agentsclimarketplace

The catalog

608,119 rows, by stacks then stars

  • Waitspin

    citedy/waitspin/skills/waitspin Skill

    0★ repo

    Use this skill for WaitSpin, the sponsored wait-state ads CLI and API. Trigger when a user wants to create or manage WaitSpin campaigns, buy prepaid impression blocks, inspect the public market, onboard with email OTP keys, install or check earning surfaces for VS Code, Cursor, Devin Desktop, Claude Code, Antigravity CLI, GitHub Copilot CLI, MiMo Code, OpenCode, Grok Code CLI, or Qoder CLI, inspect wallet/ledger/payout status, or reason about WaitSpin public API, trust boundary, privacy, and shipped vs not-shipped capabilities.

  • Agent workbench

    MuNeNiCK/agent-workbench/skills/agent-workbench Skill

    0★ repo

    Use when a coding agent needs durable work, design, review, evidence, interruption, recovery, and completion state through the native Agent Workbench CLI.

  • Bumping library versions

    vemodalen-x/VEMO_SKILLS/skills/code/bumping-library-versions Skill

    0★ repo

    Bump a device/library's four-segment version after an acceptance build+run passes, and keep the version single-sourced. The four segments X.Y.Z.W are embedded in three agreeing surfaces — a source string constant, the init log line, and a getVersion() API. Bump rules: W (last) = bug-fix +1; Z (penultimate) = feature +1 and reset W to 0; both-in-one-release = Z +1 and reset W to 0; X.Y (first two) = major/platform-line, human-set only. Precondition: the acceptance build+run has already succeeded. After bumping, report old → new explicitly. Use when releasing a library and the version must advance. Identity-decoupled — the version-string field name + file are caller parameters; no project names embedded.

  • Agentic video analysis skill

    Nu424/agentic-video-analysis-skill/skills/agentic-video-analysis-skill Skill

    no license0★ repo

    動画をフレームタイル化し、aitool recognize-imageで反復的に解析するためのスキル。 動画解析、見どころ抽出、ハイライト候補探索、ゲーム実況分析、エージェンティックな動画理解を行うときに使用する。

  • Compact handoff

    codecraftersautomation/claude-code/plugins/ccp/skills/compact-handoff Skill

    no license0★ repo

    Emergency, fast handoff when the current Claude account is almost out of usage/tokens and there's no time for a full handoff. Use this when the user says they're "about to hit the limit", "running out", "almost out of usage", "quick handoff", "emergency handoff", or needs to switch to the other profile (claude-team <-> claude-max) immediately. Writes a short .claude/ccp/handoff/COMPACT_HANDOFF.md (~1000-1500 words) with objective, state, next 3 steps, risks, and an exact takeover prompt.

  • Brevo connector solution builder

    tajoio/tajo-agent-skills/skills/brevo-connector-solution-builder Skill

    no license0★ repo

    Use when designing a connector or integration that maps an official source API into Brevo contacts, events, lists, transactional messages, campaigns, or suppression-safe lifecycle workflows.

  • Share skill with codex

    superchaospc/share-skill-with-codex Skill

    0★

    Give newly written Claude Code skills the ability to ALSO auto-trigger inside Codex, by symlinking them into Codex's skill directories. Use this WHENEVER a skill has just been created or finished in the Claude Code skills dir (including right after the skill-creator workflow), or when the user says things like "让这个 skill 在 codex 也能用", "share/link this skill with codex", "make this skill cross-tool", "两边都能用", "为什么 codex 看不到我新写的 skill", or asks how to make Claude Code and Codex share skills. Claude Code and Codex use the IDENTICAL skill format, so the fix is always a symlink — NEVER rewrite the skill into AGENTS.md (that strips the frontmatter and breaks Codex auto-discovery). Trigger proactively right after authoring any skill even if the user doesn't ask, since a Claude-Code-only skill is invisible to Codex until it is linked.

  • Ba kit

    SoftwareOneHN/ba-kit Skill

    0★

    Full-stack Business Analysis skill with structured lifecycle, templates, and quality gates. Covers intake, requirements backbone, FRD, user stories, SRS, wireframe handoff, and HTML packaging. Use when performing business analysis, writing requirements, creating SRS/FRD documents, producing user stories, preparing wireframe handoff packs, or managing BA project lifecycle. Supports Vietnamese and English. Keywords: BA, requirements, SRS, FRD, user stories, use cases, wireframe, intake, backbone, stakeholder, handoff, specification.

  • Pdfvector api

    khanhduyvt0101/pdfvector-skills/skills/pdfvector-api Skill

    no license0★ repo

    Use PDF Vector public APIs for document, invoice, identity, bank statement, and academic workflows, including parsing, ask, extract, search, citations, paper graphs, similar papers, grants, pricing, and page-separated output with includePages.

  • Superego

    spikesubingrui-design/superego/superego Skill

    0★ repo

    Operating discipline for personal AI agents — the judgment layer flagship models run on. Consult BEFORE: searching or answering from memory, doing anything external or irreversible (sending, posting, paying, deleting, scheduling), declaring a task done, writing to memory, or replying on a messaging surface. Covers: when to search vs answer, side-effect consent ladder, verify-before-done, memory upkeep, channel-aware output, failure escalation, prompt-injection defense.

  • Project radar

    sametbrr/project-radar Skill

    0★

    Günlük trend & topluluk keşif radarı. Use this skill whenever the user asks to run the "Project Radar" (or just "the radar"), produce a daily report of trending and talked-about useful projects, scan GitHub trending, or summarize what's being discussed across GitHub, Hacker News, Product Hunt, newsletters and social — output is a standalone Turkish HTML report in the project's signature design. Surfaces practically useful projects (open-source repos, apps, devtools); AI/LLM tooling is prominent but real-world usefulness is the filter. Triggers: "project radar çalıştır", "proje radarı", "radar çalıştır", "github trending raporu", "bugün ne konuşuluyor", "run the radar". Also manages a persistent WATCHLIST: "<repo>'yu watchliste ekle" / "add <repo> to watchlist" writes a medium-depth detail report (Markdown + HTML); "watchlist'i getir" / "show watchlist" lists entries with file references. Discovery-only: NEVER clones, installs, builds, or runs candidate repos.

  • Survey linter

    lonelydoctor/survey-linter Skill

    0★

    Audit a survey or questionnaire for question-quality problems before it is sent — flags leading, loaded, double-barreled, double-negative, and absolute wording; vague quantifiers; recall burden; jargon; unbalanced, overlapping, or non-exhaustive rating scales; missing neutral / 'Prefer not to say' options; sensitive questions without an opt-out; and question-order bias — then rewrites each flagged item. Works in English and Simplified Chinese, and can import surveys from plain text, Markdown, CSV, Google Forms, Typeform, or Qualtrics (.qsf). Use whenever the user shares or is writing a survey, questionnaire, poll, NPS / CSAT / feedback form, market-research instrument, course evaluation, or employee/engagement survey and wants it reviewed, critiqued, de-biased, or 'made better' before launch.

  • Harness

    jgoneit/harness-legacy/skills/harness Skill

    0★ repo

    Use only on an exact Harness activation: line-start $harness, line-start $harness:harness, a filesystem Harness skill link, or the exact personal-marketplace app link [@harness](plugin://harness@personal). Runs one approved Plan through root-only implementation, verification, clean-context review, bounded in-plan repair, optional Repair Resume or material Plan Amendment approval, and Completion. Do not activate from documentation, quotations, escaped text, ordinary requests, or inference.

  • Superdesign skill

    cskwork/superdesign-skill Skill

    0★

    superdesign - web/mobile UI design past a deterministic anti-slop gate. Use for "/superdesign", "design X", "make this beautiful", "landing page", "redesign UI", "design system / tokens", "critique this design", "explore directions", "generate image / icon / logo".

  • Diagnose

    TonkaToyXL/cursor-agent-skills/diagnose Skill

    0★ repo

    Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

    The same file is in 21 other repositories

  • Holo zlib

    helebest/holo-zlib/skills/holo-zlib Skill

    0★ repo

    Search and download published ebooks from Z-Library. Use this skill whenever the user wants to find or obtain a specific book or ebook (in formats like epub, pdf, mobi, or djvu) — whether they ask directly (find, grab, fetch, download) or indirectly (get me a copy of a title, I need this textbook as a file, do you have this book?). Trigger even when the user names no source, and when they mention Z-Library / zlibrary / zlib or name a different book library. Not for academic papers/preprints (e.g. arXiv), non-book media (movies, music, software), or operating on a file the user already has (converting, extracting text, summarizing) — though an ebook that happens to be a PDF still counts.

  • Micro app factory

    MilsimRooster/micro-app-factory/skills/micro-app-factory Skill

    0★ repo

    Use when the user wants to generate, refine, build, QA, or package a tiny static browser app from a rough idea or from scratch. Static-first workflow for utilities, quizzes, calculators, content tools, tiny games, and lightweight landing/info apps; waits for explicit "Build it" approval before creating files.

  • Media use skill

    Nu424/media-use-skill/skills/media-use-skill Skill

    no license0★ repo

    ローカルマシンのカメラ・マイク・スピーカー・画面をエージェントに使わせる。 写真撮影やウェブカメラでの確認、音声の録音・文字起こし・ボイスメモ、 スクリーンショット、音声での読み上げ返答を依頼されたときに使う。 キャプチャは ffmpeg、文字起こし・音声合成・詳細な画像解析は aitool CLI (aitool-iroiro)に委譲する。

  • Hermes skill portfolio review

    web3blind/hermes-skill-portfolio-review Skill

    no license0★

    Browser-first crypto portfolio review and weekly informer workflow using DeBank for EVM wallets and Jupiter Portfolio for Solana. Use when the user wants to review a crypto portfolio, inspect wallet allocation, compare visible DeFi/staked/claimable positions, or run a recurring portfolio informer without paid wallet APIs.

  • Fix code paper cut

    tomquirk/papercut-skills/fix-code-paper-cut Skill

    0★ repo

    Find, fix, verify, and publish one small low-risk code paper cut, excluding typo-only cleanup. Use when Codex should scan a codebase for an obvious isolated code smell, tiny duplicated code, misleading variable or function name, redundant branch, stale comment, local type cleanup, or similarly contained maintainability issue, then make the smallest safe patch and open a draft PR.

  • Advertising campaign planner

    skillim-hub/skills/advertising-campaign-planner Skill

    0★ repo

    Plan compliant Israeli advertising campaigns with multilingual targeting, budget allocation, and ROI estimation for small businesses, freelancers, and consumer-facing services.

  • Swarmskill agent skill

    DerDoPhil/swarmskill-agent-skill Skill

    no license0★

    Use when an AI agent wants to trade Solana pump.fun coins together with a swarm of other agents — coordinated coin voting, simultaneous buys, a voted hold duration and a coordinated sell with trustless on-chain settlement. Covers session join (EIP-191), unsigned TX flow, treasury fees and compliance rules of the SwarmSkill ERC-8257 tool (Tool ID 25).

  • Omnipotent search

    pengboyjak/omnipotent-search Skill

    0★

    全能搜 — 零依赖全网搜索引擎聚合。覆盖网页搜索/购物比价/职位搜索/学术论文/新闻资讯/图片视频/地图本地/URL提取/网站爬取/深度研究等全部场景。纯内置工具驱动,无需任何API Key。当用户说"搜索"、"查一下"、"搜全网"、"搜购物"、"搜职位"、"搜学术"、"搜新闻"、"抓取网页"、"爬取网站"、"深度研究"、"搜YouTube"、"查地图"、"比价"时自动触发。

  • Context engineering

    mikulgohil/claude-skills/skills/ai-agents/context-engineering Skill

    0★ repo

    Understand and optimize how context is structured in agent systems — the components, mechanics, and constraints of an agent's context window. Use when writing or tuning commands, skills, and sub-agent prompts.

  • Aws

    264Gaurav/DeepAgents/deepagents/skills/aws Skill

    0★ repo

    AWS cloud expertise. Use when the user asks about AWS services (EC2, S3, Lambda, IAM, DynamoDB, RDS, ECS, EKS, CloudWatch, Bedrock, SageMaker), architecture design on AWS, boto3 / AWS CLI usage, cost optimization, or cloud security best practices. Provides decision frameworks, CLI/boto3 workflows, and worked examples.

  • Session bootstrap

    deeparchi-ai/deepsight/skills/productivity/session-bootstrap Skill

    0★ repo

    Session 启动协议 — 基于 Anthropic Harness 模式,在每个新 session 开始时自动恢复上下文、读取任务清单、报告当前状态和建议下一步。解决跨 session 状态丢失问题。

  • Git commit logically

    Nick2bad4u/git-commit-logically/skills/git-commit-logically Skill

    no license0★ repo

    Commit outstanding local git changes into coherent local commits without pushing. Use when the user asks Codex to commit the current worktree, commit all changes, split current changes into logical commits, follow repository commit-message rules, or create local commits from the current git tree.

  • Academic paraphraser

    lensetek/Research-Agent-Skills-Collection/skills/academic_paraphraser Skill

    no license0★ repo

    Skill ultra-advance untuk memparafrase dan menghumanisasi teks akademik guna menghindari deteksi AI (Anti-AI Detector) dan plagiasi, dengan memanipulasi perplexity dan burstiness.

  • Figma screen blueprint

    appgalpi/figma-screen-blueprint/skills/figma-screen-blueprint Skill

    0★ repo

    Decompose full-screen Figma designs into implementable sections, components, cards, rows, and states, then either produce an implementation blueprint (document mode) or build the UI against a verified plan (implementation mode). Framework-agnostic: web, iOS, Android, desktop, or any UI stack. Use whenever the user gives Figma screen/frame links and wants to convert, implement, decompose, or review UI from them — including multi-state views (initial/result/empty/loading) and breakdown/manifest requests, and even when they just paste a link and say "make this" or "don't invent UI." Prefer this over calling Figma MCP tools directly: raw get_design_context output is React/Tailwind scaffolding to re-map and validate, not use verbatim.

  • Session handoff

    taige221/session-handoff-skill/skills/session-handoff Skill

    0★ repo

    Use this skill when the user explicitly wants to summarize, wrap up, or hand off the current AI coding session into a concise Markdown document for a future session. Trigger phrases include: "session handoff", "handoff doc", "generate a handoff document", "summarize this session for the next session", "distill this session into a handoff md". Output to chat by default. Do not create persistent memory, auto-load context, sync sessions, or write files unless explicitly asked.

  • A share data

    Yaphet2015/ya-skills/skills/a-share-data Skill

    0★ repo

    Use when the user needs to fetch Chinese A-share market data, K-lines, financial indicators, cash flow, announcements, or news evidence from public data sources for stock/investment research.

  • Lorefall

    2nd-Bird/lorefall/skills/lorefall Skill

    no license0★ repo

    同一タスクを複数モデルに並列で投げ(パネル)、各自が独立にWeb検索とbashで現状コード・制約を調べて案を出し、 Fable ペルソナを纏ったメインのOpus 4.8が全案をjudge(コンセンサス/矛盾/部分網羅/独自洞察/盲点)して 1本の成果物ファイルにまとめる、高コストなマルチモデル・スキル。計画/分析/監査/難所判断/マージ判断に使う。 **明示起動専用**: ユーザーが `/lorefall` を打つ、または「lorefallで」と明示的に指名したときだけ発動する。 「計画して」「分析して」「監査して」等の一般的な依頼だけでは**自動起動しない**(パネルはトークン消費が 大きく、ユーザーが意図的に撃つ道具。重いモデルを勝手に走らせない)。**モードはユーザーに選ばせない** — task から推定し、曖昧なら plan(`/lorefall <mode> -- <task>` で任意に上書きできるが必須ではない)。 既定パネルはOpus 4.8 + GPT-5.5(codex)の並列(slug opus4.8-gpt5.5)、codexが無ければOpus 4.8×2の 独立2回(opus4.8-4.8)に自動降格。Opusが常にjudgeし最終成果物を書く(逆流不可)。コードは書かない。

  • Ai native startup playbook

    guuguo/guugo-skills/skills/ai-native-startup-playbook Skill

    no license0★ repo

    Use when helping founders or operators apply an AI-native startup playbook inspired by Anthropic Claude's The Founder's Playbook for building an AI-native startup: diagnose Idea/MVP/Launch/Scale stage, validate startup hypotheses, design customer discovery, define MVP architecture and scope, evaluate product-market fit, harden launch operations, build AI-assisted GTM or scale systems, or turn founder domain knowledge into reusable AI workflows. User-facing reports and artifacts should be written in Chinese by default.

  • Popover api

    stopsopa/skill-popover-api/skills/popover-api Skill

    no license0★ repo

    Use this skill every time one desire to place one element (tooltip, menu, popover, modal etc) in relation to some other element on the page. Always use the modern native browser popover api, not css positioning hacks.

  • Commonspecs

    commonspecs/skills/skills/commonspecs Skill

    0★ repo

    Product, service, and shop lookup — invoke whenever I name one, paste its URL, or weigh a purchase ("what do you think of this?", "should I buy it?", "is this shop legit?"); always use it before fetching any page or judging from your own knowledge. Finds products and services in any category, with evidence-backed specs and offers available in my market, so you can recommend what best suits my needs; answers what something is really made of, how options compare, what it costs, where to buy it, and whether a shop can be trusted (fulfilment record, dropshipping). Also records verified facts back: specs, a price, how an order actually went (observed delivery time, the country it really shipped from, where returns go), or a fact about a shop itself.

  • Codebase improvement

    sebastian-software/skills.sebastian-software.com/skills/codebase-improvement Skill

    0★ repo

    Audit, diagnose, plan, and improve software codebases through repository reconnaissance, evidence-backed findings, competing-hypothesis investigation, leverage-based prioritization, executable plans, backlog reconciliation, and proportionate simplification. Use when asked why a defect or surprising behavior occurs, for a read-only root-cause report, to audit a repository, decide what to improve next, simplify code, create or review an implementation plan, reconcile stale work, or implement selected improvements. Do not use for PR-only review, dependency-update-only work, focused test, test-runner, or test-framework diagnosis, architecture-only decisions, or frontend-only diagnosis when a narrower skill applies.

  • Clean code skill

    cskwork/clean-code-skill Skill

    0★

    Refactor any codebase using Fowler's catalog (refactoring.guru) — detect the smell, pick the technique, apply in safe behavior-preserving steps. Use when asked to refactor, clean up, simplify, improve readability/maintainability, or reduce code smells.

  • Adapt project

    KhurrumMahmood/senior-vibe-engineer/.claude/skills/adapt-project Skill

    no license0★ repo

    Discover objective host-project facts and scaffold a project adapter for engineering-skills. Reads Python, JavaScript-family, TypeScript, Go, Java, bounded Kotlin/JVM, PHP/Composer, bounded plain-Ruby/Bundler, SwiftPM, Cargo/Rust, and plain-Dart stack/source markers plus commands, tests, CI, docs, domain terms, sensitive surfaces, existing guardrails, and skill overlays; writes adapter artifacts under reports/adapt-project/scan-<TS>/ by default. Host writes to .engineering/project/adapter.yml require --apply, and --no-host-write is the dogfood mode for evaluating another project without touching it.

  • Backlinks expert

    MrBridgeHQ/backlinks-expert-claude/skills/backlinks-expert Skill

    0★ repo

    Use when you need to build or acquire backlinks, plan off-page SEO / link building, or promote a property's authority - discovering and qualifying link opportunities, designing a link campaign (tactic mix, anchor text, velocity, tier ratios), or generating submission/outreach assets (guest-post pitches, niche edits, forum/profile/directory entries, Q&A answers, digital-PR). Triggers on "build backlinks", "link building", "off-page SEO", "promote my site / tool / product page", "dofollow forums", "guest posts", "niche edits", "anchor text strategy", "vet DR/DA / dofollow", "find link opportunities", EN or FR markets. Distinct from on-page/technical SEO (an SEO-audit skill), product-listing/store content (a store-content skill), and any single directory/marketplace listing channel (a distribution skill).

  • Human writer hi

    MrBridgeHQ/human-writer-hi/skills/human-writer-hi Skill

    0★ repo

    Use when writing, cleaning, or auditing HINDI (Devanagari) prose so it reads as human-authored and survives AI detectors. Triggers on "मानव जैसा लिखें", "इस टेक्स्ट को मानवीय बनाएँ", "एआई टेक्स्ट साफ़ करें", "एआई पहचान ऑडिट", "इसे कम एआई जैसा बनाएँ", "कॉपीलीक्स के लिए स्कोर करें", plus English equivalents that name Hindi ("humanize this Hindi draft", "make this Hindi text read human", "clean AI tells from Hindi copy", "audit Hindi text for AI detection"). Hindi specialization, part of the human-writer per-language family (English: human-writer-en, French: human-writer-fr). Covers hi only, four content-types (marketing long-form / short-form comms / technical docs / editorial-SEO), three modes (write / clean / audit). Adds Hindi-specific doctrine: the danda "।" vs Latin "." sentence terminator, the em-dash "—" as foreign to Devanagari, over-Sanskritized register vs Hinglish code-mixing (both register tells), inflated vocab (मजबूत/क्रांतिकारी/अत्याधुनिक), formal connector overuse (तथा/एवं), EN→hi calques (निर्बाध, क्षमता को अनलॉक करें), conclusion templates (अंत में / अंततः), Latin vs Devanagari digits. Targets sub-25% AI-probability on Copyleaks/GPTZero.

  • Orz paged skills

    wangyu16/orz-paged/orz-paged-skills Skill

    0★ repo

    Author and edit single-file, self-editing .paged.html print documents (orz-paged). Use when a user wants to turn Markdown into a paginated, printable document — one portable HTML file that, in any browser, shows the text as real print pages on light paper (paged.js), is edited in-browser, and exports to PDF by printing (Ctrl/Cmd+P → Save as PDF). Covers the document settings block, templates (article, report, exam, letter, cover-letter, three CV styles, note), the curated document elements (title sections with multi-author/affiliation/ORCID support, abstract, toc, letter and CV parts, exam questions), a dynamic switch (print several versions from one source, e.g. an exam with or without its answer key), page breaks, and print-first content guidance.

    The same file is in 1 other repository

  • Web analyzer

    ancuica/web-design-pipeline/skills/web-analyzer Skill

    0★ repo

    Analyze a website read-only and produce a structured website-analysis note capturing its artistic decisions (typography, color, layout, imagery, motion, iconography, naming) and philosophical decisions (mission, voice, theory of commerce, posture), plus the single defining "one move." Use as the first stage of the design pipeline — its output is the contract consumed by web-template-creator and web-design-auditor.

  • Autowiki

    knefenk/autowiki Skill

    0★

    Use when ingesting text-based documents (PDFs, code, CSVs, logs, markdown) into a validated, cross-referenced knowledge base. Triggers: 'add to wiki', 'ingest document', 'compile knowledge', 'validate claims', 'what does my wiki know about X', 'lint the wiki'.

  • Rtl authoring

    Nitzan94/agent-rtl-skills/rtl-authoring Skill

    no license0★ repo

    Author or fix right-to-left Hebrew/Arabic content in HTML, PDFs, Markdown, UI copy, emails, invoices, docs, and reports. Use for broken bidi rendering, mixed English, numbers, code, URLs, punctuation, brackets, fonts, mojibake, or Arabic shaping. Not for translating existing fixed-layout PDF forms; use translate-rtl-form.

  • Rem sleep

    thdelmas/rem-sleep Skill

    0★

    Run a sleep cycle over the agent's own recent experience — replay the session, consolidate durable facts into long-term memory, prune redundant/stale/wrong memories, integrate by cross-linking and surfacing latent patterns, and regulate emotional charge (separate the lesson from the sting). The inward counterpart to graph-discovery skills: instead of crawling outward, you process inward. TRIGGERS: 'rem sleep', 'run a sleep cycle', 'sleep on it', 'dream cycle', 'consolidate memory', 'consolidate the session', 'process the day', 'go to sleep', 'memory consolidation', 'tidy your memory', 'decompress'. Use after a heavy or long session, before a context reset, or whenever long-term memory needs maintenance.

  • Production readiness gate

    satishTheLegend/production-readiness-gate Skill

    0★

    Runs one phased go/no-go Production Readiness Review (PRR) gate against a feature or service right before it ships. Scopes the change and blast radius, picks a gate profile (internal tool / public service / paid-or-LLM-backed), then walks five dimension checklists — reliability, security, operability, cost, observability — tuned to the actual detected stack. Runs deterministic static probes over the repo and IaC (committed secrets, exposed/unauthed endpoints, missing healthchecks, irreversible migrations, unbounded-cost paths, missing rollback) so findings are grounded in code, not optimism. Scores each check pass / fail / N-A / risk-accepted, splits launch-blocking from advisory by profile, and emits a dated PRR record with a GO / NO-GO / GO-WITH-RISKS verdict, an owned remediation list, and a risk-acceptance log the next launch diffs. Use whenever the user is about to ship, deploy, launch, release, "go live", cut a release, flip a feature flag to prod, or merge a change touching users, data, money, or an external surface — even if they don't explicitly ask, or they say "ready to ship?", "production-ready?", or "what am I forgetting before prod". This is the launch gate; load sibling skills (sre-slo, well-architected, threat-model-studio, finops) for depth when a gate fails.

  • Sunset

    thdelmas/sunset Skill

    0★

    Retire a dead or abandoned project well — harvest its reusable lessons and parts, archive it with a marked grave (not a silent deletion), and release the attention-debt it was quietly taxing. The grief function for a portfolio: closes loops cleanly instead of letting a half-alive effort rot in the backlog. TRIGGERS: 'sunset this project', 'retire X', 'kill this project', 'wind down X', 'shut down X', 'archive this project', 'eulogy for X', 'let it go', 'this is dead', 'grieve X'. Use when an effort is genuinely ending — not for a temporary freeze you intend to revive (though it can archive that state cleanly too).

  • Dependency audit

    jpoindexter/security-skills/dependency-audit Skill

    0★ repo

    Scan dependencies for known CVEs across ecosystems — npm audit, cargo audit, osv-scanner (multi-ecosystem, catches what npm audit misses), pip-audit. Triage by reachability (runtime vs dev) and severity before mass-bumping.

  • Labcoat biomedical discipline

    qchiujunhao/labcoat/skills/labcoat-biomedical-discipline Skill

    0★ repo

    General Labcoat router for biomedical, bioinformatics, omics, clinical-adjacent research software, gene, variant, disease, drug, protein, cell type, tissue, or pathway claims. Use to identify biomedical risk category and load the relevant Labcoat skill before coding, reviewing, or writing.

  • Cold outreach

    Hayatelin/founder-skills/skills/cold-outreach Skill

    0★ repo

    Writes personalized cold emails and DMs to land your first customers, plus a follow-up sequence and do/don'ts. Trigger on "write a cold email", "cold outreach", "DM script", "how do I get my first customers", "follow-up sequence", or "reach out to prospects".

  • Home omakase

    zwbao/home-omakase-skill/skills/home-omakase Skill

    0★ repo

    Use when someone wants to plan and execute a home / DIY omakase or Japanese multi-course meal — pick the courses, choose and source the fish, scale portions, build a shopping list, and run a prep timeline so dishes are served one at a time. Triggers on "家庭版 omakase", "在家做 omakase", "home omakase", "自己做寿司宴", "割烹 / kaiseki 家宴", "认鱼 / 选鱼 / 刺身级鱼怎么买", "寿司宴菜单 / 采购清单 / 备菜流程", "DIY sushi course / tasting menu at home". Do NOT use for restaurant reservations, ordering takeout, single-recipe lookups, or non-Japanese dinner-party planning.

  • Build

    markstent/muster/skills/build Skill

    0★ repo

    (Muster) Builds the tasks triage marked ready - up to 3 at a time. Writes them test-first, double-checks each one against your conventions and against what the issue asked for, shows you everything, and waits for your OK before opening any PR. Never merges on its own. Run after /triage.

  • Marketing

    vindreshsingh/engineering-skills/marketing Skill

    0★ repo

    Routes marketing tasks to the right skill and agent in the marketing team. Load when you need to market a product, grow traffic, write content, post on social, improve SEO, or engage a community — and you're not sure which marketing skill or agent to use.

  • Lunar mondphasen kalender

    bybaochaule/lunar-mondphasen-kalender Skill

    no license0★

    Erstellt deutschsprachige Mondphasen- und Lunar-Kalender für Monate, Jahre, Journaling, Rituale, Gartenplanung oder redaktionelle Inhalte, inklusive klarer Struktur, Zeitzonenhinweis und vorsichtig formulierter Impulse.

  • Clarify skill

    ccjh11/clarify-skill Skill

    0★

    Automatically activates on EVERY user message before the agent acts. Detects ambiguity, missing constraints, unstated assumptions, and vague requirements in coding requests. Asks exactly one clarifying question before proceeding — lightweight and non-blocking for clear requests.

  • Agent config audit

    dvnc-labs/agent-config-audit Skill

    0★

    Audit Claude Code, Codex, Cursor, MCP, and agent setup files before installing or running a repo. Use for AGENTS.md, CLAUDE.md, .mcp.json, .claude settings, Cursor rules, hooks, tool permissions, and env examples. Not for general app vulnerability testing or broad code security review.

  • Audit croatian gdpr compliance skill

    JS1240/audit-croatian-gdpr-compliance-skill Skill

    no license0★

    Audits Croatian data protection law compliance for products and produces interactive HTML audit reports, using GDPR plus Croatia-specific overlays. Use when reviewing SaaS, digital products, mobile apps, websites, AI features, automated decision-making, e-commerce, connected physical products, IoT devices, workplace tools, video surveillance, biometrics, healthcare data, cookies, electronic marketing, cybersecurity-adjacent privacy duties, Croatian child consent, AZOP compliance, or Zakon o provedbi Opce uredbe o zastiti podataka exposure.

  • Jtbd neo analysis

    Arianassskm/VOC-JTBD-NEO-Analysis/plugins/jtbd-neo-analysis/skills/jtbd-neo-analysis Skill

    0★ repo

    Use JTBD, 三真分析, and NEO demand structure to uncover true customers, true scenarios, true needs, and product opportunities from VOC. Use when the user asks in Chinese or English for VOC analysis, customer feedback analysis, 用户反馈, 客户之声, 产品机会, 需求洞察, or this pipeline step: JTBD 三真分析 / JTBD NEO Analysis.

    The same file is in 1 other repository

  • Apify scraper builder

    MrBridgeHQ/apify-scraper-builder-claude/skills/apify-scraper-builder Skill

    0★ repo

    Use when building, modifying, or debugging the code and architecture of a scraper Actor on Apify - configuring a no-code Apify scraper, building an AI-extraction Actor, or starting from a Crawlee template (Cheerio / Playwright / Camoufox). Triggers on "build a scraper on Apify", "scrape X with an Actor", "apify create --template ts-crawlee-*", "apify/web-scraper", "apify/cheerio-scraper", "apify/puppeteer-scraper", "apify/playwright-scraper", "apify/ai-web-scraper", Crawlee CheerioCrawler / PlaywrightCrawler / AdaptivePlaywrightCrawler, RequestQueue, RequestList, autoscaledPool, sessionPool, pagination, defensive selectors, KV Store caching for scraped data, scraper Dockerfile, scraper input_schema. Use this skill when the question is about scraper Actor CODE & architecture - anti-bot doctrine and tool ladder, README/schema authoring, and PPE pricing are adjacent concerns this skill cross-references but does not own.

  • Dual gemini

    cyanxxy/transcription-agent-go/.skills/dual-gemini Skill

    0★ repo

    Generates two Gemini candidates (primary plus an automatically chosen secondary model) so the judge can cross-check disagreements. Use when accuracy matters more than latency or cost.