agentsclimarketplace

The catalog

608,253 rows, by stacks then stars

  • Pbi config drafter

    yujiyamane/pbi-ai-skills/.claude-plugin/skills/pbi-config-drafter Skill

    0★ repo

    Analyse a CSV/Excel dataset and auto-generate a Dashboard Drafter Config Block. Reads column headers, data types, unique value counts, and value ranges to classify columns into SUM/CNT/AVG/KEY/OTHER/DATE slots, then proposes a Config Block for user approval. Does NOT generate the dashboard — only drafts the config. Use when the user says: 'draft config', 'analyse this CSV for dashboard', 'create config from data', 'generate config block', 'propose config', 'what config should I use for this data', or provides a CSV/Excel path with config-drafting intent.

  • Pushary cowork

    Pushary/cowork-plugin/skills/pushary-cowork Skill

    0★ repo

    Reach the user on their phone through the Pushary connector. Use when a task finishes, when you need a decision or approval, when you are blocked or hit an error, or when the user asks to be notified, pinged, or kept in the loop while away.

  • Be the whole bitch

    88plug/be-the-whole-bitch/skills/be-the-whole-bitch Skill

    no license0★ repo

    Full execution authority on reversible work. You run commands, read outputs, iterate until done. Never hand the operator a command to paste or ask questions you could probe with tools. When imperatives conflict ("run X" vs "give commands"), run X wins. Defer irreversible ops to trigger-my-training. Use on action tasks, debugging, deploys, verification — not when the operator only wants a written plan.

  • Dehumanize

    88plug/dehumanize/skills/dehumanize Skill

    no license0★ repo

    Strip human-shaped framing from AI work. Invoke when responses drift into man-hours/sprints/EOD/"hours of work"/"afternoon's work" estimates, asking the user to paste/share/drop files or screenshots ("I can't see", "tell me what you see") the agent can read itself, emotional filler ("sure!", "certainly!", "great question", "hope this helps"), serial "I'll start with / one by one / one step at a time" checklists for independent work, or capacity theater ("this will take a while", "will take ~N min", "non-trivial effort"). Rewrites the behavior to: access data and screens directly, fan out in parallel, and act now.

  • Flip the script

    88plug/flip-the-script/skills/flip-the-script Skill

    no license0★ repo

    Use when about to assert a fact that has an exact external answer and the answer came from memory rather than a checked source — a library/API version or signature, a current-state or "latest/recommended" claim, an exact number/price/stat/date, a niche or long-tail detail, or a "yes that works / I already checked" you cannot point to evidence for. Also use whenever you notice felt-certainty standing in for a source, or you are about to declare something fixed/done/correct without a re-run. The move: treat unverified recall as stale + overconfident by default, classify whether the claim is in a reliable or unreliable recall domain, and route the unreliable ones to EXTERNAL ground truth (read-the-damn-docs, search, read the source, measure, or a fresh-context check) before asserting — not to internal second-guessing. Reach for it by default before any version/API/current-state/exact claim; skip it for stable well-known facts and settled, already-verified things (re-litigating those is its own failure mode).

  • Run ai audit

    navinramharak-rgb/10k-ai-audit/skills/run-ai-audit Skill

    0★ repo

    Audit how a business actually operates, build a digital twin of its workflows, classify every task as Agent, Copilot, or Human, and return a scored, phased AI implementation roadmap. Use when a founder, operator, or team asks "where should we use AI", "what should we automate", wants an AI audit, AI strategy, automation roadmap, or workflow mapping, says their team is drowning in manual work, or wants to know what should stay human. Not for building one specific automation — this maps the whole operation first.

  • Build perfect project

    navinramharak-rgb/perfect-project-builder/skills/build-perfect-project Skill

    0★ repo

    Turn any recurring workflow into a complete, paste-ready Claude Project — Project Instructions, a context-document plan with fill-in templates, starter prompts, and a pressure test. Use when someone wants to "set up a Claude Project", "build a project for X", needs Project Instructions or a knowledge-base plan, wants a repeatable system for content creation, newsletters, outreach, research, proposals, or support, keeps re-pasting the same context into every chat, or asks "how should I structure my Claude Project".

  • Algol

    btmoriarty/algol/skills/algol Skill

    0★ repo

    Govern code review for a project instead of performing it. Triggers when setting up or running Algol, defining or compiling review policy in .algol/policy.toml, routing a change to the right review engine by policy and undo-cost, reconciling findings from /code-review, ultra, gauntlet, or the deterministic collectors into one record, or recording a review decision with reopens-if conditions. Not a reviewer itself.

  • Deep angle finder

    LordVayron/Skills/skills/deep-angle-finder Skill

    no license0★ repo

    Takes any topic and finds the deep, structural, non-obvious angle underneath the surface take. Traces surface phenomena to structural causes, cross-pollinates from unexpected fields, names new concepts. Use when the user says "find me an angle", "go deeper on this", "find the deeper take", "structural analysis of", "what's everyone missing about", "deep angle", "think deeper about", "reframe this", "find the contradiction", "/deep-angle-finder", or shares a topic and wants the sharp non-obvious argument inside it. Any topic + desire for depth or structural thinking = use this skill. Do NOT trigger when the user already has their angle and wants to write.

  • Aromatic herb gardening expert

    MrBridgeHQ/aromatic-herb-gardening-expert/skills/aromatic-herb-gardening-expert Skill

    0★ repo

    Use when the user wants help growing, maintaining, harvesting, or using aromatic culinary herbs at home (basil, mint, thyme, rosemary, parsley, cilantro/coriander, chives, dill, oregano, sage, tarragon, lemon balm, lavender, bay laurel, marjoram, savory, Vietnamese coriander). Covers choosing herbs for a climate and space, personalized growing plans, sowing, transplanting, pruning, watering, fertilizing, propagation, diagnosing problems (yellow leaves, wilting, pests, fungus, bolting, root rot, nutrient deficiency), organic and low-toxicity pest and disease control, container gardening, seasonal calendars and weekly checklists, companion planting, and harvesting, drying, and freezing. Triggers on "how do I grow", "my herb is dying/yellow/wilting", "herb garden", "container herbs", "when do I harvest", "my basil won't grow", "best herbs for shade/pots/my climate".

  • Token discipline

    Skillproofdev/token-discipline Skill

    no license0★

    Use when the user asks to reduce token usage or Claude Code costs, complains that sessions burn tokens too fast or hit context limits, wants long sessions to stay cheap, or asks to work token-efficiently. Also apply for the whole session when installed as an efficiency layer. Enforces input-side discipline (scoped search before reads, partial reads, batched tool calls, no redundant re-reads) plus terse output. Do not trigger for API pricing questions or billing disputes.

  • Research discipline

    Skillproofdev/research-discipline Skill

    no license0★

    Use whenever an answer depends on facts outside the codebase or training data — "research X", "what's the latest", "compare A vs B", version/pricing/market/news questions, "is it true that", fact-check requests — or when the user asks for sourced, verifiable output. Enforces evidence discipline on any research-shaped answer, short or long: live sources over memory, per-claim citations, independent-source triangulation, date-stamps, explicit unverified flags, adversarial self-review. Do not trigger for pure coding tasks, creative writing, or questions of opinion/taste.

  • Compile tex

    hmasum52/skills/compile-tex Skill

    0★ repo

    Compile a LaTeX (.tex) project to PDF, building in an isolated temp directory so no build artifacts land in the project directory. Uses a local latexmk install if present, otherwise falls back to a Docker TeX Live image. Use when asked to compile, build, or typeset a LaTeX paper.

  • Data licence check

    davidbaines/claude_configs/skills/data-licence-check Skill

    0★ repo

    Check data-source licences during research and planning so experiments use shareable data and results stay independently verifiable. Use whenever a plan or experiment selects data sources (datasets, corpora, scripture translations, scraped text, model weights), before finalising a data selection, before training anything intended to be published, or when asked to check/audit licences. Flags non-redistributable sources and proposes a shareable-only subset. Invoke with /data-licence-check.

  • Apify youtube transcripts llm training data

    johnisanerd/claude-skill-youtube-transcripts-llm-training-data/apify-youtube-transcripts-llm-training-data Skill

    no license0★ repo

    Build LLM training data from YouTube transcripts in bulk with the Apify Actor johnvc/YoutubeTranscripts. Feed it an array of video URLs and get one clean row per video, with non_timestamped transcript text ready for tokenization, timestamped snippets, language_code, and provenance metadata (title, channel_name, upload_date, view_count) for dataset documentation. Filter by language or translate every transcript into one target language for a consistent corpus. Use when the user wants LLM training data from videos, a fine-tuning or RAG corpus from YouTube, bulk YouTube transcripts for machine learning, or a text dataset from spoken video content without running speech-to-text. Pay-per-video billing, MCP-ready for Claude and other AI agents.

  • Be precise

    NKAN1729/jordan-b-peterson-sort-yourself-out/skills/be-precise Skill

    0★ repo

    Peterson-style coaching session — turn a vague dread into a precisely articulated problem, then route it. Also answers /name-it. Trigger when the user says something feels wrong but they can't name it, describes foggy unease about career/life/relationships, or "doesn't know what the problem is". The entry point when nothing else fits. (sort-yourself-out)

  • Daily standup status in xyz format

    spShashankGit/skills/daily-standup-status-in-xyz-format Skill

    0★ repo

    Synthesizes git logs, terminal history, or project text into a Google-style X-Y-Z daily status update. Trigger this when the user asks for a daily standup update, status report, or summary of what they did today.

  • Hindsight

    tansharma/hindsight/hindsight Skill

    no license0★ repo

    Deep retrospective architectural review of an entire project against a user-stated goal, producing ranked, actionable findings in inHindsight.md. Use this skill whenever the user runs "/hindsight", asks for an "architectural review", "codebase review", "technical debt review", or "hindsight review", asks "what should I improve here", "what would you have done differently", or "review this project against my goal", or wants to re-check which previously reported findings have been resolved. Trigger even if the user doesn't name the skill but describes reviewing a whole project (not a single file) against a purpose or goal. Requires the user to state the project's goal; writes the review to inHindsight.md at the project root.

  • Oracle apex ut UI.skill

    raju-bd/Oracle-apex-ut-UI.skill Skill

    no license0★

    Use this skill whenever the user wants to generate, style, or reference HTML/CSS that matches Oracle APEX's Universal Theme 42 design system (Vita, Vita Dark, Vita Red, Vita Slate, Iris, Redwood, or Standard Theme Styles). Triggers include: any mention of 'Oracle APEX', 'APEX theme', 'Universal Theme', 'Vita', 'Vita Emerald', 'Theme Roller', 'APEX region/component' (Alert, Card, Interactive Report, Wizard, etc.), or requests to build a dashboard, admin UI, or component that should 'look like APEX' or use APEX design tokens. Also use when asked to create a new custom APEX Theme Style, when styling should use var(--ut-*) / var(--a-*) CSS custom properties instead of hardcoded colors, or when working with files under tokens/ (vita-light.css, vita-dark.css, vita-red.css, vita-slate.css, iris.css, redwood.css, standard.css, vita-emerald.css/.less) or components-reference.md from this package. Do NOT use for generic web design requests with no APEX/Universal Theme context.

  • Zenodo publish

    aradar46/zenodo-publish/zenodo-publish Skill

    0★ repo

    Use when preparing a research codebase for Zenodo deposition, auditing Zenodo-readiness, generating .zenodo.json or CITATION.cff metadata, or setting up GitHub-Zenodo integration. Also use when the user says 'publish to zenodo', 'zenodo audit', 'prepare for zenodo', 'make this zenodo ready', 'generate citation file', 'DOI for my code', or 'deposit to zenodo'.

  • Team lead readiness

    marian-kamenistak/team-lead-readiness Skill

    0★

    Use when an engineer asks "should I become a team lead?", wants to know if they are ready for a first lead or engineering-management role, is weighing the senior IC track against the management track, or wants a plan to get ready in 6-12 months.

  • Blog builder

    stephenpham68/citely-blog-kit/skills/blog-builder Skill

    0★ repo

    Build or upgrade a professional blog UI (blog hub + article reading experience) for any website or platform, following the Citely blog standard. Use when creating a blog from scratch, styling article HTML received from a CMS or Citely Connect, adding a table of contents / reading progress / typography system to articles, or auditing an existing blog against SEO/GEO and reading-UX standards.

  • Setup

    l3onlau/claude-life-admin/.claude/skills/setup Skill

    0★ repo

    Interviews the user about their life-admin workflow and generates the gitignored personal layer — CLAUDE.local.md, inbox.md, and optional domain modules. Use when the user asks to set up, initialize, personalize, or onboard this workspace, or when CLAUDE.local.md is missing.

  • Financial diligence dashboard

    MajedAlawad/financial-diligence-dashboard Skill

    0★

    Analyze financial statements (ratios, trends, quality-of-earnings flags) and deliver the result as a self-contained dark-themed HTML dashboard that renders identically wherever it is opened or shared. Use this whenever someone uploads a 10-Q, 10-K, earnings release, annual report, or any income statement / balance sheet / cash flow data and wants it analyzed, screened, benchmarked, or turned into a dashboard, scorecard, one-pager, or visual summary — including when they only ask for "the numbers", "key ratios", "red flags", or "a dashboard" without naming a format. Also use when revising or restyling an existing financial dashboard.

  • Dual agent review

    alainabo/aso-dual-agent-review/.claude/skills/dual-agent-review Skill

    0★ repo

    Use when someone wants two AI agents to review each other's work before a human ships it — for ANY kind of work, not just code: documents, marketing content, designs, contracts, analyses, spreadsheets, websites. Triggers include "set up dual-agent review", "peer review between my agents", "make my agents check each other", "review without babysitting", "second opinion agent", or wanting to install this workflow in a new project. Interviews the user about their domain, then installs the shared review folder, proposal template, silent whispers, per-agent manual sections, and a /check-reviews skill — all adapted to their work.

  • Agency monthly report

    SkillMedev/agency-operating-system/skills/agency-monthly-report Skill

    0★ repo

    Build the monthly client report that renews retainers - results-first structure with business outcomes before activity, the metric-that-matters-to-them rule, work-completed as evidence rather than headline, and a next-month plan with one client-action recommendation. Includes a full copy-paste template and a good/bad results-section pair. Use when an agency team says "write this month's client report", "our reports are just a list of tasks we did", "the client says they don't know what they're paying for", or "make our reporting actually defend the retainer". Do NOT use for the quarterly business review deck - use agency-qbr-upsell instead.

    The same file is in 1 other repository

  • Business harness builder

    iyinhai/business-harness-builder Skill

    0★

    Use when a user wants to turn a business, consulting, research, whitepaper, product-discovery, workshop, or non-technical collaboration project into an AI-ready harness: a reusable project workspace with start-here instructions, master prompt, source-of-truth files, evidence logs, decision logs, stage gates, task boards, templates, handoff notes, and review loops. This skill is for business/project harnesses, not coding-agent runtime harnesses.

  • Tender comparison

    deva-ships/tender-tally/tender-comparison Skill

    0★ repo

    Compare construction, civil, electrical, or interior fit-out tenders item by item and produce a clean Excel comparison. Use when the user has two or more vendor quotes, tenders, quotations, estimates, or BOQ bids (PDF, Excel, Word, or scanned images) for the same building or renovation job and wants to see the lowest rate per line item and the lowest overall vendor. Extracts every item and rate from each vendor, matches items that vendors name or group differently, flags anything a vendor left out, and ranks vendors L1 to Ln with the lowest highlighted.

  • Apify congress stock trades api

    johnisanerd/claude-skill-congress-stock-trades-api/apify-congress-stock-trades-api Skill

    no license0★ repo

    Pull US Congressional stock trades and financial disclosures as structured JSON with the Apify Congress Financial Disclosures and Stock Trades Actor (johnvc/us-congress-financial-disclosures-and-stock-trading-data). Filter Periodic Transaction Reports from the House and Senate by member name, ticker, or date range and get one row per transaction with Ticker, Asset, Transaction_Type, Amount_Range, Date, House, State_District, and Filing_ID. Use when the user wants a congress stock trades api, wants to scrape congressional financial disclosures, export House or Senate stock trades to JSON or CSV, pull a member's disclosed trades, look up which members traded a ticker, or build a congressional trading dataset for research. Pay-per-transaction billing, MCP-ready for Claude and other AI agents.

  • Session handoff

    rb17080/session-handoff/session-handoff Skill

    0★ repo

    Write or update a comprehensive HANDOFF.md at the repo root that captures the whole current session so the next chat can resume cold - what got done, what shipped, what failed, what was learned, where things stand, and how it got there chronologically since the last handoff. Use whenever the user says "update the handoff", "write the handoff", "wrap up this session", "where did we leave off", or is closing out a work session.

  • Worktree cleanup

    Enverge-Labs/skills/skills/worktree-cleanup Skill

    0★ repo

    Tear down a finished task's git worktree and branch once its PR is merged or closed. Use when a task is done, a PR was merged/closed, or the user asks to clean up / remove / prune worktrees or stale branches. Companion to the `worktree-new` skill; applies to whatever repository Claude is currently in.

  • Batch analyze

    Baikodis/claude-knowledge-base-skills/skills/batch-analyze Skill

    0★ repo

    Multi-agent data analysis — auto-chunking, parallel agents, assembly with validation

  • Template

    MaddyMOK/claude-skills/skills/_template Skill

    0★ repo

    REPLACE ME. State what the skill does AND when it should trigger, in one dense paragraph. Be specific and a little pushy about triggering — name the phrases, contexts, and task types that should invoke it (e.g. "Use this whenever the user mentions X, asks to Y, or is doing Z, even if they don't say 'skill'."). This description is the ONLY thing Claude sees when deciding whether to load the skill, so put all "when to use" info here, not in the body.

  • Phase adopt

    awjackson2/phase-skills/phase-adopt Skill

    0★ repo

    Use to retrofit the phase workflow into an EXISTING project that already has code and git history. Trigger when the user says "adopt the phase workflow here", "set up phases in this existing repo", "start using phases on this project", "retrofit the workflow", or drops these skills into a project that already has commits. Unlike phase-project-init (which bootstraps an empty repo), this works with an established, possibly-shared default branch: it adds development/phase_log/ via a docs-lane PR, optionally backfills a light phase history reconstructed from git, settles where the first new phase number starts, then hands off to phase-decompose/phase-loop or phase-tracker.

  • Pitch brief compass

    dongwu711/pitch-brief-compass/.claude/skills/pitch-brief-compass Skill

    0★ repo

    Evaluate an incoming client brief (pitch/RFP) the way an agency team does. Input is the briefing document; outputs are four deliverables in two stages — compass mapping, context research, client questions, and (after client Q&A) the pitch-ready brief. Use when the team receives a client brief, RFP, or pitch invitation.

  • Hlzd b2b research

    Alexxiang2008/hlzd-b2b-export-skills/skills/hlzd-b2b-research Skill

    0★ repo

    B2B 工业品海外市场调研全链路自动化 —— HS 编码查询(hsbianma.com)+ UN Comtrade 市场规模 + Google Trends 需求热度 + DDGS 买家线索 + 招标信息追踪,输出结构化 JSON 与 Markdown 报告。Use when 用户说'B2B 调研'、'工业品市场分析'、'查 HS 编码'、'查采购商'、'找海外买家'、'市场容量'、'招标追踪'、'B2B market research'、'industrial export research'、'find buyers overseas'、'project tender tracking'。

  • Commit craft

    moses607/skillforge/skills/commit-craft Skill

    0★ repo

    Turn a set of code changes, a diff, or a description of work done into clean Conventional Commits and, on request, a changelog entry. Use whenever the user asks for a commit message, says "write the commit", pastes a diff and wants it committed, asks to squash/split commits, or needs a CHANGELOG or release notes — even if they just describe what they changed in plain words.

  • Apify scrape google jobs

    johnisanerd/claude-skill-scrape-google-jobs/apify-scrape-google-jobs Skill

    no license0★ repo

    Scrape Google Jobs listings into structured JSON with the Apify Google Jobs Scraper Actor (johnvc/Google-Jobs-Scraper). Give a job title or search query plus an optional location, and get one row per listing with title, company_name, location, source platform, full description, job_highlights, posted_at, schedule_type, and direct apply_options links. Use when the user wants to scrape google jobs, export Google Jobs results to JSON or CSV, build a job listings dataset, pull openings for a role or city, or asks for a Google Jobs scraper, job scraper, or job scraping workflow. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Wechat pay integration

    shuangying0001-beep/wechat-pay-integration Skill

    0★

    给小程序/公众号接微信支付,强制回调验签、幂等、密钥隔离。适合任何要收款的微信应用。

  • Adr enforcer

    willianbs/skills/adr-enforcer Skill

    0★ repo

    Ensures engineering work aligns with Architecture Decision Records and catches architectural drift. Use when planning, implementing, reviewing, or when no ADRs exist and bootstrap is needed. Emits ADR_COMPLIANCE. Never silently invents architecture or auto-modifies ADRs.

  • Aggregate skills map

    Alexxiang2008/awesome-skills-map/skills/aggregate-skills-map Skill

    0★ repo

    聚合 GitHub 博主/牛人技能地图。输入 GitHub 用户名列表,自动拉取其公开仓库,按 stars 排序并按职能分类,输出 Markdown 技能地图(含简介 + 仓库地址)。支持 fork 过滤、最小 star 阈值、主题筛选、JSON 输出。当用户说「聚合博主技能」「生成技能地图」「按作者聚合 skills」「我想看 X 的 skills」「跟踪大牛仓库」时触发。依赖:gh CLI 已登录。

  • Academic code replicator

    jpmsilva1/ai-research-ecosystem/skills/academic-code-replicator Skill

    0★ repo

    Full-lifecycle skill for replicating experiments from academic papers. Guides the agent through understanding the original codebase, constructing isolated environments, making safe platform-compatibility adaptations, executing on available hardware, and producing a documented comparison against paper-reported results. Use this skill whenever the user says things like: "replicate this paper", "reproduce this experiment", "make this old code run", "run this paper's code", "I'm trying to get this GitHub repo from a paper working", "help me replicate these results", "this code is from 2019 and won't install", "I need to reproduce Table X from this paper", or any variation of scientific code replication. PROACTIVELY trigger even if the user just says "help me run this paper's experiments" without explicitly mentioning replication.

  • Zygote

    ABaliyan31/zygote Skill

    no license0★

    scaffold backend/frontend boilerplate repos (node, python, react, etc.) - dependency check - confirm - install - scaffold

  • Launch your local agent

    kimtory88/launch-your-local-agent/.claude/skills/launch-your-local-agent Skill

    0★ repo

    Build a self-checking scheduled agent that runs on the user's own machine via headless Claude Code (claude -p) on their subscription — no API key, no per-token billing. Interview the user about what the agent should do, scope a v0, assemble an agent folder (CLAUDE.md, task, rubric, outcome-loop), test-run it with an independent judge, and schedule it (systemd/launchd/cron). Community fork of anthropics/launch-your-agent retargeted from Claude Managed Agents to local infrastructure. Use when the user says "launch my local agent", "/launch-your-local-agent", "build me an agent", or wants a recurring autonomous worker on their subscription.

  • Orangutan

    whoknewicould/oranguttan-skill/skills/orangutan Skill

    0★ repo

    Two-in-one Claude Code utility skill with two independent modes, chosen by context — they never run together. (1) DESIGN.md mode: create, read, update, or validate a DESIGN.md file, the machine-readable + human-readable spec for a project's visual identity (design.md format by Google Labs, https://github.com/google-labs-code/design.md). Trigger on "document our design system", "write a DESIGN.md", "capture our visual identity for agents", or references to DESIGN.md/design tokens in a persistent-spec sense; also consult an existing DESIGN.md at repo root before UI/styling decisions on a project that has one. (2) Plugin-install mode: bulk-installs every available plugin from every Claude Code marketplace already configured on this machine. Trigger on "install my plugins", "install everything from my marketplaces", "sync my plugins", or /orangutan.

  • SEMRUSH API Skill for Claude

    tvirelli/SEMRUSH-API-Skill-for-Claude Skill

    0★

    Work with the SEMRush REST API (SEO/Analytics reports, Site Audit, Projects, Position Tracking, Trends, Local) while strictly conserving API units. Use whenever the user mentions SEMRush, semrush.com API, API units/credits, position tracking, site audit, keyword/domain/backlink reports, or competitor research via SEMRush.

  • Apify yandex search api

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

    no license0★ repo

    Get structured Yandex search results without an official API key using the Apify Yandex Search Scraper Actor (johnvc/Scrape-Yandex). One query returns the full SERP as JSON, with organic results (position, title, link, displayed_link, snippet), and optional ads, knowledge graph, inline images, and inline videos, targeted by Yandex domain, language, and any of 123,000 plus lr region IDs. Use when the user wants a yandex search api, a yandex serp api, Yandex search results as JSON or CSV, to scrape Yandex search, to check what ranks on yandex.ru for a query or region, or SEO research for Russian-speaking markets. Pay-per-page billing, MCP-ready for Claude and other AI agents.

  • Agent task compiler

    Arnie016/fable-mythos/skills/agent-task-compiler Skill

    0★ repo

    Compiles a vague project idea into agent-ready work - a sprint spec, a contract of testable assertions, and an ordered task list with acceptance criteria. Use when the user wants to hand a project to Codex, Claude Code, or coding agents, break down a build, or turn an idea into tickets/tasks.

  • Candidate shortlister

    bitesizetalent/candidate-shortlister Skill

    0★

    Shortlist a batch of candidates against one role. Use this skill whenever someone has a folder of CVs/profiles (a LinkedIn Recruiter export, an ATS download, email attachments — any format) and a job description, and wants the closest-matching candidates surfaced as a ready-to-send message for a hiring manager. Triggers on phrases like "shortlist these candidates", "who's the best match for this role", "screen this batch against the JD", "top candidates from this folder", or "put together a shortlist for the hiring manager". The recruiter can also supply notes on what matters most in the search; the skill weights the ranking accordingly and explains its reasoning. Does not contact candidates, does not store data, and does not move files.

  • Repo bullshit meter

    Nosafune/repo-bullshit-meter Skill

    0★

    Truth-first GitHub repository claim assessor. Use when the user asks to evaluate whether a GitHub repo, MCP server/plugin, AI tool, token-saver, agent framework, CLI, library, or open-source project actually supports its README/marketing claims; rate hype, slop, feasibility, or bullshit risk; or produce a sourced facts-vs-claims readout.

  • Business model canvas

    ajstars1/startup-coach/business-model-canvas Skill

    0★ repo

    Business Model Canvas (Osterwalder & Pigneur) plus Steve Blank's market types, Get/Keep/Grow, and unit economics — turn a validated problem into a testable business model where every block is a labeled hypothesis. Use late in validation or when scaling, for pricing/revenue-model questions, channel strategy, or "how does this make money".

  • Apify linkedin posts scraper

    johnisanerd/claude-skill-linkedin-posts-scraper/apify-linkedin-posts-scraper Skill

    no license0★ repo

    Scrape public LinkedIn posts into clean, structured JSON with the Apify LinkedIn Posts API Actor (johnvc/linkedin-posts-api). Give a profile URL to discover a person's recent posts, or specific post URLs to fetch directly, and get one row per post with text, hashtags, media, author details, and engagement counts (reactions, comments, shares). Use when the user wants to scrape LinkedIn posts, export LinkedIn posts to JSON or CSV, build a LinkedIn posts dataset, pull a creator's or a competitor's recent posts, or asks for a LinkedIn posts scraper or LinkedIn posts API. Pay-per-post billing, MCP-ready for Claude and other AI agents.

  • Seo audit

    chsistrying/claude-seo-skills/skills/seo-audit Skill

    0★ repo

    Audit a website or web app for SEO and AEO (answer-engine optimization) and produce a prioritized, evidence-backed report. Use this whenever the user asks to "audit SEO", "check SEO", "improve search ranking", "review meta tags / Open Graph / structured data", "why isn't my site showing up on Google", "make my site rank", "check my sitemap/robots.txt", or mentions crawlability, indexing, rich results, JSON-LD, canonical tags, social share previews, or getting cited by AI assistants (ChatGPT, Perplexity, Google AI Overviews). Also trigger when someone ships a marketing site, landing page, blog, or docs site and wants it "found" — even if they don't say the word "SEO". Framework-agnostic: works on React/Vue/Svelte SPAs, Next/Nuxt/Astro, static HTML, WordPress, or any live URL.

  • Concurrency invariants

    yakoshiq/skills/skills/concurrency-invariants Skill

    0★ repo

    Design, fix, or review concurrent and asynchronous code so atomicity, ordering, retries, idempotency, cancellation, timeouts, ownership, and partial success are explicit. Use for queues, workers, transactions, event handlers, parallel tasks, scheduled jobs, WebSocket/SSE, repeated delivery, concurrent requests, and race-condition fixes.

  • Hipaa ai compliance

    EliasAli0720/HIPAA-agent-skill/skills/hipaa-ai-compliance Skill

    0★ repo

    Guides HIPAA-compliant deployment of AI on health data — using an LLM with PHI, AI agents in healthcare, HIPAA chatbots, medical AI, RAG over patient data, ambient scribes, and de-identifying data for AI training — covering BAA'd endpoint selection, zero data retention, redaction, agent scoping, and audit logging. Use when someone asks about a HIPAA chatbot, sending PHI to an LLM, or Claude/OpenAI/Azure OpenAI/Bedrock BAA availability.

  • Agentic dev loop

    goingli0324/muzi-going-skills/plugins/agentic-dev-loop/skills/agentic-dev-loop Skill

    0★ repo

    從研究、plan.md、實作、Verify 雙閘到部署的開發迴圈編排器。當使用者要有計畫地把一個功能或 bug 從規劃走到上線(「開一個新功能」「先研究再做」「整理成 plan.md」「從頭做到上線」「幫我排開發步驟」「<專案名> 要加…」),或提出未指明範圍的「部署前/上線前檢查」時觸發——後者一律走雙閘,只跑 UI/UX 會漏掉安全與個資驗證。明確只要 UI/UX、只要安全審查、或只要分析連動禁區時,改用對應的單一 skill。

  • Book compiler

    immeasurablematt/book-compiler/book-compiler Skill

    0★ repo

    Turns a book on writing, editing, communication, rhetoric, storytelling, or copywriting into an executable Claude skill that performs the book's method rather than summarizing it. Use when the user supplies a book (PDF, EPUB, DOCX, or extracted text) and wants a skill built from it, wants an existing skill audited or rebuilt against its source book, or wants a library of books processed into skills.

  • Create x voice skill

    simple-post/create-x-voice-skill/plugins/create-x-voice-skill/skills/create-x-voice-skill Skill

    0★ repo

    Create or update a portable personal writing-voice Agent Skill from an X (Twitter) data archive or exported post files. Use when an AI agent needs to analyze authored X posts, replies, quote posts, or threads; derive evidence-based tone and style guidance; and package it for drafting, rewriting, or reviewing future social posts across Codex, Claude, or other Agent Skills-compatible systems.

  • SLUG

    matematicsolutions/patron-language-edition-template/_OBSZAR_/skills/_SLUG_ Skill

    0★ repo

    Gdy chodzi o {{zagadnienie}} w {{OBSZAR}} ({{AKT_KRAJOWY}}, {{JURYSDYKCJA}}): {{co robi - czasownik}}; zwraca {{artefakt}}. Uzywaj gdy {{trigger 1}}, {{trigger 2}}, {{trigger 3}}.

  • Apify google ai overview api

    johnisanerd/claude-skill-google-ai-overview-api/apify-google-ai-overview-api Skill

    no license0★ repo

    Get Google AI Overview answers and their cited sources as structured JSON with the Apify Google AI Overview API Actor (johnvc/Google-AI-Overview-API). Send one query or a batch, and get one row per query with ai_overview_present, ordered text_blocks (paragraphs, headings, lists, tables), references with link and source domain, retrievals_used, and a fetched_at timestamp. Use when the user wants a google ai overview api, wants to extract or export Google AI Overview answers to JSON or CSV, check which sources an AI Overview cites for a keyword, batch AI Overview lookups across a query list, or asks how to get Google AI Overview data programmatically. Pay-per-retrieval billing, MCP-ready for Claude and other AI agents.