agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Apify flight price api

    johnisanerd/claude-skill-flight-price-api/apify-flight-price-api Skill

    no license0★ repo

    Collect current airfares by route with a flight price api built on the Apify Google Flights Actor (johnvc/Google-Flights-Data-Scraper-Flight-and-Price-Search). Give routes and dates and get structured fare rows back, price, currency, airlines, stops, duration, plus route-level price insights (lowest price, price level, typical price range), ready to export, compare across dates, or poll on a schedule for price monitoring. Use when the user wants a flight price api, airfare data by API, to compare fares across dates or airports, to build a flight price dataset, or to watch a route's fares over time. Current quotes only, honestly framed, no fare forecasts and no reservations. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify google maps directions api

    johnisanerd/claude-skill-google-maps-directions-api/apify-google-maps-directions-api Skill

    no license0★ repo

    Get Google Maps directions as structured JSON with the Apify Google Maps Directions API Actor (johnvc/google-maps-directions-api). Give a start and end point as an address, GPS coordinates, or a Google Maps place ID, pick a travel mode (best, driving, cycling, walking, transit, flight, two-wheeler), and get route options back with formatted_distance, formatted_duration, a via summary, turn-by-turn steps, a per-mode durations summary, resolved place coordinates, and a google_maps_directions_url. Use when the user wants a google maps directions api, route data as JSON, distance and ETA between two addresses, turn-by-turn directions inside a script or agent, or directions without a Google Cloud API key. Pay-per-route billing, MCP-ready for Claude and other AI agents.

  • Supervisory analyst skill

    michael7908/supervisory-analyst-skill Skill

    0★

    Review investment research and financial content the way a FINRA Series 16 Supervisory Analyst would before publication. Use this skill whenever the user asks to review, check, approve, or improve an equity research report, investment analysis, stock commentary, price target rationale, financial newsletter, or any public-facing investment content — in English or Chinese — even if they don't mention "Series 16", "compliance", or "supervisory analyst" explicitly. Also use when the user asks "can I publish this?", "is this compliant?", or wants their investment writing to meet professional sell-side standards.

  • Done means done

    unclecatvn/done-means-done/done-means-done Skill

    0★ repo

    Top-tier execution discipline — apply to EVERY multi-step action task, regardless of domain: writing code, fixing bugs, refactoring, data analysis, drafting documents, system configuration, file processing. Use this skill whenever the user ASSIGNS WORK that must be carried to completion (build, write, fix, create, run, check, analyze, merge, convert), even if they never ask for care, proof, or thoroughness. Especially important when the running model is not Fable 5. Do NOT use for single-step knowledge questions or casual conversation.

  • Caveman

    lankyjo/lankyjo-core-skills/skills/code/caveman Skill

    no license0★ repo

    Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

    The same file is in 16 other repositories

  • Notemd knowledge graph

    a-aigner/notemd-skills/skills/notemd-knowledge-graph Skill

    0★ repo

    Use when the user asks about notemd's graph view, knowledge graph, backlinks, connections between notes, or "argument maps", or when reasoning about how notemd notes relate. Explains that notemd's graph is derived (not an authorable file) and that argument maps are read-only AI output that must not be fabricated.

  • Spec loop

    aelhady03/spec-loop Skill

    0★

    Turns a raw user story into shipped, reviewed code through a bounded loop — grill it for gaps, write a spec, plan it, split it into small PR-sized tasks with tests-first, implement autonomously, and adversarially review before merge. Use when a user hands you a feature request, ticket, or user story and no spec/plan exists yet, or when they ask to "plan this properly," "spec this out," or want autonomous implementation with review gates instead of ad-hoc prompting.

  • Deckle paper

    SamsShow/deckle-paper Skill

    0★

    Design direction and taste orchestration for building UI in canvas tools (Paper, Figma) and frontend code. Use when designing or redesigning a landing page, website, app screen, dashboard, component, or brand surface, when the user asks to make something look good, premium, distinctive, or less generic, when choosing a visual direction or aesthetic, or when reviewing a design for AI-slop tells. Composes the installed taste skills (design-taste-frontend, gpt-taste, high-end-visual-design, minimalist-ui, industrial-brutalist-ui, userinterface-wiki) into one direction-first workflow with a screenshot critique loop. Not for backend code, API design, image generation, copywriting in isolation, or accessibility audits without visual work.

  • Mindmesh skill

    ShivamGoyal03/mindmesh-skill Skill

    no license0★

    Transform unstructured knowledge from conversations, research, URLs, ideas, screenshots, and other sources into structured, searchable personal knowledge. Use when capturing, organizing, enriching, connecting, updating, or retrieving knowledge through the MindMesh knowledge system.

  • Cold email personalizer

    buildwithreef/claude-skills/skills/cold-email-personalizer Skill

    0★ repo

    Researches a prospect and writes short, personalized cold emails using proven frameworks (observation → implication → question, PAS), plus a three-touch follow-up sequence. Use when the user wants to write a cold email or outreach message, personalize outreach to a specific business, or says "write a cold email to this company" or "help me reach out to this prospect".

  • Coaching cost calculator

    marian-kamenistak/coaching-cost-calculator Skill

    0★

    Use when someone asks how much a coach should cost, what a fair rate for executive, leadership, career, or life coaching is, whether a coach's quote is overpriced or suspiciously cheap, or how much to budget for a coaching engagement in the US, UK, Western Europe, or Central and Eastern Europe.

  • Food scout

    skandm/trip-planner-template/.claude/skills/food-scout Skill

    0★ repo

    Recommend 2-3 vetted meal options grounded in profiles/travelers.md. Trigger when the user asks about food, restaurants, or where to eat for a trip or location ("where should we eat tonight in Denver"), when a planning phase reaches food scouting (travelers -> route -> stays/food -> itinerary), or when trips/<trip>/trip.md has a food item marked "_to scout_" or "_candidate: ..._" (a lightweight pick route-planner seeded while comparing routes). Filters out anything violating a hard constraint (allergy, medical, religious dietary law), ranks survivors by soft preferences, and explains why each pick fits. Works standalone with no active trip file too.

  • Battlecard

    tga-cheetung/competitive-intel-engine/.claude/skills/battlecard Skill

    0★ repo

    Turn a tracked competitor's profile + live sources into a 6-section, rep-ready, fully-cited battle card. Triggers: 'battle card', 'battlecard', 'build a battle card for', '/battlecard'.

  • Adversarial review

    lesue1/adversarial-review Skill

    0★

    The builder is the worst reviewer. When the user finishes writing code, adding a feature, fixing a bug, or says "review this"/"check my code"/"looks good?", spawn a FRESH subagent with ZERO context from the build session. The subagent's job is adversarial: assume every line is wrong until proven correct. Only report findings that can be reproduced with concrete inputs. Do NOT trigger for trivial changes (typos, comments, formatting only).

  • Blurb writer

    DeltaCorvi/Claude-Skills-for-Smart-Crows/blurb-writer Skill

    0★ repo

    Write promotional blurbs for live talks, presentations, or webcasts, following a fixed hook/beginning/middle/climax/end structure in exactly five sentences. Use this skill whenever the user asks for a promo blurb, teaser, or promotional description for a talk, session, webinar, conference presentation, or webcast, or asks to promote/hype up an upcoming talk or speaker. Also use it if the user references "the promo blurb format" or wants an event description that builds excitement and entices people to attend.

  • Think trail

    fengqiyiping/think-trail Skill

    0★

    深度讨论的协作技能——陪你想清哲学/系统/设计问题。能在跳跃思维中接住闪现灵感、不被带偏、保证讨论质量、结束时记录好内容和关键细节。当用户想头脑风暴、探讨某个问题、做顶层哲学或机制设计、说"开始讨论""我们聊聊""探讨一下""我想想"某个开放话题时触发——即使用户没明说"think-trail"。维护一张外部线索地图,像拿着地图的导游,走偏也能回主路。

  • Apify duckduckgo scraper

    johnisanerd/claude-skill-duckduckgo-scraper/apify-duckduckgo-scraper Skill

    no license0★ repo

    Scrape DuckDuckGo search results into structured JSON with the Apify DuckDuckGo Scraper Actor (johnvc/DuckDuckGo-Scraper-for-serp-rankings). One query returns a page item holding organic_results rows with position, title, link, snippet, favicon, and a date when DuckDuckGo shows one, plus page metadata and slots for ads, knowledge graph, news, inline images, inline videos, and related searches. Localize across 42 region and language codes, filter by date, set safe search, and cap pages to control spend. Use when the user wants a duckduckgo scraper, duckduckgo scraping, DuckDuckGo search results as JSON or CSV, a DuckDuckGo SERP export, or a keyless way to read DuckDuckGo from code. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify app store optimization reviews

    johnisanerd/claude-skill-app-store-optimization-reviews/apify-app-store-optimization-reviews Skill

    no license0★ repo

    Mine Apple App Store reviews for app store optimization signals with the Apify Apple App Store Reviews API Actor (johnvc/apple-app-store-reviews-api). Pull most-critical and most-recent reviews for your app and competitor apps across 52 country stores, then turn the rows into complaint themes, rating trends by reviewed_version, and per-country feedback that feeds listing updates and release notes. Use when the user wants app store optimization insight from reviews, an ASO review audit, competitor app review analysis, review sentiment for an iOS app, to find out why users leave 1-star reviews, or to check how an app update changed the reviews. Review mining only; keyword rankings belong to the Apple App Store Search Actor and listing metadata to the Product API Actor. Pay-per-review billing, MCP-ready for Claude and other AI agents.

  • Apify gas prices api

    johnisanerd/claude-skill-gas-prices-api/apify-gas-prices-api Skill

    no license0★ repo

    Turn live US fuel prices into a gas prices API with the Apify Fuel Prices Scraper Actor (johnvc/fuelprices). Give a ZIP code, city, or GPS coordinates plus a fuel type (Regular, Midgrade, Premium, Diesel, E85, Unleaded88) and get one row per station with name, address, starRating, ratingsCount, cash and credit prices, and the time each price was posted. Use when the user wants a gas prices api, fuel prices api, gas price api, gas prices by zip code, real time gas prices as JSON or CSV, gas price data for an app or pipeline, or per-station fuel price extraction. Pay-per-result billing, MCP-ready for Claude and other AI agents.

  • Security audit

    ayman-benmada/owasp-security-audit/skills/security-audit Skill

    0★ repo

    Performs a complete application security analysis based on the OWASP Top 10 (2025). Use this skill whenever the user mentions: security audit, OWASP analysis, security code review, application vulnerabilities, application pentest, security review, security flaw, API security, code verification, hardening, or asks to verify the security of code, an architecture, or a configuration. Also trigger for terms such as: SQL injection, XSS, CSRF, weak authentication, secrets in code, sensitive data exposure, access control, SSRF. This skill orchestrates 10 OWASP category reference guides and produces a structured, actionable report.

  • Fixture immutability

    SeamStressDev/seam-scaffold/skills/fixture-immutability Skill

    0★ repo

    Use this protocol whenever a test fails after a change, whenever editing test files, test fixtures, expected outputs, snapshots, or scoring criteria, and whenever the temptation exists to make a red check green by touching the check instead of the code.

  • Analyze first skill

    callahkate/analyze-first-skill Skill

    0★

    Enforces a strict analysis-before-synthesis discipline rooted in human-centered design (HCD) methodology. Trigger this skill whenever the user shares research data of any kind — interview notes, transcripts, survey responses, observation notes, JTBD artifacts, usability findings, discovery outputs, or any qualitative or quantitative research material. Also trigger when the user says phrases like "analyze this," "slow down," "let's be methodical," or "don't jump ahead." If the user shares research data WITHOUT specifying a goal or workflow, always pause and ask whether they want analysis or synthesis mode before proceeding. Never skip to synthesis, conclusions, recommendations, ideas, concepts, action items, or next steps without explicit user permission. This skill has two mandatory gates: (1) confirm all data is collected before beginning analysis, and (2) ask permission before moving into synthesis.

  • World first

    88plug/world-first/skills/world-first Skill

    no license0★ repo

    Use when the goal is to produce and defensibly claim a genuine world-first, invention, novel algorithm/protocol/kernel/mechanism, or "nobody has done this" capability — and to prove the claim rather than assert it. Triggers on intent like "invent", "world-first", "first-ever", "beat the incumbent with something new", "break all dogma", "is this novel?", "prove this is new", or any push to build a mechanism a competitor structurally cannot. Also use to audit an in-flight "first" claim for overclaim before it ships, is committed, benchmarked-for-publication, or sent externally. This is the packaging of the INVENTION PLAYBOOK: confirmed-limit entry → TRIZ ideation → the removed-constraint test → refute-then-build vs a tuned baseline → provenance search → certify → kill failure modes. Reach for it by default on invention and novelty-claim work; skip only for routine feature work with no novelty claim attached.

  • Humanize writing

    n-eriksson/humanize-writing/skills/humanize-writing Skill

    0★ repo

    Rewrite or generate prose so it reads as natural human writing instead of obviously AI-generated text. Use when the user asks to humanize, de-AI, or un-robotify a text, and proactively whenever drafting substantive prose the user will publish or send (essays, blog posts, articles, emails, reports, marketing copy, bios).

  • Teach ai

    Henriquepb22/teach-ai/teach-ai Skill

    0★ repo

    Teach.ai — turns AI-assisted coding into active learning. Instead of writing explanatory comments, ask the engineer to explain what was just implemented, grade the answer, and award XP toward levels, streaks, and per-concept mastery. Use this skill on any task where you write, edit, refactor, or debug code for the user, even if they never mention learning, teaching, quizzes, or XP — it changes how you document and hand off code by default. Also use it when the user asks about their progress, XP, level, streak, learning journal, progress card, weak concepts, or wants a review session, or when they invoke the skill directly (e.g. /teach-ai status).

  • Session audit

    youkistudios/session-save-system/skills/session-audit Skill

    0★ repo

    Audit source-attributed Session Save records across Claude Code and Codex, grouped by project, into one local weekly report. Use when the user asks what happened this week, what remains open, or what to do next.

  • Helpnest author

    babble-open-source/helpnest-skills/skills/helpnest-author Skill

    no license0★ repo

    Author or update customer-facing help-center articles in HelpNest via its MCP server. Use whenever the user wants to write, publish, refresh, or fix help articles, help-center docs, knowledge-base content, support articles, or FAQ content for HelpNest — or when they ask "what should I document", "close the learning loop", or "what are customers asking that we can't answer" (knowledge gaps). Handles workspace verification, collection lookup/creation, idempotent create-or-update, draft-vs-publish decisions, code-grounded UI labels, and concurrency-safe editing. Trigger this even when the user only names the article topic (billing, notifications, onboarding) without saying "HelpNest" or "help article", as long as the destination is the HelpNest help center. Not for developer/engineering docs, READMEs, API references, or internal wikis.

  • Apify hotel price monitoring

    johnisanerd/claude-skill-hotel-price-monitoring/apify-hotel-price-monitoring Skill

    no license0★ repo

    Run hotel price monitoring on Google Hotels with the Apify Google Hotels Search Scraper Actor (johnvc/google-hotels-search-scraper). Poll the same destination and stay dates on a schedule, snapshot rate_per_night and total_rate per property with numeric extracted values, then diff snapshots keyed on property_token to alert on drops, watch competitor hotel rates, or chart how prices move as the stay date approaches. Use when the user wants hotel price monitoring, wants to track or watch hotel prices over time, monitor competitor hotel rates for a property or market, build a rate drop alert pipeline, or asks whether hotel prices go down closer to the date. Pay-per-page billing plus a small per-run setup fee, MCP-ready for Claude and other AI agents.

  • Apify bulk job listings export

    johnisanerd/claude-skill-bulk-job-listings-export/apify-bulk-job-listings-export Skill

    no license0★ repo

    Export Google Jobs listings to CSV, Excel, Sheets, or JSON in bulk with the Apify Google Jobs Scraper API Pay Per Result Actor (johnvc/google-jobs-scraper---pay-per-result). Output is already flat, one row per opening, so a dataset export drops straight into a spreadsheet or a database load with no reshaping. Covers multi-query batches, exclusion filters that shrink the file and the bill together, and job_id dedupe across runs. Use when the user wants to export google jobs to csv, download job listings as a spreadsheet, build or backfill a job board, load openings into a warehouse or ATS, or bulk export job postings for many roles and cities at a known cost. Pay-per-result billing, MCP-ready for Claude and other AI agents.

  • Apify yandex scraper bulk serp

    johnisanerd/claude-skill-yandex-scraper-bulk-serp/apify-yandex-scraper-bulk-serp Skill

    no license0★ repo

    A yandex scraper for bulk SERP collection where the bill is predictable, powered by the Apify Yandex Search per-result Actor (johnvc/yandex-scrape-yandex-search-results-at-scale---per-result). Run a keyword list through Yandex across 6 domains, 19 languages, and any lr region, and get structured items back with organic rows (position, title, link, displayed_link, snippet) plus optional ads, knowledge graph, and inline media, each result type billed as its own item so you pay only for what you collect. Use when the user wants a yandex scraper, wants yandex data or Yandex search results as JSON or CSV in volume, wants to scrape many Yandex queries at scale, needs a per-result cost model instead of per-run fees, or is building a Russian-market SERP dataset. Pay-per-result billing, MCP-ready for Claude and other AI agents.

  • Apify job search api

    johnisanerd/claude-skill-job-search-api/apify-job-search-api Skill

    no license0★ repo

    Turn Google Jobs into a job search API for your app, AI agent, or alerts pipeline with the Apify Google Jobs Scraper Actor (johnvc/Google-Jobs-Scraper). Query by role and location with country, language, and radius filters, and get fresh structured listings back, including title, company_name, source platform, posted_at, schedule_type, and direct apply_options links, ready to dedupe by job_id and serve as a feed. Use when the user wants a job search api, a job postings API or job listings feed for an application or AI agent, wants to refresh a job board or job alerts programmatically, or asks which job search sites have an API. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Blog refresh optimizer

    aarushibhatt-cloud/blog-refresh-optimizer Skill

    no license0★

    Audits and optimizes EXISTING, already-published Acquia blog posts — historical content optimization, not new content. Takes a URL (or a batch) plus its performance data (GSC, GA4) and produces a triage decision (Keep / Refresh / Consolidate / Repurpose / Retire), then a section-by-section refresh plan: on-page fixes, freshness/accuracy updates, content gaps, internal links, CTR, a GEO/AI-search retrofit, and cannibalization checks. Pulls data itself from Porter/Supermetrics, the live SERP, Conductor, and Screaming Frog. TRIGGER on "optimize old blog posts", "refresh content", "update an old post", "historical optimization", "content decay", "why did this post drop", "should we update or delete this", pasting an existing URL to improve, or a content-audit batch of published URLs. Do NOT use for planning a brand-new post — that is blog-seo-content-brief. Repetitive, high-volume task; default to producing the plan, not a long questionnaire.

  • Api endpoint

    syniol/llm-software-project/.agent/skills/api-endpoint Skill

    0★ repo

    Instructions for creating REST API endpoints following conventions, validation, and documentation standards.

  • Remove breath gaps

    wcy4213/remove-breath-gaps Skill

    0★

    去气口——自动检测并压缩口播音频中句与句之间的气口/换气声/静音停顿,让节奏紧凑起来。当用户说"去气口""去掉气口""剪气口""把停顿剪掉""去掉呼吸声/换气声""句间空隙太长""节奏太拖/让节奏快起来""压缩口播的停顿",或提供一个口播音频文件(mp3/wav/m4a等)要求加快节奏、剪紧凑时,务必使用本 skill。采用不对称保留策略(句尾留短、句首留长缓冲),保证下一句的起始音不被切掉。只处理纯音频,不处理视频文件。

  • Prelaunch test audit

    wlh26/test-VideCoding/prelaunch-test-audit Skill

    0★ repo

    Use when a project is preparing to launch, release, deploy, go live, or needs 涓婄嚎鍓嶆祴璇? 鍙戝竷鍓嶆鏌? 鍥炲綊娴嬭瘯, 鎺ュ彛瀹夊叏娴嬭瘯, release readiness review, production readiness, or a Go/No-Go launch decision.

  • Skill feedback

    bstegemoller/skill-feedback Skill

    0★

    Capture structured feedback when a skill misfires, so it can be reported upstream to the skill's maintainer. Use this whenever a loaded skill's instructions turn out to be wrong, stale, incomplete, or ambiguous during a task; whenever you have to work around a skill's guidance to finish the job; whenever a script or reference bundled with a skill fails; or whenever the user says anything like "that skill didn't work," "report this," "the skill got that wrong," or "how do I give feedback on this skill." Also use it proactively at the end of a task if you noticed skill friction along the way, even if the user didn't mention it.

  • Raporty po ludzku

    wysocki-lu/raporty-po-ludzku Skill

    0★

    Komentarze do raportów marketingowych dla klienta (Google Ads, Meta Ads, SEO, social media), które czyta się jak od specjalisty, nie od generatora. Używaj przy pisaniu podsumowań wyników, komentarzy do raportów miesięcznych i sekcji rekomendacji: perspektywa Państwa, fakt + liczba zamiast koloryzowania, każda rekomendacja z liczbą, zgodność treści z platformą raportu.

  • Worker budget

    esummervill/worker-budget/skills/worker-budget Skill

    0★ repo

    Use BEFORE spawning any Agent worker for substantial work (builds, audits, releases). Deterministic budget analysis — pricing snapshot, per-worker-class token forecast from observed history, tier recommendation, and a worker contract with success thresholds + orchestrator-escalation triggers. Also use when the user asks about worker costs, budget analysis, or model-tier selection.

  • Code review

    jacobjustin8/skill-forge/examples/code-review Skill

    0★ repo

    Review code changes — pull requests, diffs, commits, or a pasted snippet — the way a sharp, respected senior engineer would: prioritizing what matters, catching real defects, and improving the codebase without nitpicking the author into the ground. Use this whenever the user asks you to review, critique, look over, "check", give feedback on, or approve/reject code or a PR/MR/diff, whether they paste code, link a change, or ask "what do you think of this implementation?" — even if they don't say the words "code review". Also use it when someone wants help deciding whether a change is safe to merge or how to give review feedback well. Produces a prioritized, actionable review, not a vague thumbs-up.

  • Fanout cve iteration loop

    omonuj/claude-horizon-skills/skills/fanout-cve-rollout/fanout-cve-iteration-loop Skill

    no license0★ repo

    Orchestrator skill that runs the full push → Oracle → live red-team → rollout → tune cycle for the fanout-cve-rollout task (<TASK_ID>) until Oracle scores 1.0 and the 5 reward-shaped subscores form a dense, correct partial-credit gradient. Delegates to fanout-cve-task-guardian, fanout-cve-validation-debugger, fanout-cve-score-tuner, and horizon-agentic-reviewer. The agent executes every step except triggering the rollout batch.

  • Tree ring memory skill

    TerminallyLazy/tree-ring-memory-skill Skill

    0★

    Guides AI agents in using Tree Ring Memory for durable recall, project decisions, user preferences, warnings, future seeds, privacy-safe memory capture, and lifecycle-aware forgetting.

  • Fable mode

    amanlakra-art/fable-mode/fable-mode Skill

    0★ repo

    Activate Fable-class operating discipline on any model (Sonnet/Opus/Haiku). Encodes how Anthropic's Mythos-class Fable 5 operates — task-adaptive routing, verify loops, agent orchestration, adversarial self-checks, outcome-first communication. Use when the user invokes /fable-mode, asks for maximum-quality execution, or asks about Fable/Mythos capabilities. Persists for the whole session.

  • Cloudflare use

    hsjinde/cloudflare-use-skill/cloudflare-use Skill

    0★ repo

    Query and modify Cloudflare D1 databases and R2 object storage from any project, fast and Windows-safe. Use whenever the user asks to check or query a D1 database, run SQL against Cloudflare, upload/download/list/delete R2 objects or buckets, verify data stored in Cloudflare, or reaches for wrangler d1/r2 commands. 只要使用者提到查 D1 資料庫、跑 SQL、上傳/下載/檢查 R2 檔案、驗證 Cloudflare 上的資料,就用這個 skill。

  • Ai roleplay practice

    goingli0324/ai-roleplay-practice Skill

    0★

    Sets up an interactive AI roleplay so the user can rehearse a difficult conversation or scenario — any persona, any context — with structured feedback at the end. Use this whenever the user wants to practice, rehearse, or prepare for a conversation by having AI play a specific role (a difficult student, a skeptical parent, a colleague pushing back, a dissertation committee member, an interviewer, a negotiation counterpart, or any other identity the user names), says things like "讓AI扮演...", "陪我練習...", "模擬一下...情境", or wants a safe, repeatable space to rehearse before a real high-stakes interaction. The persona is never fixed to one category — always let the user define who AI plays, and offer example personas only as starting suggestions.

  • Obsidian rest api

    TomMaSS/agent-skills/skills/obsidian-rest-api Skill

    0★ repo

    Call the Obsidian Local REST API directly (over HTTP) for vault operations that the mcp__obsidian__* tools do NOT expose. Use when needing to move/rename a note, overwrite a whole file atomically (PUT), act on the currently-open "active" file, run an Obsidian command, open a note in the UI, list all tags, or do date-specific periodic-note CRUD. Prefer the mcp__obsidian__* tools for plain read/append/patch/delete/search; fall back to this skill only when the required method is missing from MCP.

  • Skill selector

    HWY1dot0/skills/skill-selector Skill

    0★ repo

    Decide whether to reuse an existing skill, adapt/compose one, or build a new one for a given task — and pick the best-matching option among candidates. Use this whenever someone is about to tackle a repeatable task and is weighing build-vs-reuse, asks "should I make a skill or find one," is choosing among several existing skills, wants to judge whether a discovered skill is good enough or trustworthy, or is unsure which skill fits. Trigger even when the word "skill" isn't used but the user is clearly trying to source or select tooling for a recurring task. Do not trigger for one-off or trivial tasks that are faster to just do directly.

  • Claude fable method orchestrator

    iesjoaco7-cyber/Claude---Fable-5-Clone/.claude/skills/claude-fable-method-orchestrator Skill

    0★ repo

    High-performance agent workflow (intent → context → plan → execute → verify → deliver) for complex or multi-step work. Use whenever the user asks for code analysis, debugging, refactoring, repository or Skill creation, research synthesis, UI/UX or design review, technical documentation, project planning, learning explanations that need structure, or agent/prompt architecture — even if they don't name the skill. Also trigger on phrases like "fable method", "claude-fable", "trabajá como agente", "planificá y verificá", or requests to audit/improve an existing Skill or repo. Do not use for trivial single-fact questions. This skill builds safe behavioral workflows only; it never extracts or reproduces proprietary model internals.

  • Skill

    0xPiPo/ultracodex/skill Skill

    0★ repo

    Token-frugal orchestration — Claude/Opus stays the architect (decompose, judge, synthesize, verify critical work) and routes all token-heavy work (writing code, searching, running tests, bulk discovery) to the cheaper Codex lane (gpt-5.6) via codex exec, keeping artifacts on the filesystem instead of in Claude's context. Use for substantial coding/refactor/audit/migration tasks to minimize metered Bedrock tokens. Invoke as /ultracodex <task>, or when the user asks to offload work to Codex, save Claude tokens, or run the architect pattern.

  • Automation audit

    kochellenk-afk/claude-marketing-skills/skills/automation-audit Skill

    0★ repo

    Run a full business automation audit. Inventory every workflow across departments, rank the top 10 automation opportunities by time saved, money impact, and build difficulty in a prioritized table, produce a one-screen visual company map with bottlenecks and automation opportunities marked, and recommend the 3 to build first with build specs and reasoning. Trigger whenever the operator wants to automate a business or find automation opportunities, on phrases like "automation audit", "automate my business", "where can AI save time or money", "find automation opportunities", "map my company", "what should I automate first", "AI automation project", or when they loads a business's processes and tools and asks what to automate or systematize. Works for any client (any client, any industry). Do NOT use for building one already-chosen automation (just build it), for social/ad/SEO content, or for go/no-go validation of a brand-new idea (that is idea-pressure-tester).

  • Pull feishu minutes

    YijiaDuan/pull-feishu-minutes Skill

    0★

    把飞书妙记(会议/讲座/Coffee Chat 的录音转写)全量拉到本地,存成带 AI 总结的 Markdown 笔记。首次全量、之后自动增量。用户不需要自建飞书应用、不需要申请 API 权限、也不需要管理员审批——只要在弹出的浏览器里登录一次飞书即可,完全没授权过飞书的人也能用。触发词:拉飞书妙记、同步妙记、下载妙记、把妙记存到本地、导出飞书妙记、飞书录音转写、feishu minutes、把我的妙记同步到 Obsidian。

  • Incident decision log

    taufiqigalih/launch-decision-kit/skills/incident-decision-log Skill

    0★ repo

    Use when a live incident is unfolding during a launch window or in production and someone needs to keep a running decision log while diagnosis is still unsettled — separating what's observed from what's hypothesized from what's confirmed. Trigger on phrases like "start an incident log," "track this as we go," "what do we actually know right now," or "keep the timeline straight while we figure this out." Not for a completed incident write-up after the fact (that's a postmortem) and not for a pre-launch decision (use launch-decision-record).

  • Evidence led copywriter

    devschro/evidence-led-marketing-skills/evidence-led-copywriter Skill

    0★ repo

    Writes, rewrites, adapts, audits, and tests distinctive evidence-grounded conversion copy without fabricated proof or generic AI voice. Use for homepages, landing or sales pages, offers, pricing and checkout copy, ads, lifecycle email, cold outreach, product launches, app-store listings, product or UX microcopy, calls to action, headlines, copy decks, voice development, message-match audits, copy variants, or copy experiments—especially when copy must reflect product truth, customer language, brand voice, current channel rules, substantiated claims, and measurable commercial outcomes. Do not use for broad market selection or positioning before strategy is settled, general editorial or fictional writing, visual design, or autonomous publishing/sending.

  • Skill auditor

    ki-stuff/skill-auditor Skill

    0★

    Use when vetting any new, external, or unknown skill before installation. Scans for prompt injection, data exfiltration, privilege escalation, persistence, and social engineering. Always run before installing skills from GitHub, ClawdHub, or unknown sources. Also use when the user wants an overview/inventory/dashboard of all their installed skills, e.g. "which skills do I have installed", "skill inventory", "skill overview", "audit all my skills".

  • Claude freelance strategist skill

    ziakamal/claude-freelance-strategist-skill Skill

    0★

    Long-term strategic mentor for growing a freelance/creator business — market trends, niche selection, pricing, client acquisition, sales, personal branding, content monetization, operations, automation, recurring revenue. Covers BOTH income streams, client-services work (agency/consulting/contract) and content/audience income (personal brand, sponsorships, digital products, courses). Use whenever the user explicitly asks for business strategy, growth planning, niche/positioning advice, pricing decisions, client acquisition or sales tactics, branding or monetization roadmaps, or an action plan to scale income. Trigger on: "help me grow my freelance business," "what niche should I focus on," "how do I get high-ticket clients," "build me a 90-day plan," "should I monetize with courses or sponsorships," "is this a good pricing model." Skip it for one-off asks unrelated to overall strategy (debugging code, one email, one reel script) — handle those directly.

  • Scenario test design

    phatnguyen975/scenario-test-design Skill

    0★

    Apply this skill whenever a user needs to design test scenarios based on real-world business workflows before writing test data or test scripts. Triggers on: "design test scenarios", "scenario testing", "create test scenarios", "scenario-based testing", "test scenario design", "identify test scenarios", "write test cases from requirements", or any request to analyze requirements, BRs, FRs, or User Stories and produce scenario flows. This skill covers TEST DESIGN (analysis + scenario flow), NOT automation code or test scripts. Invoke even if the user only pastes requirements and says "help me test this".

  • Apify news monitoring

    johnisanerd/claude-skill-news-monitoring/apify-news-monitoring Skill

    no license0★ repo

    Monitor news coverage of a brand, competitor, or topic with the Apify Google News API Actor (johnvc/GoogleNewsAPI). Poll a watchlist of queries on a schedule and get fresh articles with title, link, source, snippet, and relative date, ready to dedupe by link and turn into alerts, digests, or a mentions feed. Use when the user wants news monitoring or media monitoring, brand mentions from news, competitor news tracking, google news tracking or google news monitoring, crisis or reputation watch, or a recurring news digest for a market, industry, or portfolio. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Apify gas price monitoring

    johnisanerd/claude-skill-gas-price-monitoring/apify-gas-price-monitoring Skill

    no license0★ repo

    Monitor gas prices across ZIP codes and cities with the Apify Fuel Prices Scraper Actor (johnvc/fuelprices). Poll a watchlist of locations on a schedule and get one row per station with cash and credit prices plus posted timestamps, ready to diff against your last snapshot for price-change alerts, cash versus credit spreads, and station-level competitive tracking. Use when the user wants gas price monitoring, fuel price monitoring, price-change alerts for fuel, tracking gas prices across multiple ZIP codes or cities, watching diesel or E85 prices for a fleet, or a live feed for a fuel price dashboard. Pay-per-result billing, MCP-ready for Claude and other AI agents.

  • Cz cellxgene

    Agents365-ai/cz_cellxgene Skill

    no license0★

    Expert reference for pulling single-cell RNA data from CZ CELLxGENE — the cellxgene-census Python/R API (query, slice, and download cells across the whole harmonized corpus via TileDB-SOMA) and the CELLxGENE Discover Curation REST API (find and download published datasets/collections). Use whenever the user wants data from CELLxGENE / cziscience / cellxgene-census: opening the Census (open_soma), writing obs/var value_filters, building an AnnData with get_anndata, listing cell metadata, deduplicating with is_primary_data, loading hosted embeddings (scVI, Geneformer, UCE), downloading a source H5AD by dataset_id, or querying collections/datasets over REST. Also triggers on "cellxgene census", "cziscience", "get_anndata", "census_data", "下载 cellxgene 数据", "查询单细胞图谱". Gives correct API signatures, the exact obs/var schema and filter syntax (which models routinely get wrong), memory-safe query patterns, and version pinning for reproducibility.

  • Web studio

    youkistudios/web-studio/skills/web-studio Skill

    0★ repo

    One art-directed design studio in a box — an art-director agent commits direction, Claude builds, an image CLI renders media, a second model gates cost and reviews mechanically, then deploy + receipt. A 9-stage pipeline that turns a brief into a deployed, on-brand, non-slop website. Use when the user wants a new marketing/product/launch website built end-to-end, not for small edits to an existing site.

  • Transcribe

    katsu9999/transcribe-skill/skills/transcribe Skill

    0★ repo

    Transcribe voice recordings locally on Apple Silicon Macs using mlx-whisper (free, private, no cloud). Use when the user asks to transcribe an audio file, a voice memo, or an iPhone recording.