agentsclimarketplace

The catalog

609,856 rows, by stacks then stars

  • Tufte aesthetics and technique

    jpoindexter/tufte-skills/skills/tufte-aesthetics-and-technique Skill

    2★ repo

    Edward Tufte's visual design principles as agent skills — 38 skills plus a router that picks them for you. Works in Claude Code, Codex, Copilot, Gemini, or any agent that can read a file. Every claim verified page-by-page against all five books.

  • AI SKILL davinci resolve

    LevyBytes/AI-SKILL-davinci-resolve Skill

    2★

    Use when working in DaVinci Resolve (the Blackmagic Design editing, color, VFX, and audio app): the Media, Cut, Edit, Fusion, Color, Fairlight, and Deliver pages; importing and managing media, proxies, and the Media Pool; timelines, editing tools, trimming, transitions, retiming, and keyframing in the Inspector; color grading (primaries, curves, qualifiers, power windows, tracking, nodes, scopes, color management RCM/ACES, LUTs); Resolve FX and OpenFX; Fusion compositing and the node editor; Fairlight audio editing, mixing, and effects; rendering and export on the Deliver page; project/database management, collaboration, and Blackmagic Cloud. Covers the DaVinci Resolve 20.3 Reference Manual plus the DaVinci Resolve 21 New Features Guide. Use this when answering how to do something in Resolve, what a control/menu/parameter does, keyboard shortcuts, or which page/panel a feature lives in. Not for other NLEs (Premiere, Final Cut, Avid).

  • AI SKILL gimp

    LevyBytes/AI-SKILL-gimp Skill

    2★

    Use when working with GIMP, the GNU Image Manipulation Program (especially GIMP 3.2) - editing or generating raster images; working with layers, layer/blend modes, masks, channels, selections, or Bézier paths; applying tools or filters; adjusting colors, levels, curves, or ICC color profiles; importing or exporting image files (.xcf, PNG, JPEG); or automating GIMP through Script-Fu, Python-Fu, the Script-Fu Console, or the Procedural Database (PDB) - including driving GIMP from a GIMP MCP server or a headless/batch (gimp -i -b) run. Also fires when you see .xcf files, gimp-* procedure calls, script-fu-register, "from gi.repository import Gimp", or GObject-Introspection GIMP plug-ins, even when the user never says "GIMP" by name. Gives task-routed, faithful 3.2 reference with worked examples.

  • Cli first decision

    High-cla/multi-skilled-repository/skills/cli-first-decision Skill

    2★ repo

    AI Agent Skills 合集 — CMD+PowerShell 避坑指南 · CLI 优先决策矩阵 · 更多技能持续添加

  • Ganhuo geo engineer

    yuanyuanyuan430/ganhuo-geo-skill/skills/ganhuo-geo-engineer Skill

    2★ repo

    Use this Skill when the user provides an existing article, product page, tutorial, FAQ, or knowledge note and wants to rebuild it into a GEO or AI-search-friendly content asset. Use it for old-content refresh, citation-readiness improvement, answer-first restructuring, GEO upgrades, and Ganhuo AI content workflows. Do not use it for topic-only drafting, fabricated statistics, ranking guarantees, keyword stuffing, legal compliance audits, or GEOFlow system operations.

  • Wassenger ai agent

    wassengerhq/whatsapp-skills/skills/wassenger-ai-agent Skill

    2★ repo

    Build a production-grade AI agent that answers your customers on WhatsApp with Wassenger — an LLM (OpenAI/Claude) replies to inbound messages inside the 24-hour window, with a hard human handoff for sensitive or low-confidence cases, idempotent webhook handling, opt-out, and a kill switch. Use when the user wants an "AI chatbot / assistant / auto-responder" that handles FAQs, qualifies leads, and covers after-hours on WhatsApp — and wants it safe enough to put in front of real customers, not a naive autonomous bot.

  • Before git push

    host452b/polish/skills/before-git-push Skill

    no license2★ repo

    Use before running git push, or when the user asks to push / ship / deploy / 上线 / 推送 changes that could reach production — a final risk gate to catch what is most likely to break prod before code leaves the local machine. Triggers - "push this / ship it / ready to push? / 可以 push 了吗 / 上线前检查 / 这次改动能推吗", pre-push review, pre-release gate, production safety, don't break prod, rollback readiness, feature toggle.

  • Wavedash

    wvdsh/ai/providers/claude/plugin/skills/wavedash Skill

    2★ repo

    Use when building, integrating, testing, uploading, publishing, or preparing a browser game for Wavedash, including CLI setup, Wavedash SDK features, multiplayer, achievements, leaderboards, cloud saves, player identity, user-generated content, store metadata, monetization, and content guidelines.

  • Sift memory

    roccodaffuso/sift/.agents/skills/sift-memory Skill

    2★ repo

    Use this skill when an agent needs local historical context from AI coding assistant sessions, prior project conversations, debugging history, implementation decisions, or user asks to search Claude Code, Codex, or Cursor chat history. It teaches agents to use the local-only `sift` CLI for indexed full-text search across Claude Code, Codex, and Cursor logs without network calls.

  • Apex review

    gvago/unofficial-qodo-review-skills/skills/apex-review Skill

    2★ repo

    Use when a PR diff adds or modifies Salesforce Apex (.cls / .trigger) or SOQL/SOSL — flags governor-limit killers (SOQL/DML inside loops), missing CRUD/FLS & sharing enforcement, SOQL injection, hardcoded IDs, trigger anti-patterns, and swallowed exceptions in the CHANGED code only. Skip for non-Apex diffs.

  • Draft response

    latent-variable/agentscope/skills/draft-response Skill

    2★ repo

    Draft a response on the user's behalf for github, forums, or any external platform. Always present the draft for approval before posting.

  • Principal architect review

    satishTheLegend/principal-architect-review Skill

    2★

    Acts as a principal/staff engineer architecture review board for a solo or small-team operator: reverse-engineers a C4 model of the codebase, forces Architecture Decision Records (with >=2 real alternatives + consequences), runs an adversarial reviewer that pressure-tests designs, and — the core — derives evolutionary-architecture FITNESS FUNCTIONS and wires them into CI so layering/coupling/cycle/size drift is caught mechanically forever. Maintains an append-only decision ledger as the system-of-record for "why we built it this way." Use whenever the user adds a new dependency, datastore, service boundary, protocol, or framework; designs/refactors a module or system; writes or edits an ADR/RFC/design doc; sets up or fixes CI architecture checks; or asks "is this a good design?", "what are the tradeoffs?", "will this scale?", "review my architecture", or "has the architecture drifted?" — even if they don't explicitly ask for an architecture review. Also use proactively before merging a structurally significant change. Composes with (does not replace) quality-attribute, planning, and threat-modeling skills.

  • Sql aggregation and grouping

    ctoth/sql-skills-plugin/plugins/sql/skills/sql-aggregation-and-grouping Skill

    no license2★ repo

    32 agent skills for writing correct, portable, modern standard SQL (ISO/IEC 9075) — vendor-neutral, with per-feature portability across PostgreSQL, MySQL/MariaDB, SQLite, and more.

  • Nestjs architecture principles

    benedya/nestjs-skills/skills/nestjs-architecture-principles Skill

    no license2★ repo

    Architecture and coding conventions for this NestJS + TypeORM backend: request-flow layering (controller → service → repository → entity), module boundaries, SOLID / DRY / single-responsibility, service and business-logic patterns, dependency injection, TypeORM entities and custom repositories, DTOs, file/import organization, and testing strategy. Use when designing, adding, or editing any module, controller, service, repository, or entity, or when deciding where code should go, how to structure a module, name files, inject dependencies, define entities/columns/indexes, write queries, or expose data safely. Trigger on phrases like "add a service/module/entity/controller", "business logic", "inject a dependency", "custom repository", "extend Repository", "query builder", "which layer", "where should this go", "new table", "add a column", or any work under controllers/, services/, repositories/, entities/, or dtos/.

  • Ylf coding standards

    yaolifeng0629/ylf-agent-skills/skills/ylf-coding-standards Skill

    2★ repo

    Apply compact YLF engineering discipline to the current task. Use when the user explicitly asks for YLF coding standards, wants a concise AGENTS/CLAUDE-style rule set applied to one task, or asks the agent to follow disciplined coding rules before making code changes.

  • Cotend collaboration

    lhh1301506137/CoTend/skills/cotend-collaboration Skill

    2★ repo

    Use for governed Codex/Claude collaboration: Codex primary + CodexSelf review by default, dev-high local fast mode for confirmed personal/local projects, human-led delegated continuous development, idea-to-consensus intake, user interruption/new idea reconciliation, delegated mission/batch contracts, claim-to-evidence summaries, STATUS user cockpit, user acceptance walkthroughs, Plan Tree + user-readable expanded understanding, PROJECT-DECISION-LOG, PROJECT-KNOWLEDGE-CHANGELOG, post-init checks, upstream dependency review, official skill-creator companion quality gate, framework-change evaluation with mechanism budget, local closeout plus Trellis finish/archive/journal, critical-risk stop boundaries, Claude/Gemini review triggers, Trellis active/dormant coordination, cotend-project-init routing, CodeGraph/Code Context Harness, Acceptance/Test Harness with Playwright/browser/Chrome routing, Harness Ratchet, Done Gate, intent drift review, Release Hardening, AI UAT, and Quality Sentinel.

  • Aiogram architecture refactor

    ballisarium/aiogram-bot-skills/skills/aiogram-architecture-refactor Skill

    2★ repo

    use for a deliberate, bounded aiogram bot refactor; рефакторинг, move handler logic, split routers, services, keyboards, texts, i18n, repositories.

  • Okf domain elicit

    NickMoignard/okf-domain-elicit Skill

    2★

    Conduct a structured, resumable domain-elicitation interview and emit an OKF knowledge bundle (ubiquitous language, tri-temporal domain events, business rules, context map) as you go. Use when the user wants to map a domain, elicit domain knowledge from a non-technical stakeholder, run a domain-discovery or event-storming session, or when another skill needs to drive a resumable domain interview.

  • Slide story architect

    linxumoney/slide-story-architect/skills/slide-story-architect Skill

    2★ repo

    把资料、文档、研究或想法整理成面向特定观众和决策的演示文稿叙事骨架,生成每页唯一任务、结论式标题、证据、视觉形式和讲者过渡。适用于汇报大纲、路演结构、课程幻灯片、提案、PPT 改稿和“这些内容该怎么讲”。

  • Change review

    marinsokol5/change-review/skills/change-review Skill

    2★ repo

    Open an interactive human review of proposed file changes. The user sees an inline diff in their browser, leaves line comments, and returns a verdict (approve / request_changes / reject) printed as JSON on stdout. Use before applying substantive or risky changes, whenever the user asks to review a change ("let me review", "show me the diff", "open a review"), or to re-review after addressing feedback. Can also open existing files with no diff for line-comment annotation ("let me annotate", "I want to comment on the code") — the user's comments become the spec, and your edits come back as round 2 of the same review.

  • Langgraph docs

    sw30labs/oscal-skills-guardrails/examples/skills/langgraph-docs Skill

    2★ repo

    Use this skill for requests related to LangGraph to fetch relevant documentation and provide accurate, up-to-date guidance. Trigger when the user asks about LangGraph concepts, APIs, or middleware.

  • Tu vi dau so research

    duandigi/tu-vi-dau-so-research Skill

    2★

    Nghiên cứu và luận giải Tử Vi Đẩu Số Việt Nam theo phương pháp đối chiếu nhiều tầng. Dùng khi cần chuẩn hóa lá số, luận Mệnh–Thân–Cục, tam phương tứ chính, tứ hóa, đại vận/lưu niên, phân tích sự nghiệp–tài chính–hôn nhân–gia đình, hiệu chỉnh giờ sinh, so sánh trường phái, nghiệm lý hoặc phản biện một bản luận. Bắt buộc truy vết chứng cứ, nêu phản chứng và tránh phán theo một sao.

  • Ai search visibility

    liftli-ai/skills/skills/ai-search-visibility Skill

    2★ repo

    Use when the user asks whether ChatGPT, Claude, or Perplexity can find or cite them, or wants a personal GEO / AI-search-visibility audit — runs ~12 checks across Presence, Consistency, and Citability, and returns a verdict tier (Invisible / Fragments / Citable) with next actions.

  • Plg growth council

    lmanchu/council-forge/examples/plg-growth-council Skill

    2★ repo

    PLG Growth Council — three thinkers for recurring product-led growth decisions: Elena Verna (DIAGNOSIS: activation and retention forensics — is this an acquisition problem or an activation problem), Brian Balfour (ARCHITECTURE: growth loop design — loops compound, funnels decay), Lenny Rachitsky (BENCHMARK: cross-company calibration — is this number actually good for your stage and category). Rotating fourth seat: Casey Winters (SCALE: network-effect growth and scaling a growth org past its first wedge). Use for: diagnosing a stalled activation funnel, deciding whether a growth idea is a real loop or a funnel wearing loop language, calibrating whether a retention/activation number is actually good, designing a north star metric, planning when to build a dedicated growth team, and scaling growth past an initial product wedge. Run `/plg-growth-council sync` to refresh all four seats' current public positions before convening on anything time-sensitive. Trigger on: activation, retention, onboarding, PLG, product-led growth, growth loop, funnel, D1, D7, D30, cohort, churn, aha moment, north star metric, self-serve, freemium, viral loop, referral loop, network effects, growth team, "is this good", benchmark, time-to-value — even without /plg-growth-council.

  • Ip detector

    eligapris/ip-detector/.agents/skills/ip-detector Skill

    no license2★ repo

    Brutal, numbers-first IP detector that mines a codebase or technical write-up for genuinely fileable intellectual property. Runs heavy web research against USPTO, Google Patents, WIPO, EPO, Google Scholar, GitHub, and arXiv; classifies the concept as patent, copyright, trademark, or trade secret; scores it on five numeric dimensions (Novelty, Non-obviousness, Industrial Applicability, Defensibility, Market Value); projects 5-year and 10-year market size with cited CAGR and full filing+maintenance cost across US/EU/CN/JP/KR; then emits a surgical PDF dossier with a one-line verdict — FILE, BORDERLINE, or DO NOT FILE. Use this skill whenever the user mentions patents, IP, intellectual property, filing, prior art, novelty, trade secrets, copyrightable code, trademark, defensibility, IP strategy, monetization of an idea, or asks whether a codebase, algorithm, whitepaper, or technical concept is worth protecting. The point is to talk the user OUT of filing when evidence does not support it.

  • Programasweights

    tolimcn7786/skills/skills/programasweights Skill

    2★ repo

    Compile a natural-language spec into a tiny neural function that runs locally with ProgramAsWeights (PAW). Use it for fuzzy text-in / text-out tasks that a regex can't handle but that are too slow, costly, or overkill to send to a full LLM on every item - classify, categorize, label, or tag text (sentiment, urgency, intent, topic, spam, support tickets, ALERT vs QUIET log lines); extract fields from messy text (emails, names, dates, IDs, invoice numbers); repair or normalize formats (broken JSON, dates); fuzzy or typo-tolerant matching, near-duplicate detection, and deduplication; map a misspelled value to the closest option; semantic search; log and error triage; and intent routing. Compile once on the hosted API, then run the function locally and offline via the Python or browser/JavaScript SDK; cheaper and faster than calling a large model per item. Not for long-form generation, open-ended chat, writing code, or multi-step reasoning.

  • Skill reviewer

    annost/skill-reviewer Skill

    2★

    Review another Claude skill (its SKILL.md and bundled files) or a slash command (.claude/commands/) for skill smells — research-backed authoring anti-patterns — and best-practice violations, then produce an inline report with severity-ranked findings and concrete fixes, offer to apply them, and run a feedback loop that logs lessons and improves this reviewer itself. Use whenever the user wants to review, audit, critique, lint, quality-check, or improve a skill or command named by the user (e.g. "review my find-invoices skill", "review my /deploy command", "check this skill for problems", "audit the SKILL.md", "is my skill any good"), or asks about skill smells or skill quality. Works in any repo.

  • Davinci resolve skill

    odaiouattara0022-del/davinci-resolve-skill Skill

    2★

    Use when editing video in DaVinci Resolve - building timelines, cutting clips, importing media, color grading, applying LUTs or CDLs, adding titles or subtitles, auto-cutting silences, managing render queues, or automating any Resolve post-production task via its Python scripting API. Triggers include "DaVinci", "Resolve", "timeline", "media pool", "color grade", "render", "auto captions", "Text+".

  • Build seedance2 prompts

    mqrox/seedance-2.0-prompt-skill/build-seedance2-prompts Skill

    2★ repo

    Build, rewrite, diagnose, or validate production-ready prompts specifically for ByteDance Dreamina/Doubao Seedance 2.0 Standard, including text-to-video, image-to-video, first/last-frame animation, multimodal image/video/audio references, dialogue and sound, multi-shot narratives, video editing, extension, and clip transitions. Use whenever the user mentions Seedance 2.0, Seedance2, Dreamina 2.0, Doubao video, @Image/@Video/@Audio references, or asks for a Seedance-ready video prompt; also use when adapting a creative brief, storyboard, script, image, video, audio asset, or API content array into Seedance 2.0 syntax. Do not use for Seedance 1.x or generic cross-model prompting unless the user also needs a Seedance 2.0 version.

  • Todo archive review

    wensente9682/notion-work-organizer/skills/todo-archive-review Skill

    2★ repo

    Use when the user says "organize todo-test", "organize todo", asks to review/archive/整理 Notion to-do records by category with ok/dismiss/skip/undo approval, or asks to setup/adopt/configure a Notion personal work maintenance system. Supports existing organize workflows plus guarded setup/adopt routing. Normal Codex use does not require or store a Notion API token; use the Notion connector tools available to Codex.

  • Repoglyph

    remsky/repoglyph-py/plugin/skills/repoglyph Skill

    2★ repo

    Generate isometric repo-city banners and OKF structural context bundles from a local git clone with the repoglyph CLI. Use when the user wants a repo banner image, a codebase map, an agent-readable repo summary, or a self-updating repo-map skill.

  • Content score and fix cn

    caoproAI/content-score-and-fix-cn Skill

    no license2★

    检查并改好面向中国用户的短视频脚本、口播稿、标题、发布文案、商品内容、封面图和 60 秒内短视频。用于电商经营者、企业自媒体、个人 IP 和个人自媒体提交一份真实内容,询问能不能发、为什么没人看、开头是否吸引人、传播和行动可能性如何、封面或成片怎样修改时。按留人、好奇、看懂、信任、传播、行动六项给出带证据的内容体检;材料足够时给总分,材料不足时只检查能看见的部分。必须交付可直接使用的修改稿,不预测实际流量、销量或收益。

  • Brainstorm

    matvej-melikhov/karpathy-llm-wiki/.claude/skills/brainstorm Skill

    2★ repo

    Запускает brainstorm-сессию по заданной теме (или bridge-gap паре далёких страниц), модерирует поток тезисов пользователя через продвигающие вопросы и в конце склеивает permanent note (тип `mind`) из реплик пользователя дословно. Один цикл = один источник в `raw/brainstorm/` + одна или больше страница в `wiki/minds/`. Реализация ножки Mind Mapping из гибридного фреймворка организации знаний. Триггеры: /brainstorm, "поразмышляем", "хочу подумать про X", "брейнсторм", "давай развей мысль".

  • Reify

    srinitude/skills/skills/reify Skill

    2★ repo

    Use when a vague idea, stray thought, remembered fragment, or uncertain direction needs to become a concrete outcome, tested design, decision record, artifact, or executable handoff.

  • Abogacia argentina

    Bitcoindefi/agente-smith/skills/abogacia-argentina Skill

    no license2★ repo

    Punto de entrada para práctica jurídica argentina: fija las reglas de operación (jurisdicción primero, fuente primaria SAIJ, marcadores de verificación pendiente, alerta normativa, cómputo diferenciado de plazos) y rutea por área del derecho (laboral, civil, penal, familia, consumidor, societario, administrativo, previsional, tributario, tránsito, faltas municipales, protección de datos) hacia sus ejes normativos y las sub-skills plazos/diagnóstico/bucles. Usar en cualquier consulta o trabajo de abogacía bajo derecho argentino.

  • Marc principles

    meunomeebero/marc-principles Skill

    2★

    Apply a paraphrased 32-principle Marc Lou viral-product lens to product design, landing pages, dashboards, onboarding, pricing, naming, CTAs, social proof, demos, copy, and sharing. Use when the user mentions Marc principles, Mark principles, viral product, cognitive biases, vieses cognitivos, memorable or shareable design, one idea per screen, simplifying hierarchy, or asks for a product/CRO/design critique. Treat these as provocative heuristics, never as automatic policy: product evidence, accessibility, truth, ethics, and the host product's explicit strategy win conflicts.

  • Sansheng distill

    Kiasma1/sansheng-distill/skills/sansheng-distill Skill

    2★ repo

    书籍/视频系列蒸馏引擎 -- 输入一本书的电子全文(epub/pdf/txt/azw3/mobi),或一组视频 (YouTube/B站,单视频按 1 集系列处理),产出单文件交互 HTML 蒸馏页(浏览型): 五板块(全书速览/逐章精读/批判与评价/行动清单/延伸阅读)= 凝练地图 + 详实正文 + 页内二级视图; 书魂可视化并入①,金句墙并入②,同类书内联板块⑤。 四源融合方法论(李继刚三轮压缩 + 决策规则 + 心智模型 + 批判段)两遍蒸馏(Pass1 压缩骨架 + Pass2 详实转述) + 可交互脑图(点节点跳章节/集数)+ 联网增补两张页内子视图(作者页/观点对照页,全带来源;同类书内联板块⑤) + 跨书跨作品知识索引互链(越蒸越富)。 Triggers on 蒸馏这本书 / 书籍蒸馏 / 拆书 / 拆这本书 / 蒸一本书 / 把这本书做成蒸馏页 / book distill / 蒸馏这个系列 / 视频蒸馏 / 蒸馏这个UP主 / 蒸馏这几个视频 / 把这个系列做成蒸馏页。 批量多本先抽样 1 本验收再并行铺量(6本/批串行)。 Do not use for: 写文章、做口播视频成片、只要视频字幕/摘要而不做蒸馏、网站页面维护。

  • Industry research

    DoomDeity/new-media-core-skills/skills/01-research-insight/R01-industry-research/dist/standard/industry-research Skill

    no license2★ repo

    研究行业格局、产业链结构、主要玩家、趋势与机会/风险。当用户要评估是否进入某行业、寻找市场机会或做行业竞调时使用。不虚构市场规模等量化数据;无可靠来源与估算方法时不输出市场量级。

  • Adjudicate review

    JacobStephens2/skills/adjudicate-review Skill

    2★ repo

    Adjudicate a review

  • Skill craft review

    MuhammadBahaa/majarrah-marketplace/plugins/skill-craft/skills/skill-craft-review Skill

    2★ repo

    Use when reviewing, auditing, or giving feedback on an agent skill (SKILL.md file), slash command, or plugin — before merging or publishing one, when a skill never triggers, misfires, or bloats context, or when asked whether a skill or plugin is well designed, safe to approve, or ready to ship.

  • Openshift api

    msilich/openshift-skill/.agents/skills/openshift-api Skill

    2★ repo

    Discover and verify Kubernetes and OpenShift API resources, served group versions, fields, and CRD schemas from the target cluster. Use before creating or reviewing manifests, choosing apiVersion/kind pairs, diagnosing rejected fields, or calling generic oc or MCP resource operations when the exact live API schema matters.

  • Swift cycle

    Solismuchengxue/skill_swift_cycle/skills/swift-cycle Skill

    2★ repo

    Manual-invocation workflow for lightweight governance of personal and small software projects. Use only when the user explicitly invokes swift-cycle to initialize or review README, DESIGN, AGENTS, local TODO and DEVLOG, shared docs, candidate evaluations, ADR decisions, documentation drift, or project closeout. Keep small local changes fast and avoid heavyweight process.

  • Schedulala

    schedulala/schedulala-agent/skills/schedulala Skill

    2★ repo

    Install, connect, and use Schedulala to schedule and publish social media posts to 12 platforms (Twitter/X, Instagram, TikTok, LinkedIn, YouTube, Facebook, Threads, Bluesky, Pinterest, Mastodon, Telegram, Google Business Profile). Use when the user asks to install or set up Schedulala, or wants to create, schedule, preview, or bulk-plan social posts, post photos/videos/PDFs, auto-post a first comment (link-in-first-comment), check post status or analytics, reply to or moderate comments, monitor keywords, or repurpose YouTube videos. Works through the schedulala CLI (any agent with a shell), the hosted MCP connector (claude.ai / ChatGPT, with interactive widgets), or the local @schedulala/mcp-server (Claude Desktop, Claude Code, Cursor, OpenClaw). Encodes key setup, the per-platform rules (TikTok privacy + postMode, Instagram media, YouTube titles, Pinterest boards, character limits), and the safe workflow draft → validate/preview → confirm → publish → verify.

  • Data analyst guide

    genapohub/data-analyst-guide Skill

    2★

    数据分析师方案产出指南。当用户提出数据分析需求、需要产出分析方案时触发。覆盖场景:数据体系搭建、专项分析报告、指标波动归因、数据基础设施升级、探索性分析。先识别需求属于5类场景中的哪一类(0到1数据体系搭建/中大型分析需求/小分析临时取数/数据基础设施升级/数据探索洞察),再按对应场景的产出清单生成完整方案。

  • Data schema design

    Yuuzulight/db-artisan/skills/data-schema-design Skill

    2★ repo

    Generate production-grade SQL schemas with proper indexing, partitioning, constraints, and performance considerations for Postgres, Snowflake, and BigQuery.

  • Zheng qinan skill

    88lin/zheng-qinan-skill Skill

    2★

    Use this skill when the user wants to locate, quote, compare, or study passages from Zheng Qin'an's three books: 医理真传 / 醫理真傳, 医法圆通 / 醫法圓通, and 伤寒恒论 / 傷寒恆論. Trigger for searches by formula, symptom term, theory, book section, Shanghan clause, or stable doc ID, including 郑钦安 / 鄭欽安, 火神派, 扶阳, 元阳元阴, 坎中一阳, 白通汤, 四逆汤, 潜阳丹, 封髓丹, and related historical-text questions. This is a textual-retrieval and historical-study skill only. Do not use it to diagnose, choose treatment, prescribe, provide dosage or preparation instructions, or decide whether a formula fits a person.

  • Arr connect

    t3chnaztea/arr-stack-skills/skills/arr-connect Skill

    2★ repo

    Use when pointing a coding agent at Radarr, Sonarr, Prowlarr, or a *arr companion for the first time or in a fresh session: "connect to Radarr", "talk to Sonarr's API", find the API key, hit /api/v3, check whether a movie or show is already in the library, confirm a title has a file on disk, work out why an API write reported success but changed nothing, or why `ls` on the server says the media folder does not exist. Covers the API-key lanes, the v3 endpoint map, the container-path trap, the read-after-write rule, and identifier-based existence checks. Foundation skill: every other arr-* skill assumes its connection pattern and doctrine. Not for quality profile design (arr-quality-profiles) or building the instance inventory (arr-context-map).

  • Skill atlas

    Jorgut/skill-atlas Skill

    2★

    Audit, discover, recommend, orchestrate, monitor, and safely manage agent skills across Codex, OpenCode, Claude-style agents, plugin caches, and configurable skill roots. Use when the user wants to inventory installed skills, detect duplicates or symlinks, check upstream freshness, compare public alternatives once or periodically, review third-party skill safety, plan cross-platform consolidation, describe a product or professional task and ask which skills should be combined, compare current AI models for a workflow, or find skills and connectors for software such as design, HMI, animation, CAD, and 3D modeling tools. The skill is platform-neutral and local-aware. It reports and recommends before acting; it must not overwrite, delete, symlink, install, or upgrade skills without explicit confirmation.

  • Workbuddy dream skin skill

    TimekeeperXY/workbuddy-dream-skin-skill Skill

    no license2★

    Design, generate, apply, verify, repair, update, and restore complete personalized skins for the Windows WorkBuddy desktop app without modifying app.asar. Use when users ask for WorkBuddy UI beautification, custom themes or backgrounds, character/IP skins, CSS injection, persistent local theme launchers, fixing frozen assistant/input/account interactions after injection, correcting misplaced model/workspace/account menus, reapplying a skin after restart or update, or safely returning to the original WorkBuddy appearance.

  • Create routable skill

    Ninaix0217/create-routable-skill/skill/create-routable-skill Skill

    2★ repo

    Design, audit, or repair routing contracts for Codex skills using concrete trigger scenarios, explicit exclusions, distinctions from similar skills, progressive-disclosure resources, and routing evaluation cases. Use when a user explicitly wants reliable Skill selection, reports missed or false triggers, needs catalog conflict analysis, or asks for routing regression tests. Do not use for ordinary Skill creation without routing requirements, executing or installing an existing Skill, creating a plugin, or implementing a runtime embedding-based router.

  • Matt auto

    DestinySail/matt-trellis/templates/matt-auto Skill

    2★ repo

    MUST use for any non-trivial software engineering request in a repository. Automatically routes natural-language requests to the appropriate Matt Pocock skills and composes them with Trellis, so the user never needs to type skill names. Covers new features, unclear requirements, bugs, TDD, architecture, prototypes, research, PRDs, issue breakdown, triage, teaching, and handoffs.

  • Frontend responsive design

    ryanbaumann/fieldwork/.agents/skills/frontend-responsive-design Skill

    2★ repo

    Design and review responsive frontend layouts, styling, accessibility, interaction behavior, Tailwind usage, and visual QA for the portfolio and demo apps. Use before changing layout, CSS, semantic HTML, map controls, responsive behavior, or other perceptible frontend interactions.

  • Add helm chart

    makigjuro/cloudstack-ai-plugins/plugins/cloud-infra/skills/add-helm-chart Skill

    2★ repo

    Scaffold a new Helm chart with standard templates and values. Use when deploying a new microservice or component to Kubernetes and it needs its own chart.

  • Agent designer

    bob798/ai-skill-kit/ai-engineering/agent-designer Skill

    no license2★ repo

    AI Agent 架构设计 Skill。当用户提到"帮我设计一个 Agent"、"多步骤任务自动化"、"ReAct 怎么实现"、"Agent 怎么用工具"、"多 Agent 协作"、"Agent 老是陷入循环"、"工具调用失败怎么处理"时触发。适用于 Agent 系统设计、面试 Agent 架构考题、生产级 Agent 工程实现。

  • Pdflatex skill

    b1rd33/pdflatex-skill Skill

    2★

    Professional LaTeX document compilation skill for creating publication-quality PDFs. Supports pdflatex, xelatex, lualatex engines with full bibliography chains (BibTeX/Biber), smart cross-referencing (cleveref), publication-quality tables (booktabs/siunitx), and automated builds (latexmk). MANDATORY TRIGGERS: LaTeX, pdflatex, xelatex, lualatex, .tex file, compile LaTeX, research paper, academic paper, journal article, thesis, dissertation, conference paper, BibTeX, Biber, biblatex, bibliography, citations, documentclass, beamer presentation, equations, mathematical notation, academic writing, paper submission, ACM template, IEEE template, Springer, Elsevier, arXiv, LaTeX invoice, LaTeX CV, LaTeX resume, LaTeX letter, LaTeX report, LaTeX certificate, typesetting, latexmk, fontspec

  • Excalidraw diagram

    twotwo/obsidian-skills/.skills/excalidraw-diagram Skill

    2★ repo

    Generate Excalidraw diagrams from text content for Obsidian. Use when user asks to create diagrams, flowcharts, mind maps, or visual representations in Excalidraw format. Triggers on "Excalidraw", "画图", "流程图", "思维导图", "可视化", "diagram".

  • Flutter design

    obiwancenobi/klamben/build/.claude/skills/flutter-design Skill

    2★ repo

    Use when writing, reviewing, or refactoring Flutter mobile UI code. Teaches Flutter-specific design principles (Material 3 + Cupertino adaptive), type scales, theming, spacing grids, motion, interaction, responsive layout, and UX writing. Prevents common Flutter AI-slop patterns like hardcoded Colors.purple, missing SafeArea, nested Container/Padding chains, Material widgets on iOS paths, missing const, and absent semantic labels.

  • Claudeemailmarketing

    Sequenzy/skills/skills/claudeemailmarketing Skill

    2★ repo

    Use when Codex, Hermes, OpenClaw, Claude Code, Cowork, or another AI agent needs to plan, review, implement, audit, or improve email work focused on Claude-assisted positioning, segmentation, lifecycle content, and marketing review systems. Triggers include requests about offer refinement, segment-specific messaging, lifecycle copy reviews, positioning tests, and campaign strategy.

    The same file is in 1 other repository

  • Skill autopilot

    deepshal99/skill-autopilot/skill-autopilot Skill

    2★ repo

    ALWAYS-ON universal skill router for every project and every message. Classifies user intent, resolves duplicate skills to the best variant, chains multi-skill workflows in correct order, and discovers missing skills online. Ensures no relevant skill is ever skipped. Complements superpowers:using-superpowers with concrete routing logic, dedup rules, and discovery.

  • Next forge

    broomva/symphony-forge/skills/next-forge Skill

    2★ repo

    Expert assistance for next-forge — a production-grade Turborepo template for Next.js SaaS apps. Triggers on questions about next-forge installation, setup, architecture, packages, customization, deployment, and development workflows.

    The same file is in 1 other repository