agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Agri env permit check

    Zerif007/Claude_Legal-Bangladesh_Edition/bd-agriculture-environment-legal/skills/agri-env-permit-check Skill

    0★ repo

    Maps the permit/clearance stack for agriculture, forestry-adjacent, fisheries or water-touching operations in Bangladesh — forest/wildlife constraints, fisheries licences, seed/pesticide/fertiliser registrations, water-use rights, brick-kiln rules, hill-tracts overlays — and flags criminal exposure. Use for "set up a hatchery/kiln/ agri-input business", "forest land issue", "riverbank project", "pesticide launch".

  • Apify google events tracking

    johnisanerd/claude-skill-google-events-tracking/apify-google-events-tracking Skill

    no license0★ repo

    Track Google Events listings as structured JSON with the Apify Google Events Scraper Actor (johnvc/google-events-api---access-google-events-data). Give it a search query like concerts in Chicago plus an optional location and date filter, and get one row per results page with a nested events array, title, start_date, when, address, venue name and rating, ticket_info seller links, and image per event. Re-run the same input on a schedule and diff by event link to catch new or dropped listings. Use when the user wants google events tracking, wants to track or monitor Google Events for a city, venue, artist, or competitor, watch for new concerts, conferences, or festivals, or export Google Events results to JSON or CSV. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Cdp graphql scraper

    brightstone111/web-scraping-skills/plugins/web-scraping/skills/cdp-graphql-scraper Skill

    0★ repo

    Scrape data from sites you're authorized to access by attaching Playwright to your OWN already-logged-in Chrome over the DevTools protocol (CDP) and harvesting the JSON/GraphQL responses the page already fetches — instead of re-authenticating, driving login forms, or hammering endpoints directly. Use this whenever a task involves collecting structured data from a logged-in web app, building a resilient web scraper/collector, intercepting XHR/GraphQL/API responses, or when an existing scraper is getting rate-limited, soft-blocked, or returning empty results. Also reach for it for the operational side — running, resuming, or debugging a long crawl, or making one survive blocks and restarts. Covers the anti-block hygiene (human-paced delays, batch cooldowns, block-signal detection, resumable state) that naive scrapers miss.

  • Apple design

    reagin/agent-skills/skills/apple-design Skill

    no license0★ repo

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading), reduced-motion, or the design foundations (feedback, spatial consistency, restraint) behind Apple-style interfaces.

    The same file is in 5 other repositories

  • Sitesmith

    byensitmagnus/sitesmith/skills/sitesmith Skill

    0★ repo

    Design, build, redesign, audit and polish websites and web apps that do not look AI-generated. Use for landing pages, marketing sites, product and e-commerce pages, SaaS sites, dashboards, web apps, local business sites, portfolios and editorial sites, and for improving existing React, Next.js, Astro, Vue, Tailwind, shadcn or plain HTML/CSS projects. Triggers on: build a website, make a landing page, design a page, redesign this, make it look better, fix the design, improve the UI, this looks generic, choose colours or fonts, pick a style, add animations, make it responsive, add dark mode, accessibility pass, hero section, pricing table, dashboard layout, product page, component styling, design system, design review, UI audit.

  • Frontend gym

    BrettThurs10/frontend-gym Skill

    no license0★

    Run focused daily frontend programming workouts to build and maintain frontend fundamentals — implementation reps, planted-bug diff reviews, code review, and skill upkeep. Use when the user asks for a frontend drill, coding challenge, practice session, a diff with bugs or anti-patterns to review, review of a practice solution, hints, a learning plan, live-coding practice, or professional-readiness work involving HTML, CSS, JavaScript, TypeScript, React, Vite, browser APIs, accessibility, testing, performance, or frontend system design.

  • Ad copywriting frameworks

    gmmh1/claude-paid-media-skills/skills/ad-copywriting-frameworks Skill

    0★ repo

    Choose and apply persuasion copywriting frameworks — AIDA, PAS, BAB, FAB, 4Ps, StoryBrand, and psychological triggers — to any advertising message. Triggers on 'what copywriting framework should I use', 'apply AIDA to this ad', 'PAS structure for my copy', or 'which persuasion angle fits this product'. Platform-agnostic knowledge base feeding every platform's copywriting skill.

  • Google business profile optimizer

    SkillMedev/local-service-business-engine/skills/google-business-profile-optimizer Skill

    0★ repo

    Optimizes a Google Business Profile as the storefront of a local service business - primary category selection, service-area setup, weekly photo cadence, Q&A seeding, posts, and NAP consistency - ordered by ranking impact. Use when an owner asks "why don't I show up on Google Maps", "how do I set up my Google Business Profile", "what category should my business be", or "how do I get more calls from Google". Do NOT use for broader local ranking strategy across the website and citations - use local-seo-playbook instead. Do NOT use for review generation and responses - use review-engine instead.

    The same file is in 1 other repository

  • Claude skill

    fbenkstein/cross-agent-skills/claude-skill Skill

    0★ repo

    Drive the `codex` (OpenAI Codex) CLI as a local background worker — spawn it, inspect its progress, monitor its real token usage, resume/steer it, and forcibly kill it if it runs away — without using Codex Cloud. Use this whenever you'd otherwise reach for the `codex` MCP server's `codex`/`codex-reply` tools: both are fully synchronous (the calling turn blocks until Codex's whole turn finishes) with no background, list, kill, or cost-telemetry primitives at all. `codex exec`, backgrounded via the shell yourself, is the workaround. Also use when asked to check on, babysit, or kill a runaway/looping local Codex session.

  • Learn by building

    reezanahamed/learn-by-building Skill

    0★

    Turn "I want to learn X" into a ladder of 5 tiny projects with teach-back gates, for any topic (coding or not). Use when the user says they want to learn, understand, study, or get good at something, or asks to continue their learning ladder.

  • Apify baidu rank tracker

    johnisanerd/claude-skill-baidu-rank-tracker/apify-baidu-rank-tracker Skill

    no license0★ repo

    Track where a brand, domain, or competitor ranks on Baidu with the Apify Baidu Search Scraper Actor (johnvc/Baidu-Search-Scraper), built for China SEO. Run your keywords on a schedule, read each SERP page's nested organic_results (position, title, link), match your domain, and build a Baidu tracking history for rank checks, brand monitoring, and competitor watch in the Chinese market. Filters by device, Simplified or Traditional Chinese, and time period. Use when the user wants baidu tracking or baidu monitoring, a Baidu rank tracker or rank checker, to check keyword rankings on Baidu, to monitor a brand or competitor on the Chinese web, or China SEO reporting for a site. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify congress trading tracker

    johnisanerd/claude-skill-congress-trading-tracker/apify-congress-trading-tracker Skill

    no license0★ repo

    Build a congress trading tracker with the Apify Congress Financial Disclosures and Stock Trades Actor (johnvc/us-congress-financial-disclosures-and-stock-trading-data). Watch a member of Congress or a ticker, poll for newly filed Periodic Transaction Reports from the House and Senate, dedupe on the stable row id, and route new disclosures to alerts, a database, or a dashboard, with member, chamber, Ticker, Transaction_Type, Amount_Range, Date, and Filing_ID on every row. Use when the user wants a congress trading tracker, wants to track congressional stock trades over time, monitor a member's disclosures, watch which members trade a ticker, get alerts on new filings, or run disclosure monitoring for compliance, ESG, or journalism research. Pay-per-transaction billing, MCP-ready for Claude and other AI agents.

  • Apify investor database

    johnisanerd/claude-skill-investor-database/apify-investor-database Skill

    no license0★ repo

    Search a curated investor database of 10,469 firms with the Apify Startup Investors Data Scraper (johnvc/startup-investors-data-scraper). Filter by firm type (VC, angel, private equity, family office, accelerator, venture debt and more), industry focus, investment stage, country, and keyword, and get one row per firm with name, description, city, country, website, LinkedIn URL, AUM, stages, and focus areas, plus profile extras like Crunchbase and social links when on file, and partner contacts with job titles and check sizes when requested. Use when the user wants an investor database, a venture capital database, a list of venture capital firms, an angel investors list, a private equity firms list, or a Crunchbase or PitchBook alternative for investor data. Pay-per-firm billing, MCP-ready for Claude and other AI agents.

  • Inner outer monologue

    duncan806/inner-outer-monologue Skill

    0★

    Two-layer reasoning discipline (Inner_Monologue → Outer_Monologue → main body) for substantive analytical responses. Use this skill whenever a question is heavy, ambiguous, strangely phrased, or structural — anything where the framing itself might be the problem, where assumptions need surfacing before answering, or where the user asks for deep analysis, critique, review, hypothesis generation, or a second opinion. Also use when the user explicitly mentions, Inner/Outer monologue, or asks Claude to show its assumptions and gaps before answering. Do NOT use for light factual queries, translations, or execution-first tasks — for those, run the moves silently and skip the visible scaffolding.

  • Systemic

    gdavidpb/systemic Skill

    0★

    Systemic analysis of software based on General Systems Theory (GST): models a solution as systems (elements, operators, conceptual state machines) and verifies their consistency — closure, reachability, transition completeness, invariants, operator ambiguity, idempotency, symmetry, minimal expression and system limits — producing a local Markdown findings report with evidence, severity and recommendations. Use it whenever the user asks for a systemic analysis, wants to review the consistency of states or a state machine, find inconsistencies or contradictions in a design, flow or operation, audit a lifecycle (workflow, saga, state machine), apply systems thinking or GST/TGS, or asks "is my design consistent?" — even if they never say the word "systemic". Works on code, design documents, or both.

  • Skill

    JanKups/screen-list/skill Skill

    0★ repo

    Use when someone wants to visually review or capture their running web app across many pages at once — for design QA, a pre-launch or pre-demo look-over, a redesign or restyle check, or handing screens to a designer for feedback. Triggers on requests to screenshot, capture, or grab shots of every route/page/view/screen of a site or app (Next.js, Remix, React Router, SvelteKit, Astro, Vite, or a monorepo of apps) and collect them into one scrollable gallery to browse and comment on — typically full-page, at desktop and mobile widths, including dynamic routes and auth-gated pages. Not for single-page screenshots, component/Storybook shots, native iOS/Android/Expo app captures, Figma exports, terminal captures, or visual-diff regression tests.

  • Eliminate ai tone

    connect24h/eliminate-ai-tone Skill

    0★

    AI生成文章の「AIっぽさ」を除去し、人間が書いたような自然な日本語に書き換える。読み物・ビジネス・SNS・学術に対応。ペルソナ憑依・3段階校正・AI検出診断を搭載。

  • Powershell script reviewer

    maximsmd/powershell-script-reviewer/powershell-script-reviewer Skill

    0★ repo

    Senior-engineer / script-manager review of PowerShell scripts across Microsoft 365 and Windows admin — Intune/endpoint, Exchange Online, SharePoint (PnP), Microsoft Teams, Microsoft Graph/Entra ID, and general enterprise automation. Covers security, reliability, idempotency, execution-context correctness (SYSTEM, unattended, scheduled), exit-code contracts, and module/auth currency (flagging retired modules like MSOnline/AzureAD before they cause an outage). Use whenever a PowerShell script is written, pasted, reviewed, debugged, refactored, or prepared for deployment — Intune detection/remediation pairs, Platform scripts, Win32 app scripts, ConfigMgr, Exchange/Graph/PnP automation, scheduled tasks, or Azure Automation runbooks. Also use for "will this work", "is this safe to deploy", "why did this fail", or any pre-production check, even a quick one — scripts touching a whole tenant or fleet deserve the full review.

  • Dnd build

    mlabarrere/dungeons-and-skills/skills/dnd-build Skill

    no license0★ repo

    Dungeons & Skills — a grounded D&D 2024 (5.5) character-builder skill pack: the AI reads a bundled rules catalogue + deterministic engine instead of hallucinating.

  • Crypto news screener

    su-ekachai/skills/skills/finance/crypto-news-screener Skill

    0★ repo

    Screen and rank cryptocurrency news into an impact-scored report — deduplicated stories from tiered sources, each with affected coins, expected price direction, and a 1–10 impact score. Use when the user asks for "crypto news", "screen crypto news", "crypto market update", "what happened in crypto today", or runs a scheduled crypto news screen. Defaults are the last 12 hours, watchlist BTC/ETH/BNB/SOL/XRP, and top 10 stories, all overridable in the request. Reports in chat; writes a dated vault note on request.

  • Notes janitor

    olevasyliev/notes-janitor Skill

    0★

    Audits and reorganizes a user's Apple Notes archive on macOS - exports every note via Notes automation, classifies each one with a cheap model, produces a digest and a secrets inventory, and optionally re-sorts notes into folders. Use when the user asks to clean up, organize, audit, declutter, or "do something with" their Apple Notes / Notes.app archive.

  • Premortem plan check

    kalshamsi/fable-discipline-skills/evidence/cut-skills/premortem-plan-check Skill

    0★ repo

    Before finalizing any plan, run a premortem — assume the plan has already failed, list the likeliest causes, and reshape the plan with mitigations before presenting it. Use this whenever producing something that will be executed later: project plans, rollouts, proposals, timelines, migration or launch schedules, research plans, event logistics, hiring or content plans, implementation plans for code changes. Trigger even when the user just says "draft a plan", "give me a timeline", "how should we roll this out", or "propose an approach" without ever mentioning risk.

  • Cold email pl

    wysocki-lu/cold-email-pl Skill

    0★

    Pisanie zimnych maili B2B po polsku, które dostają odpowiedzi. Używaj przy prospectingu, mailach do potencjalnych klientów i follow-upach: właściwy rejestr (Pan/Pani zamiast kalki "Hey Marek"), krótkość, personalizacja z konkretem, jedno niskoprogowe CTA, polskie realia prawne. Adaptacja cold-email z marketingskills (Corey Haines, MIT) na polskie warunki.

  • Genomic prediction skill

    scicrow/genomic-prediction-skill Skill

    no license0★

    Execution blueprints and code templates for fitting genomic prediction models, including GBLUP, GFBLUP, MultiBLUP, Bayesian methods, and Random Forest using peer-reviewed software. Strictly incorporates robust self-auditing, high-clarity code commenting, big data performance safeguards, and strict matrix alignment rules.

  • Explain like im 10

    gitsukrit/claude-skills/explain-like-im-10 Skill

    0★ repo

    Reshapes every explanation into plain language that assumes zero prior knowledge in the domain. Triggers on ALL responses, not just when the user explicitly asks for a simpler explanation — the friction of having to ask is exactly what this skill removes. Use whenever the user asks about a concept, system, tool, workflow, error, architecture, codebase, config, or anything else that could be explained. Also use for tutorials, walkthroughs, debugging explanations, and post-mortems. Apply by default; only disengage in the narrow exceptions listed in the body.

  • Protocol qa

    thebitanpaul/VERA/.claude/skills/protocol-qa Skill

    no license0★ repo

    Answer a clinical-trial coordinator's question about what a protocol CURRENTLY requires — eligibility, concomitant medications, dosing, washout periods, visit timing — for a specific trial. Answers come only from the current governing protocol version, always with citations (trial, version, section, effective date), and disclose when a rule changed across versions. Use whenever a coordinator asks whether something is permitted, what a requirement is, or what changed. If the protocol does not cover the question, VERA abstains rather than guessing.

  • Design brainstorm

    hsiangyilu/claude-design-skills/skills/design-brainstorm Skill

    0★ repo

    AI設計部門核心技能 — 設計發想思考夥伴。當使用者要開始一個新功能/新產品的設計、還在「不知道該怎麼做」的最前期階段時使用此技能。AI 在這裡不是幫你畫圖,而是當你的「思考夥伴 + 辯論對手」:陪你把還沒想清楚的地方問清楚。流程為:抓資料 → 發想 3-5 個設計方向 → 評估可行性 → 混合式辯論優缺點 → 產出可直接使用的 Claude Design 原型提示。觸發情境:「我有個新功能要做,先幫我發想」、「陪我想一下這個設計怎麼做」、「幫我把方向辯一辯」、「我想開始設計但不知道從哪切入」、「幫我釐清這個功能該長怎樣」、「陪我 brainstorm 這個設計」、「這幾個方向哪個比較可行」、「幫我生一個可以拿去做原型的 prompt」。任何從「一個模糊的想法」到「想清楚、可以進 Claude 做原型」的思考階段,都屬於此技能。

  • Git patch workflow

    6543/git-patch-workflow Skill

    no license0★

    Generic workflow for implementing tasks on any git repo or provided file set and delivering verified git-format-patch files the user applies with git am. ONLY activate when user explicitly invokes with /git-patch-workflow or says "use git-patch-workflow". Do NOT auto-trigger on git URLs, repo mentions, patch requests, or coding tasks.

  • Quorum skill

    davidbrown1775/quorum-skill Skill

    0★

    Convene an advisory board of real, well-documented experts the user chooses, audit their already-launched product or business, and return a prioritized backlog, a roadmap, and a council-weighted prioritization framework. Use when the user asks for an expert audit or advisory board, a "council" or "board" of experts, help prioritizing a backlog or roadmap, a review of their product or go-to-market, or says "run quorum" or "/quorum". Built for post-launch, pre-scale builders who have something real in production. Not for the idea stage, and not for post-product-market-fit scaling.

  • Harden repos

    MrToAster13/mrtoaster13-plugins/plugins/autonomous-workflows/skills/harden-repos Skill

    0★ repo

    Harden several repos in one pass by fanning out one fresh-context sub-agent per repo. Each agent secret-scans, reviews, applies only verified-safe fixes on a branch (never pushing), and reports back; the orchestrator aggregates everything into HARDENING_HANDOFF.md. Use when the user says "harden my repos", "harden-repos", "clean up all my repos", "run hardening across the portfolio", or wants multi-repo cleanup without hitting context limits.

  • Nitpicker

    ege2734/nitpicker Skill

    0★

    Install the nitpicker in-app dev-feedback overlay into a React/Next repo. Use when a developer wants to visually mark up their running app (region screenshots with a red box, or click-to-pick an element's component/source) and batch-send that feedback straight to the AI coding session — with no hand-wiring. Installs a framework-agnostic overlay, a Next/React adapter, a dev-only source-stamp transform, and a local sidecar + `poll` CLI. Next.js (App Router) / React 19 target; dev-only and tree-shaken from production.

  • Gutcheck

    mhavelka77/gutcheck/skills/gutcheck Skill

    0★ repo

    Calibrates subjective quality against real human preference instead of a proxy metric. Serves a tiny local keyboard-driven rating UI over a directory of artifacts (audio wav/mp3, images, text snippets, HTML); the user gives 50-100 gut-reaction judgments in ~10 minutes, then it fits a preference model (mean ratings or Bradley-Terry) and writes calibration/scores.json as a personalized scorer the agent can optimize against. Use when optimizing a subjective target (audio pleasingness, visual style, text tone, UI feel), when a metric, model judge, or heuristic disagrees with what the user says they perceive, or when the user asks to rate, rank, A/B-test, or calibrate generated variants.

  • Brief

    ENEmyr/brief/skills/brief Skill

    0★ repo

    Use when research, analysis, review, or planning work ends in decisions a human must make (architecture choices, migration plans, incident reviews, dependency upgrades) and the findings are too large or too visual for chat. Publishes the work as an interactive document on Brief (https://brief.algoryth.me) that the human reads, annotates, and answers from, then replies back into the conversation.

  • Comiket kantei shi assessment

    saitoomituru/pain-scouter-assessment/comiket-kantei-shi-assessment Skill

    0★ repo

    同人誌市場・ギーク/ニート系創作コミュニティ・二次創作を含むインディー/ガレージ制作市場で起きる、配給元・プラットフォーム(棚)側の方針転換や淘汰圧による市場荒廃・ジャンル終焉系のペインを鑑定するスキル。「このジャンルは規制で終わった」「プラットフォームが締め出しを始めた」「二次創作ガイドラインが急に厳格化された」といった話題、棚選びの相談、淘汰圧への防壁構築、自前で棚を作る(棚フォーミング)検討の場面で使う。pain-scouter-assessment(工学的稼働評価)・narrative-marketing-assessment(ナラティブ/マーケ表現評価)とは別レイヤー。通称コミケ鑑定士。

  • Debug by bisection

    duliangkuan/cc-clone/examples/demo-brain/skills/debug-by-bisection Skill

    0★ repo

    Find the cause of a regression by systematically halving the search space (git bisect, feature flags, input reduction).

  • Api and interface design

    rabius-sunny/agent-skills/api-and-interface-design Skill

    no license0★ 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.

    The same file is in 14 other repositories

  • Net worth

    saverio87/net-worth/.claude/skills/net-worth Skill

    no license0★ repo

    Parses assets.md, queries local scripts, aggregates values in EUR, and exports a professionally styled, modern HTML/PDF dashboard using external templates.

  • Backend build

    muzalee/claude-atelier/skills/backend-build Skill

    no license0★ repo

    Implement the backend from a BACKEND_DESIGN.md brief — set up plugins, database, routes, tests, and wire everything into the server entry. Biased toward Fastify + Node. Use when user says "build the backend", "implement the server", "code the API from the brief", or after running /backend-design.

  • Build ready

    jovylle/build-ready/skills/build-ready Skill

    0★ repo

    Scores whether a spec/plan Markdown file is ready for a zero-context AI agent to build end-to-end WITHOUT asking a single question. Use when the user asks "is my spec/plan ready to build", "can an agent build this", "check PLAN.md before I start", "what's missing before autonomous build", "build-readiness", "will a builder agent get stuck on this spec", or wants a cold-build red-team of a PLAN/SPEC/PRD/DESIGN doc before dispatching it to autonomous builders.

  • Skill vetter

    micajxne/skill-vetter Skill

    0★

    Security-first skill vetting for Claude Code. Use this skill BEFORE installing any skill from GitHub, a direct file share, a zip, or any untrusted source. Reviews SKILL.md, bundled scripts, and resources for malicious patterns, excessive permissions, and suspicious code. Triggers on: "vet this skill", "is this skill safe to install?", "check this SKILL.md before I install it", "should I trust this skill?", "security review for skill", "scan this skill for red flags", "I found this skill on GitHub — is it safe?", or anytime someone wants to install a skill and safety is a concern. Always use this skill when asked to evaluate a skill before installation — don't just eyeball it.

  • Build reimbursement packets

    allenlee0430/allenlee-lab-skills/.claude/skills/build-reimbursement-packets Skill

    0★ repo

    Extract, reconcile, and package lab receipts, invoices, purchase orders, travel expenses, and grant-expenditure evidence into checked spreadsheets and ordered PDF packets. Use for University of Toronto reimbursements, vendor reconciliation, expense reports, PO matching, missing-document audits, and expenditure reporting.

  • Cash flow

    kelsi-bizer/bizer-ai-agent-skills/skills/cash-flow Skill

    0★ repo

    Answer the question that actually sinks small businesses — "do I have the cash, and when do I run out?" Works from whatever the owner can show you: an uploaded statement, pasted figures, or a few numbers in chat. Computes money in vs out, a monthly burn, runway against cash on hand, a safe-to-spend number, and a straight "can I afford this?" answer. Use whenever the user asks about cash, runway, whether they can afford a purchase, or whether they're going to be okay.

  • Aeo competitor gap

    KingForm242/claude-aeo/skills/aeo-competitor-gap Skill

    0★ repo

    Entity-level comparison of your content vs a competitor page ranking above you: missing entities, data points, FAQ coverage, depth and structure deltas, with impact-ranked gap report. Use when user says competitor gap, why do they outrank me, content gap, or compare pages.

  • Ai crawler check

    meturley/trail-marker-geo/skills/ai-crawler-check Skill

    0★ repo

    Diagnose whether a website is accidentally blocking AI search crawlers (GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-SearchBot, Claude-User, PerplexityBot, Perplexity-User, Google-Extended). Use this whenever a user asks if AI can read/find/cite their site, whether ChatGPT or Claude or Perplexity can see their pages, why their site isn't showing up in AI search or AI answers, or asks to check/audit their robots.txt for AI or LLM crawler access. Trigger it for phrases like "can ChatGPT read my site", "is my site blocking AI", "check my robots.txt for AI crawlers", "why don't I show up in AI search", or when someone shares a campaign/business URL and worries about AI visibility. Diagnostic only — it inspects robots.txt and headers and reports findings plus a suggested fix; it never modifies the user's site.

  • Support inbox agent

    sitespeakai/support-inbox-agent Skill

    0★

    Use when doing the daily support-inbox pass - checking the support chatbot inbox for new visitor issues and questions and preparing personalized email drafts for human review. Triggers on "/support-inbox-agent", "support inbox pass", "draft support replies".

  • Copy paste via file

    cobuchan/compounding-operator/skills/copy-paste-via-file Skill

    0★ repo

    Whenever the assistant needs the user to copy-paste a command, code snippet, prompt, or any text where chat-rendered formatting could mangle line wrapping, regex literals, or string contents (e.g. DevTools console one-liners, terminal commands with quoted JSON, long URLs, multi-line prompts), write the exact text to a file and open it so the user can copy it clean. Use whenever the assistant is about to say "paste this command into..." or similar, especially for browser DevTools console pastes, complex shell commands, or anything containing regex literals, escaped quotes, or backticks.

  • Meta prompt toolkit

    hmbseaotter/meta-prompt-toolkit Skill

    0★

    Use when the user wants help writing, generating, or improving a prompt for an LLM - e.g. "write me a prompt for...", "turn this into a prompt", "help me prompt for...", "improve this prompt", or when they hand over a use case and want a polished, reusable prompt back. Produces a finished, copy-ready prompt (not advice about prompting). Also applies when the user references the CoSTAR framework or asks for a prompt built to a named structure.

  • Spec architect

    DahanItamar/flowsystem/plugins/flowsystem/skills/spec-architect Skill

    0★ repo

    Turn a rough product idea into an engineering-grade Technical Spec — architecture, data models, interfaces, edge cases, and risks — before any code is written. Use when someone describes something they want to build ("I want an app that…", "I'm thinking of building…", "how should I structure a…"), asks for a PRD, tech spec, architecture doc, system design, data model, or stack recommendation, or is starting a new project or major feature from only a loose description. Also use to reverse-engineer a spec from an existing codebase before a large change. Produces one Markdown file meant to live in the repo and be loaded as project context.

  • Aeo site audit

    rikocr8orh8/compliance-skills-previews/skills/aeo-site-audit Skill

    0★ repo

    You can be found by an AI assistant and still be unusable to it.

  • Apify yandex rank tracker

    johnisanerd/claude-skill-yandex-rank-tracker/apify-yandex-rank-tracker Skill

    no license0★ repo

    Use this as a yandex rank tracker. Check where a domain or URL ranks on Yandex for a keyword, in a specific Yandex domain, language, and lr region, using the Apify Yandex Search per-result Actor (johnvc/yandex-scrape-yandex-search-results-at-scale---per-result). Each run returns ranked organic rows with position, title, link, displayed_link, and snippet, so you match your site against the SERP and log the position with the run timestamp for a rank history. Use when the user wants a yandex rank tracker or yandex rank checker, wants to check Yandex rankings or keyword positions, wants yandex tracking of a site across Moscow, Saint Petersburg, or other regions, or wants to monitor Russian-market SERP positions over time on a schedule. Pay-per-result billing, MCP-ready for Claude and other AI agents.

  • Study notes

    LuoHaomin/study-notes Skill

    0★

    Process learning materials (PDFs, slides, lecture notes) into structured study notes. Generates per-chapter study notes, course overview with dependency graphs, exam-point summaries, and practice problems. Uses a two-pass "segment-summarize-synthesize" pipeline to handle large files that exceed context. Make sure to use this skill whenever the user mentions: 整理笔记, 生成复习笔记, study notes, process slides, 整理课件, 生成练习题, 提取考点, 复习大纲, 或者要处理 PDF 学习材料。

  • Srib design

    sayonsom/srib-godot-skills-demo/.claude/skills/srib-design Skill

    0★ repo

    Implement design-layer features in the SRIB Godot 4.6 Android app — UI layout, theme resources, color palette, typography, spacing, control-node composition, navigation flow, onboarding copy, and accessibility (TalkBack). Use when a feature is about how the user encounters and reads the interface. Do NOT use for 3D scene rendering (srib-view) or animation math (srib-model). Typically invoked after srib-triage classifies a feature as "design".

  • Donor communications

    SkillMedev/nonprofit-grants-toolkit/skills/donor-communications Skill

    0★ repo

    Builds a small nonprofit's individual-donor communication system - segmenting donors into major, recurring, first-time, and lapsed with different treatment for each, thanking within 48 hours of every gift, structuring impact stories around one beneficiary with the donor as hero, writing appeal letters, and holding a 3:1 impact-to-ask calendar ratio. Use when a nonprofit leader says "our donors are lapsing", "write our year-end appeal", "how often should we email donors", "write a thank-you letter for a major gift", or "we only contact donors when we ask for money". Do NOT use for winning back lapsed donors with a full re-engagement sequence - use win-back-campaign for the sequencing mechanics - and do NOT use for foundation funder communications - use grant-loi-writer instead.

    The same file is in 1 other repository

  • Fear of abandonment

    jagp/claude-session-guardrails/fear-of-abandonment/skills/fear-of-abandonment Skill

    0★ repo

    Scan the current git repo for stranded agent work — worktrees, branches not merged into the integration branch (develop/main), and worktrees holding uncommitted changes. Use when you suspect work happened in a worktree or background session but never got merged, or to audit before deleting worktrees.

  • Finance fx

    SkillMedev/live-data/skills/finance-fx Skill

    0★ repo

    Use when a task needs live or historical money data - "convert USD to EUR", "current/past exchange rate", "FX rate on this date / over this range", or "current price of Bitcoin/Ethereum, market cap, 24h change". Frankfurter (ECB reference rates, no key) is the FX default; CoinGecko's free keyless tier covers crypto. Do NOT use for stock quotes or equities - no keyless stock API survives verification, say so instead of guessing; do NOT use for country economic indicators like GDP or inflation series - use government-open-data instead; if the request is a vague "I need live data", route through public-data-api-picker.

    The same file is in 1 other repository

  • Text humanizer

    Skillproofdev/text-humanizer Skill

    no license0★

    Use when the user asks to humanize a text, says a draft "sounds like AI" or "reads like ChatGPT", wants text to "sound human/natural", worries about AI detection, or asks to edit/clean an AI-generated draft — blog posts, emails, product copy, docs, posts, any language. Rebuilds the prose in a human voice while keeping every fact, number, name, quote, and caveat exactly intact. Do not trigger for writing new content from scratch, for translation jobs, or for non-text tasks (code, images, audio).

  • Life insurance recommender

    daichupeng/life-insurance-recommender Skill

    no license0★

    Recommend and assess life insurance policies for a Singaporean user by interviewing them about their coverage needs (who benefits — themselves, a dependent, or as a legacy — and for how long), checking their reasoning is consistent, decoding candidate policies from a local policy bank against a suitability scorecard, and generating an interactive HTML report. Use this whenever the user asks about buying life insurance, term life vs whole life, critical illness cover, how much coverage they need, whether a specific policy is a good fit, or wants to compare insurance product summaries/PDFs (e.g. Prudential, Income Insurance, AIA, Great Eastern policy documents). Trigger even if they only upload a policy PDF and ask "is this good for me" without using the word "skill."

  • Dialogic reading

    bellaleng/dialogic-reading-skill/dialogic-reading Skill

    0★ repo

    Turn any book into a structured, conversational reading program — plan the read, deliver one short reading prompt at a time (location + vocabulary + focuses + a single question), capture the reader's answers verbatim, and keep the plan, progress, notes, and stage summaries as Markdown files. Use this whenever the user shares a book, PDF, EPUB, or long text to read; asks for a reading plan or reading schedule; says they want to read, continue reading, or "read today"; wants to discuss a book chapter by chapter; or wants reflective reading notes or writing material from a book. Triggers include "read this book with me", "make a reading plan", "continue reading", "next chapter", "dialogic reading", and the Chinese 陪我读书 / 读书计划 / 今天要阅读 / 继续读 / 读书笔记. Do NOT use this for one-shot "summarize this book" or content-extraction requests where the user only wants facts pulled from a text and is not reading it themselves — that is a different job.

  • Automerge

    NasserAlbusaidi/ship-gate/skills/automerge Skill

    0★ repo

    Review-gated auto-merge for Rihla PRs. Classifies a PR's diff; Gate-exempt PRs (docs, token sweeps, one-sentence diffs) get GitHub native auto-merge enabled immediately so they merge on green `readiness`. Gate-category PRs (money math / firestore.rules / Cloud Functions auth / routing / schema-field-name) get a fresh-context Opus diff review, then an independent refuter, and auto-merge is enabled ONLY if both clear. Use when asked to "auto-merge this PR", "/automerge <N>", or under /loop to sweep open PRs.

  • Idea to spec

    HelloWorldU/skill-collection/skills/idea-to-spec Skill

    0★ repo

    Turn a vague idea into a concrete, actionable spec through structured dialogue — disambiguating requirements, surfacing decision points, and probing technical feasibility before any code is written. Use when the user brings an open-ended or half-formed idea ("I want to build...", "what if we...", "help me create...") and the shape of the thing is not yet clear. Converges into an approved spec, after which concrete modification tasks should go through task-intake, and unfamiliar-codebase investigation through progressive-abstraction. Do not write code inside this skill — producing the aligned spec and getting it approved is the entire deliverable.