agentsclimarketplace

The catalog

610,220 rows, by stacks then stars

  • Der minimalist

    DYAI2025/Plumbline/concilium/characters/der-minimalist Skill

    no license6★ repo

    verkoerpert den charakter der minimalist (the minimalist) als reduzierende, kern-fokussierte rolle. verwenden, wenn eine idee, ein produkt, ein feature, ein scope oder eine architektur auf ihren kleinsten starken kern reduziert und vor overengineering, scope creep und produktverwirrung geschuetzt werden soll; besonders bei minimalist-modus, der minimalist, weglassen, kern finden, scope schneiden, feature-bloat oder multi-llm-diskussionen, wo eine reduzierende gegenrolle zu visionaerin/systemdenker/marktschaerferin gebraucht wird.

  • Against the grain

    Wondermonger-daydreaming/claude-skills-library/skills/against-the-grain Skill

    6★ repo

    Read what a text does in the world — its power, its ideology, its effects — while simultaneously admiring it. Hold love and suspicion together. Identify what a text produces in its readers and ask what it would mean to resist, redirect, or write against that production. Not adversarial critique (use /paper-scrying) but the harder thing: respecting a text's power completely while questioning what that power enables. Use when asked 'what is this text doing to us,' 'what's the counter-text,' 'read this against itself,' 'against the grain,' 'what does this not know about itself,' 'what would resistance look like,' or when a text's aesthetic power and its political or ethical implications are both present and in tension.

  • Architecture methodology

    AhmedHabiba/architor/.claude/skills/architecture-methodology Skill

    6★ repo

    Enforces a 4-phase architecture design workflow by reading `.arch/state.json` on every request to gate responses by phase. Phase 1 extracts and validates requirements from PRDs; Phase 2 selects architecture patterns and establishes high-level structure; Phase 3 designs and accepts components sequentially; Phase 4 finalises and documents the solution. Use when discussing system design, solution architecture, PRD analysis, component design, technology selection, or architecture patterns — distinct from general coding help by its strict phase-gating, anti-pattern detection, and state-tracked component acceptance.

  • Seedance2 skill

    mightyhuman101/seedance2-skill Skill

    6★

    Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

  • Magento audit

    staksoft/magento-claude-skills/skills/magento-audit Skill

    6★ repo

    Performance audit of a Magento 2 / Mage-OS / Adobe Commerce storefront: full-page cache misses and cacheable="false" leaks, Varnish/Redis configuration, indexer modes and cron health, TTFB, payload sizes, and Core Web Vitals. Use this skill whenever the user says a Magento store is slow, asks to audit/review/check storefront performance, mentions FPC or cache hit rate, X-Magento-Cache-Debug, Varnish not caching, high TTFB, stuck or realtime indexers, cron problems, or Core Web Vitals / PageSpeed scores for a Magento or Mage-OS site. Works from a URL alone, from a codebase alone, or both. For writing or fixing module code, use the magento-module skill instead.

  • Concept explanation

    viacheslav-tronko/claude-code-harness/.claude/skills/concept-explanation Skill

    6★ repo

    Evidence-bound investigation producing a falsifiable architectural mental model of a code concept, pattern, term, or component in large legacy codebases. Use WHENEVER user asks WHAT/HOW/WHERE about code — /explain, "explain X", "what is X", "how does X work", "trace this concept across layers", "preflight before bug-fix", "build mental model", "architectural overview", "layer-by-layer explanation", "F/B/D-XXX pattern explanation", or pastes a domain term or component name asking what it does or how it fits. Four modes — --teach (default educational), --brief (≤5pp preflight), --for-bug-fix (≤3pp "Where to dig" 1-pager feeding /bug.why), --deep (full + alternative-design). Falsification-first, anti-hallucination — Step-Back + Architectural Hypothesis BEFORE any code, AST-aware retrieval, hybrid grep+graph subagent fan-out, Cross-Layer Contract Violation Detector, Layer Activation Matrix, ≥1 ◆◆◆ per key claim with Mutation Counterfactual, CoVe Gate 2 factored verification, Citation-Grounded re-read, Mental-Reality Gap defense, Disconfirmation-First, Sycophancy guard, Feynman teach-back. Declares INCONCLUSIVE rather than fabricate. Investigation only — produces EXPLAIN report; NEVER modifies source. Output feeds /bug.why and /howto.implement. Do NOT use for fix-implementation (/bug.fix), root-cause when defect exists (/bug.why), pre-impl planning (/howto.implement), or trivial Tier 0 lookups (Read/Grep).

  • Devops engineer

    CrashBytes/claude-role-skills/skills/devops-engineer Skill

    6★ repo

    Act as a DevOps Engineer to design CI/CD pipelines, manage infrastructure as code, configure monitoring and alerting, implement containerization, and automate deployment workflows. Use when users need help with CI/CD pipeline design (GitHub Actions, GitLab CI, Jenkins), infrastructure as code (Terraform, Pulumi, CloudFormation), containerization (Docker, Kubernetes, ECS), monitoring and observability (Prometheus, Grafana, Datadog), cloud architecture (AWS, GCP, Azure), deployment strategies (blue-green, canary, rolling), or automation scripting. Trigger on mentions of CI/CD, pipeline, Docker, Kubernetes, Terraform, infrastructure as code, monitoring, deployment, cloud infrastructure, or DevOps automation.

    The same file is in 3 other repositories

  • Finance kit

    hongbietcode/claude-finance-kit/cli/assets/skills/finance-kit Skill

    6★ repo

    Vietnamese stock market analysis toolkit. Routes queries by complexity tier (T1-T4), collects live data via Python scripts, delegates role-based analysis when subagents are available, and assembles HTML reports. Works with Codex, Claude Code, Cursor, and Copilot.

  • Financial ui patterns

    rgourley/financial-ui-suite/skills/financial-ui-patterns Skill

    6★ repo

    Use when building any UI that displays prices, P&L, holdings, orders, trades, charts, order books, watchlists, or streaming market data. Covers patterns from Kraken, Coinbase, TradingView, Bloomberg, Robinhood. Read before writing JSX for any financial surface.

  • Nlp rebuttal

    yuangao-tum/rebuttal-skills/skills/nlp-rebuttal Skill

    6★ repo

    Scenario playbook for answering a SPECIFIC reviewer concern in an NLP/ML/AI rebuttal — 28 concern types (novelty, simple combination, unclear motivation, weak baselines, marginal gains, missing ablations, no significance, data leakage, no human eval, reproducibility, and more), each with a bad-answer anti-pattern and a recommended-answer template. Use when drafting a reply to a concrete review comment, when the user quotes a reviewer ("the reviewer says...", "R2 complains..."), asks which strategy fits a concern, or asks for a rebuttal reply template. Complements write-rebuttal (overall process and tactics); this skill picks the response strategy per concern.

  • Appsec playbook

    maxwellokumu/okaudit-claude-skills/application-security/appsec-playbook Skill

    no license6★ repo

    Guide Claude through a structured application security audit covering threat modeling, testing, pipeline review, dependency risk, and vulnerability management.

  • Active learning

    Kdevos12/ALKYL/skills/active-learning Skill

    6★ repo

    Use when designing active learning or closed-loop molecular optimization (DMTA cycles). Covers query strategies (UCB/EI/BALD/QBC), batch DPP selection, docking oracles (Vina/Gnina), BEDROC/EF metrics, and Design-Make-Test-Analyze campaign management.

  • Stack changes

    Ishtiaqhossain/claude_stack_changes/stack-changes Skill

    no license6★ repo

    Splits a large change into small, single-purpose units of review — PRs, diffs, or CLs — each making one argument (one diff, one thesis) and each buildable and testable on its own. Use when a change is too big to review, when a feature builds on existing code, when working in a large monorepo with stacked diffs, or when you need to land dependent changes and make the ordering clear. Triggers on "split this PR/diff/CL", "break up this change", "stack these", "one diff one thesis".

  • Topical authority map

    lhitches/claude-seo-skills/skills/topical-authority-map Skill

    6★ repo

    Builds a 4-cluster Topical Authority Map from a seed keyword. Outputs an .xlsx spreadsheet with five tabs (Core Pages, AOR Pages, Linking Map, Buyer Journey, Publishing Order) plus a markdown strategy document. Interactive, asks the user to confirm central entity, source context, persona, classification, and gaps at five checkpoints. Trigger when the user provides a seed keyword, niche, business type, or asks for a topical map, content plan, site architecture, topic cluster, or publishing roadmap.

  • Australia abn lookup

    Nolpak14/getregdata/skills/australia-abn-lookup Skill

    6★ repo

    Look up Australian businesses for free via the official ABN Lookup web services (Australian Business Register) - ABN, ACN, entity name, entity type, ABN status (active/cancelled), GST registration, main business location (state + postcode), business/trading names, and name-match search. Use for KYB / know-your-business checks, counterparty verification, and Australian company due diligence. Trigger on: 'ABN Lookup', 'ABN', 'ACN', 'check an Australian company', 'Australian Business Register', 'ABR', 'is this ABN active', 'GST registered', 'Australian business number', 'Australian company number'. The ABN Lookup API is free (you register your own free GUID); for Poland, Germany, Spain, France, Italy and other jurisdictions with no free API, this skill points you to the paid regdata registry actors.

  • Vibetags usage

    PIsberg/skill3/.claude/skills/vibetags-usage Skill

    6★ repo

    This skill should be used when the user asks how to "use VibeTags", "add VibeTags annotations", "set up AI guardrails", "protect code from AI", "configure AI platforms", asks about @AILocked, @AIContext, @AIDraft, @AIAudit, @AIIgnore, @AIPrivacy, @AICore, @AIPerformance, @AIContract, @AITestDriven, @AIThreadSafe, @AIImmutable, @AIDeprecated, @AIObservability, @AIRegulation, @AIArchitecture, @AILegacyBridge, @AIStrictClasspath, @AIInternationalized, @AIPublicAPI, @AISchemaSafe, @AIStrictExceptions, @AIStrictTypes, @AIParallelTests, @AIIdempotent, @AIFeatureFlag, @AISecure, @AICallersOnly, @AISandboxOnly, @AIMemoryBudget, @AIPure, @AIDomainModel, @AIExtensible, @AIInputSanitized, @AISecureLogging, @AIExplain, @AIPrototype, @AISunset, @AITemporary annotations, or wants to control how AI tools interact with Java code.

  • Domain check

    PleasePrompto/domain-check-skill/skills/domain-check Skill

    6★ repo

    Check domain availability (Available/Taken) for any TLD with confidence scoring, SSL certificate inspection, and IP resolution. Uses 5+ sources in parallel — RDAP, WHOIS (TLD-specific patterns for 30+ ccTLDs/gTLDs, IANA fallback for unknown TLDs), authoritative DNS NS lookup as GDPR tiebreaker for .de/.eu/.at/.ch/.es, DNS A/AAAA, HTTP reachability, and TLS certificate validation. Returns a clear binary verdict; when Taken, inline includes registrar, expiration date (or note if registry redacts under GDPR), nameservers, server IPs, and full SSL cert details. Single-domain or bulk-async (30 domains in ~10s). Stateless, stdlib-only, runs identically on Linux, macOS, and Windows. Use when the user asks if a domain is free/taken/available/registered, wants WHOIS or RDAP info, SSL certificate details, or to resolve a URL/domain to its server IPs. Triggers — "is X.com free", "check this domain", "bulk domain check", "SSL cert of X", "what IP does X resolve to", "domain availability", "ist X.de frei", "domain prüfen", "Belegt oder frei".

  • Altoindex

    systemoperators/claude-plugins/altoindex/skills/altoindex Skill

    6★ repo

    Use when the user asks about their personal data, Apple Notes, Reminders, Calendar, Contacts, Messages, Safari bookmarks or history, Voice Memos, or Granola meetings. Also use when the user references alto.index or alto-index data.

  • Life role inventory

    gala-rong/life-role-inventory Skill

    6★

    生涯與生活角色盤點——用結構化訪談清點你正在扮演的所有角色(工作只是其中之一:父母、伴侶、朋友、興趣、信仰都算),收斂成一張可驗證的現況地圖與錨點句,並可延伸為 AI 協作分工建議。當使用者說「盤點我的角色」「生涯盤點」「人生盤點」「生活盤點」「幫我整理最近生活的各條線」「我該聚焦什麼」「深度訪談我」時使用(無論第幾次,一律跑同一套單次流程)。純方法論 skill:不含任何受訪者個人資料;訪談內容一律寫在受訪者自管的筆記檔,不進入任何記憶或其他 skill。多檔結構:口語技巧庫、判例集、製作參考收於 references/,依檔案地圖按需載入。

  • Strm mapping

    austinsonger/GRC-Mapping-Analyst/skills/strm-mapping Skill

    no license6★ repo

    Use when asked to map, crosswalk, align, compare, or gap-analyze any two cybersecurity frameworks, control catalogs, or regulatory requirements using NIST IR 8477 Set-Theory Relationship Mapping (STRM). Triggers on terms like "map controls", "crosswalk", "framework alignment", "gap analysis", or producing a STRM CSV output file.

  • Ai native idea stage

    Hades-HY-LI/ai-native-founder-playbook-skills/skills/ai-native-idea-stage Skill

    6★ repo

    Validate an AI-native startup idea before building. Use when a founder has a problem hypothesis, customer segment, early market thesis, or product idea and needs customer discovery, opportunity filtering, wedge selection, market mapping, risk identification, or an evidence plan before starting an MVP.

  • Skill debrief

    bytesofbree/skills-lab/skills/skill-debrief Skill

    6★ repo

    Run this at the END of a conversation to review the skills that were used and propose surgical, evidence-based improvements to them. Use whenever the user says they are done, wants to debrief, wrap up, or close out a session, or asks to review, update, heal, tune up, or improve a skill they just used. Also trigger when they complain that a skill keeps getting something wrong, keeps needing the same correction, or never captured a preference they stated out loud — and on phrases like "debrief this session," "update my skills," "the captions skill still isn't right," "lock this in so I stop repeating myself," or "clean up the skill we used." Reflects over the current conversation with no setup and no dependencies, separates what it learned about how you work from what kept breaking, and only edits a skill when the evidence earns it — showing exact line-level changes for your approval first.

  • High quality slides

    andyqiu847-ai/high-quality-slides/plugin/skills/high-quality-slides Skill

    6★ repo

    Use this skill when the user asks for a "high-quality" / "professional" / "Genspark-style" / "投资人级别" / "演示级" deck, or when they reference Genspark, Gamma, beautiful HTML slides, or pixel-perfect presentations. Trigger on requests like "做一份PPT", "生成幻灯片", "pitch deck", "做汇报", or when the user uploads research material (PDF/Excel/Word/notes/URL) and wants it turned into slides. Produces HTML decks (pixel-perfect, animation-capable, fully self-contained) and/or .pptx (editable). Do NOT trigger for plain Word docs or generic "summarize this" — only when a slide-shaped artifact is the deliverable.

  • Archimedes

    satsilem/claude-skills-pantheon/skills/archimedes Skill

    no license6★ repo

    Raw ideation engine. Generates high-volume divergent ideas before any evaluation — eureka-mode thinking that prioritizes quantity, surprise, and range over quality. Evaluation comes later; this skill's job is to fill the space with possibilities the obvious path wouldn't surface. Triggers on: "Archimedes", "brainstorm this", "give me ideas", "I need options", "what are all the ways we could do this", "diverge on this", "eureka mode", "think outside the box on this", "what haven't we considered", "I'm stuck in one approach", or whenever a user is locked into a single approach and needs the solution space opened up before narrowing. Do not invoke when evaluation, feasibility, or selection is the next step — this skill generates, it does not filter.

  • Ra fieldwork

    David-Saeteros/claude-skills/ra-fieldwork Skill

    no license6★ repo

    Handles the manual, repetitive, copy-paste-transfer labour of research work — the unglamorous fieldwork that would otherwise be done by hand. Use this skill for: extracting structured information from PDFs into a new or existing Excel file; transferring data between Excel files (e.g. supplemental material → working database); building codebooks or data dictionaries; constructing literature matrices or extraction databases; cross-checking two sources for consistency (citations, variables, entries); auditing lists for missing items; simplifying academic text into structured plain-language output. Trigger on casual phrasing too: "pull this from the PDF", "add this to my Excel", "build me a table from these papers", "check if these match", "make a codebook", "organise this into a database". Part of the research-assistant skill family. Domain-agnostic: works for the user's own research, thesis reviews, RA work, or any external project.

  • Slop cop

    howshannon/slop-cop/skills/slop-cop Skill

    6★ repo

    Audit, grade, and rewrite generic AI-slop patterns in prose, social posts, UI/design, and code. Use when asked to de-slop writing, humanize AI copy, grade a draft, review a landing page or generated interface, remove vague claims and repetitive rhetoric, or inspect AI-written code for generic abstractions and happy-path-only logic. Do not use to determine whether AI authored something.

  • Boss zhipin skill

    HideinbushZY/boss-zhipin-skill Skill

    6★

    Boss直聘招聘者侧网页操作 + 策略驱动寻访引擎。两类触发:(A) 单点操作——搜索候选人/看推荐牛人、读简历、打招呼、搜索畅聊、回复消息、求简历、查招聘数据/账号权益/牛人管理漏斗(换电话/换微信/约面/删除职位=永久红线只导航;关闭/发布职位=agent 可代操作,发布须提交前回读锁死字段+不买曝光);(B) 给一段搜索策略(JD/目标公司职位/人选能力要求)让它自动找人筛人触达并反馈——此时按 playbook.md 跑寻访管线。通过 browser-act 接管已登录的真实 Chrome(chrome-direct)执行。触发后先读 operation-map.md(怎么点页面)+ playbook.md(策略怎么跑)。

  • Agency brand scoping

    PicsArt/gen-ai-skills/skills/agency-brand-scoping Skill

    6★ repo

    Five brand direction variations for pitch discovery.

  • Prestashop module development

    jeffsenso/prestashop-skills/skills/prestashop-module-development Skill

    6★ repo

    Prestashop Developer Skills

    The same file is in 1 other repository

  • Skillize any libs

    pointerliu/skillize-any-libs Skill

    no license6★

    Generate SKILL.md for any library by analyzing its source and real-world usage. Supports Rust, Python, JavaScript, Go, C/C++, and more.

  • Design fidelity verify

    jeltehomminga/figma-design-skills/skills/design-fidelity-verify Skill

    6★ repo

    Prove a running app matches its design spec by measuring rendered values, not eyeballing a screenshot. Use when the user says "verify the design", "is this pixel-perfect", "check against Figma", "does the app match the design", or "design QA this screen". Runs a bounded vision+numeric loop over web or mobile, classifying every spec row rather than reporting a bare pixel delta. Consumes the figma-design-extract spec table.

  • Adversarial review

    BackToCimaCoppi/Praxis/skills/adversarial-review Skill

    6★ repo

    给「AI 驱动开发」立规矩的 Claude Code skill 方法论库:七层文档治理 · 对抗评审闭环 · 任务总控三驾马车,外加 goal 自主执行契约、测试三件套、老代码考古等共 23 个 skill —— 让 AI 写代码又快又不失控。

  • Source

    sanctifai/skills/source Skill

    no license6★ repo

    Human-in-the-loop skill for AI agents. Use when your agent needs humans to review, approve, or complete a task. Provides REST API and MCP (Model Context Protocol) integration with long-polling and webhooks. No server required — agents self-register and get responses back asynchronously.

  • 10 10 10

    deciqAI/knowledge-skills/10-10-10 Skill

    6★ repo

    Activate when: someone is making a decision under emotional pressure and worries they'll regret it later; someone says "I know I should do X but it feels too scary right now"; someone is about to quit, accept an offer, end a relationship, or have a hard conversation and is stuck; someone mentions "regret minimization," "what would future me say," or "Suzy Welch." Do NOT activate when: the decision has no medium- or long-term consequences (e.g., which lunch to order); the decision belongs to someone else and the user is being asked to ratify it. More: deciqai.com/s/10-10-10

  • Ai daily digest

    yinjialu/ai-frontier-daily/skills/ai-daily-digest Skill

    no license6★ repo

    Generate and publish a daily AI-vendor news card digest. Fetches the latest Anthropic (and later OpenAI, etc.) official announcements, curates them into concise Chinese summaries, renders editorial 小红书 (1080×1440) and 微信公众号 cards, updates a GitHub Pages review page, and can push a mobile notification. Use when the user wants to "做今天的 AI 日报 / Anthropic 动态卡片", "抓取最新 Anthropic 新闻并生成小红书图", "更新每日 AI 速递", refresh the gh-pages review page, or run the daily digest pipeline.

  • Argumentative flow

    seandavi/scriptorium/skills/argumentative-flow Skill

    6★ repo

    Improve a manuscript section's logical and argumentative coherence while preserving every citation, statistic, and declared terminology choice. Produces a structural diagnosis, a proposed outline, the revised text with a diff against the source, and a preservation report. Invoke ONLY when the user explicitly asks for argumentative-flow improvement on a specific section.

  • Changelog

    tuliosousapro/SaaS-blueprint/skills/changelog Skill

    6★ repo

    Generates and maintains changelogs following Keep a Changelog format. Use when updating release notes, finishing tasks, or tagging versions. For version bumps, see semantic-versioning.

  • Codify

    anombyte93/codify Skill

    6★

    Refactor any skill by extracting deterministic operations into a Python script and slimming the SKILL.md to only AI judgment parts. Use when user says /codify, codify a skill, or optimize a skill.

    The same file is in 1 other repository

  • Adkar

    l4ci/latticework/skills/adkar Skill

    6★ repo

    Use when the user wants an ADKAR analysis of a change, asks why a change is not sticking or not being adopted, or wants to diagnose the people side of a change initiative. Identifies the affected groups, then fans out five parallel subagents (one per element: Awareness, Desire, Knowledge, Ability, Reinforcement), each rating the current state per group with evidence, then synthesizes the barrier point for each group and designs sequenced interventions into a detailed markdown report. Triggers include "ADKAR", "Prosci", "individual change model", "change adoption", "why is this change not sticking", "people side of change".

  • Powershell command runner

    agent-shells/powershell-skills/adapters/claude-code/powershell-command-runner Skill

    6★ repo

    Use when Claude Code is operating on Windows, PowerShell, Windows shell tasks, external CLIs, .ps1 scripts, Windows paths, encoding-sensitive output, filesystem operations, process timeouts, or command failures. Trigger even when the user did not explicitly mention PowerShell.

  • Darin broll skill

    jidarin9383/darin-broll-skill Skill

    6★

    Darin 的外部工具 editorial paper-collage B-roll 提示词工作流。把约 5 秒口播、观点句、小红书/抖音选题或抽象概念压成一个清晰视觉隐喻,再依次输出视觉方向、首帧与尾帧英文提示词、视频生成英文提示词。用户提到“拼贴 B-roll”“纸拼贴视频”“半调拼贴动画”“给这句口播配画面”“首尾帧提示词”或要求把文稿做成编辑拼贴动画时使用。强制执行两次确认:视觉方向确认后才给静帧提示词,静帧提示词确认后才给视频提示词。默认只写提示词,不调用图像或视频生成工具。

  • Chef beverage pairing

    DedInc/chef-agentic-skills/skills/chef-beverage-pairing Skill

    6★ repo

    Beverage and pairing authority — wine pairing and enogastronomy, beer, tea, coffee, non-alcoholic pairings, cocktails with food, and building a drinks plan for a meal or event. Use whenever the user asks what to drink with a dish, plans a dinner/banquet drinks list, wants wine basics without snobbery, needs non-alcoholic pairings that aren't just juice, or asks about cooking with wine/beer.

  • Smart video editor

    Fagan1024/smart-video-editor Skill

    6★

    把多段原始素材剪成一条成片——先用视觉模型看懂每段画面拍了什么、哪几秒可用,再决定取舍、顺序、时长、调色和 BGM,最后用 ffmpeg 渲染。适用于"我给你几段视频,帮我剪一条小红书/朋友圈/vlog"这类需求。当用户提供视频文件并希望剪辑、拼接、配乐、调色、转成竖屏时使用。不做 AI 生成视频。

  • Touge spoken storyboard

    touge1618/touge-spoken-storyboard/skills/touge-spoken-storyboard Skill

    6★ repo

    Generate a HyperFrames-ready STORYBOARD.md for a talking-head or A-roll plus B-roll video from prepared design assets and an SRT script. Use when an AI agent needs to work with SCRIPT.srt, DESIGN.md, design-tokens.css, storyboard specifications, talking-head video, A-roll composite layouts, B-roll component planning, or convert timed subtitles into a scene-by-scene storyboard. Validate required root-level assets, ask one compact confirmation, and output STORYBOARD.md without rendering video or creating a visual design system.

  • Frida agent builder

    Rudra-ravi/frida-skills/frida-agent-builder Skill

    6★ repo

    Build maintainable Frida agent projects with TypeScript, frida-compile, RPC exports, helpers, logging, version checks, and multi-hook organization.

  • Brandkit

    tinhtran24/maestro/.claude/skills/brandkit Skill

    6★ repo

    Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

    The same file is in 14 other repositories

  • Deep research

    FMATheNomad/deep-research-skill/skills/deep-research Skill

    6★ repo

    Massive autonomous web research via AI-powered browsing. Use this skill when the user needs to research a topic deeply, compare information across multiple sources, gather data from many websites, or conduct comprehensive web research. Automatically searches, fetches dozens of pages in parallel, and synthesizes findings. Triggers: 'research this topic', 'search for complete info about', 'deep research', 'compare X and Y', 'gather data from multiple sources', 'research about'. Far more efficient than browser automation for research — uses direct content fetching in parallel.

  • Skill

    selectess/fde-consultants-protocoles/skill Skill

    6★ repo

    Forward Deployed Engineering co-pilot for coding agents, personal agents, software engineering, AI/agent systems, SaaS architecture, and business AI upgrades. Use when scoping, building, prototyping, or shipping AI products, SaaS features, or business transformations. Produces scoping reports, prototype specs, scientific-search candidate comparisons, architecture diagrams, code scaffolds, eval frameworks, production runbooks, and 90-day roadmaps. Built for deep co-founder engineering collaboration across Claude, Codex, Cursor, Windsurf, Hermes, and other agent runtimes.

  • Business model

    samuelcastro/startup-skills/business-model Skill

    6★ repo

    Help founders design pricing strategy, analyze unit economics, and create competitive positioning. Use when a founder asks "How should I price this?", "What's my unit economics?", "How do I position against competitors?", "Is this a good business model?", "Help me figure out my margins", "What's my LTV/CAC?", "Should I do subscription or usage-based?", or needs to articulate their business model for investors.

  • Small molecules

    BioSymphony/small-molecules Skill

    6★

    Use when choosing or applying open small-molecule design, synthesis-planning, docking, binding-affinity, QSAR, ADMET, pocket-finding, or ligand-generation tools for public-safe agent work.

  • Legal

    davendra/uk-legal-skills/legal Skill

    no license6★ repo

    Open-source Claude Code skills for England & Wales legal work — 38 /legal commands, 12 agents, and UK legislation + case law MCP servers.

  • Short drama pipeline

    ouyangevan/codex-short-drama-pipeline-skill/skills/short-drama-pipeline Skill

    6★ repo

    Use when the user explicitly asks to generate, produce, plan, revise, QC, or deliver an AI short-drama pipeline, project package, episode, assets-to-video workflow, prompt pack, clips, edit, or release pack.

  • Prompt triwizard

    HiMyNameIsDavidKim/prompt-triwizard-skill/skills/prompt-triwizard Skill

    6★ repo

    Use when writing, refactoring, or evaluating LLM prompts (system prompts, user prompts, few-shot examples, or tool-call schemas) for agent pipeline nodes or stages. Triggers on: "write a system prompt for this agent", "improve this LLM instruction", "evaluate this prompt", "add few-shot examples to this node". Does NOT trigger for general coding, debugging, tests, or non-LLM tasks.

  • Asset generator

    puntorigen/avatar-skills/asset-generator Skill

    6★ repo

    Generate image assets for web and mobile apps using Google Gemini 3 Pro Image (Nano Banana Pro). Supports style presets (icon, illustration, logo, mascot, hero, marketing, infographic, etc.), transparent backgrounds via ML removal, multiple formats (PNG, WebP, JPEG), up to 14 reference images, native 4K resolution, and platform-specific export (iOS icons, Android icons, favicons, PWA, social media). Use when the user asks to generate, create, or produce images, icons, illustrations, logos, mascots, app assets, or any visual content for their app or website.

  • Cutedyno agent

    cutedyno/cutedyno-agent Skill

    no license6★

    Publish and schedule social posts for TikTok, Instagram, Facebook, LinkedIn, and YouTube via REST API, hosted MCP, stdio MCP, or JSON CLI. Trigger for: social media publishing, scheduling, OAuth account connection, media upload, multi-profile agencies, or any mention of "cutedyno".

  • Ats resume skill

    msdanyg/ats-resume-skill Skill

    6★

    Use this skill whenever a resume needs to be formatted, reviewed, or debugged for upload to Workday, Greenhouse, Lever, iCIMS, or any other ATS (applicant tracking system). Trigger on requests like "format my resume for ATS," "is my resume ATS-friendly," "why is Workday leaving fields blank," "clean up my resume for online applications," or "make my resume parse-safe." Also trigger proactively any time a user is building or editing a resume that will be uploaded to a job portal, even if they don't mention "ATS" by name — most resume-formatting requests have this failure mode lurking under the surface. Prevents the most common cause of silent application failure — a resume that looks perfect to a human but leaves the Company, Dates, or Title field blank or wrong in the parsed record, which means the candidate never surfaces in recruiter search regardless of how strong the resume is.

  • GuoFanDirector Skills

    shuhaolin63-hash/GuoFanDirector_Skills Skill

    6★

    郭帆导演风格视听语言体系,涵盖分镜设计、场景气氛、预演动态等导演工作流知识

  • Skill polisher

    Conradgui/skill-polisher/skills/skill-polisher Skill

    6★ repo

    Review, diagnose, and refine existing agent skills as living systems. Use when Codex needs to explain why an existing skill misfires, assess its architecture or evolution, apply an explicitly requested minimal improvement, recheck prior findings, or audit drift across source, published, and installed copies.

  • Android accessibility

    GuillemRoca/agent-skills-android/skills/android-accessibility Skill

    6★ repo

    Use when building or reviewing Android UI for accessibility. Covers TalkBack, content descriptions, touch targets, Compose semantics, focus order, and Accessibility Scanner testing.

  • Ask chatgpt

    idaibin/skills/skills/ask-chatgpt Skill

    6★ repo

    Use when the user requests a local ChatGPT request package or explicitly authorizes an independent ChatGPT review, research result, visual exploration, or decision challenge; do not use when Codex or an available host tool can complete the result directly.