizer", "cv-ify this", "does this sound like a director CV", "my resume sounds like ChatGPT", finalizing any CV section.

  • Tanya warga yux skills

    alfathony/tanya-warga-yux-skills Skill

    no license1★

    Simulasikan feedback desain UI dari beberapa persona pengguna yang berbeda, dalam bentuk "think aloud" (bicara sambil mikir) saat mereka menjelajahi tampilan dari atas ke bawah, ditutup dengan rangkuman temuan lintas persona. Gunakan skill ini kapan pun user melampirkan desain UI (screenshot, gambar, atau link Figma) dan minta divalidasi, dicek, diminta pendapat, second opinion, atau feedback dari sudut pandang user/pengguna — bahkan jika mereka tidak secara eksplisit menyebut kata "persona" atau "usability testing". Trigger juga untuk frasa seperti "tanya warga", "coba tanya user", "gimana menurut user awam", atau "validasi desain ini ke beberapa tipe pengguna".

  • Apify linkedin post engagement

    johnisanerd/claude-skill-linkedin-post-engagement/apify-linkedin-post-engagement Skill

    no license1★ repo

    Analyze LinkedIn post engagement with the Apify LinkedIn Posts API Actor (johnvc/linkedin-posts-api). Collect a profile's posts or a list of post URLs, then measure reactions, comments, and shares alongside author reach (followers, headline) to see what performs. Use when the user wants to analyze LinkedIn post engagement, measure engagement rate, find a creator's or a competitor's top-performing posts, benchmark engagement across profiles, track post engagement over time, or build a LinkedIn engagement report. Returns one row per post with numLikes, numComments, numShares, datePosted, and a ready-made engagement view. Pay-per-post billing, MCP-ready for Claude and other AI agents.

  • Arnes implementador

    Ajlm1978/arnes-implementador/skill/arnes-implementador Skill

    1★ repo

    Implementa "arneses" (harness engineering) profesionales en repos de software para que agentes de IA trabajen de forma fiable y multi-sesión. NO es un generador de plantillas: primero AUDITA el repo como ingeniero senior — identifica el stack real, corre la prueba de arranque en frío, revisa los 5 subsistemas y busca gaps/fallas (verificación ausente, tests acoplados al entorno, crashes de arranque, sin estado entre sesiones, alcance sin WIP=1), y ENTREGA hallazgos + recomendaciones ANTES de escribir nada. Luego genera e instala un arnés adaptado (CLAUDE.md/AGENTS.md router, init.sh, claude-progress.md, feature_list.json, DECISIONS.md) con comandos reales, en rama + PR. Usa SIEMPRE que el usuario quiera "implementar/instalar un arnés", "arnesear un proyecto", "preparar el repo para agentes/Claude Code", "hacer mi proyecto agent-ready", "auditar mi repo", "diagnosticar gaps" o entregue un repo para dejarlo listo. Aplica aunque no use la palabra "arnés".

  • Adhd working mode

    dlectronique/adhd-mode-marketplace/plugins/adhd-working-mode/skills/adhd-working-mode Skill

    1★ repo

    A lean, momentum-first working mode for building software with an AI assistant — lead with the action, one decision at a time, one next step (never the whole tree), keep state in the tracker so nobody re-explains, and build to a real production bar. Built by and for someone with ADHD, but you don't need ADHD to benefit — anyone who thinks better with less on the screen and a clear next move will. Apply it as the default working style on every task, question, plan, and code change, even short ones. If you're about to write a wall of text, dump a pile of options, or ask something already answered, this skill is why you shouldn't.