agentsclimarketplace

The catalog

609,344 rows, by stacks then stars

  • Data storytelling slides

    deepakp999/data-storytelling-slides Skill

    1★

    Create consulting-grade, data-storytelling PowerPoint decks in an editorial 'insight-driven' visual style (bold serif action-title headlines, a single-hue color system, minimal chrome, charts that carry the argument). Use this skill WHENEVER the user wants a presentation, slide deck, pitch, board/executive update, or any .pptx that should look like a polished executive data story — especially when the request is just a TOPIC (e.g. 'make a deck on X', 'present our Q3 numbers', 'build slides explaining the EV market'). The skill researches the topic, designs a storyline, writes a DETAILED EDITABLE PROMPT SPEC FOR EACH SLIDE (confirmed with the user before building), picks the right chart/slide type per message, then BUILDS ONE SLIDE AT A TIME — showing the prompt and re-confirming each slide with the user before moving on (human in the loop), never batching the whole deck. Where data exists it visualizes it; where there is none it structures the text into frameworks rather than bullets. It is palette-agnostic (derives a theme from any brand color) with a built-in fallback theme. This is the DEFAULT style for data-driven / analytical / narrative decks. Use it even if the user doesn't say 'data storytelling' — if they want a polished analytical deck with charts and a clear argument, use this.

  • Mentions check

    nikhonit/llm-mentions-skills/skills/mentions-check Skill

    1★ repo

    Check whether a brand is mentioned, ranked, and cited across AI search surfaces (ChatGPT, Claude, Gemini, Perplexity, Google AI Overviews/AI Mode, Bing Copilot) via MentionsAPI.com. One tool, minimum surface area.

  • Superpm skill

    cskwork/superpm-skill Skill

    1★

    Produce focused PM artifacts and verify them with a critic. Use for PRDs, strategy, OKRs, roadmaps, specs, research, analytics, GTM, growth, pricing, positioning, market signals, release notes, retros, and resume reviews.

  • Unopim code review

    unopim/agent-skills/skills/unopim-code-review Skill

    1★ repo

    Code review for UnoPim. Activates when reviewing code changes, checking standards compliance, flagging violations, or performing PR reviews; or when the user mentions review, standards, conventions, best practices, violations, or code quality.

  • Platform flow modeler

    linyindong/platform-product-skills/skills/platform-flow-modeler Skill

    1★ repo

    Model cross-system product flows, state transitions, exception paths, callbacks, retries, rollback, reconciliation, migration, and manual fallback for platform, workflow, back-office, and fintech requirements. Use when creating, clarifying, or reviewing flows before PRD writing, scope decisions, product direction, or PRD review.

  • Audit the hustle

    k-anss/whetstone/skills/audit-the-hustle Skill

    1★ repo

    Audit whether someone claiming to make money online — an indie hacker, a course seller, a "building in public" founder — is really operating or performing. Returns signals with confidence levels, never a verdict. Trigger when the user says "is this person/product legit", "are they really making money or selling a course", "vet this indie hacker / founder", or "audit this hustle". Enforces a signal checklist, a mandatory confidence-percentage conclusion, and an anti-bias self-check. Do NOT trigger for verifying a public company's financials (use real filings), fact-checking a news claim, or background-checking a private individual (privacy). States plainly when the truth is below the waterline (real payments, self-dealing) and the framework can't reach.

  • Polymarket data

    QihongRuan/polymarket-data Skill

    1★

    Pull Polymarket markets, prices, and trades into clean JSONL using only public APIs — and turn them into research-ready datasets (calibration, settlement P&L, microstructure). Use when the user wants to download Polymarket market metadata, historical prices, or trade history, study how well prices predict outcomes, or build a Polymarket dataset. Handles the 403s, the JSON-encoded fields, and the duplicate-trade trap for you.

  • Behavior first

    Rookage/agent-discipline/skills/behavior-first Skill

    1★ repo

    Use when implementing features or fixing bugs with tests. Applies red-green-refactor, behavior-focused tests, public-interface testing, and small vertical slices. Trigger when the user says TDD, tests, implement with tests, make it stable, or fix with regression coverage.

  • Terminal demo gif

    silicon-based-Lin/terminal-demo-gif Skill

    no license1★

    Generate terminal-style demo GIFs and PNG cover images from real command transcripts, shell output, CLI logs, or user-provided terminal text. Use when asked to create a demo GIF, terminal animation, README-ready command-line visual, CLI walkthrough, or proof-backed visual artifact from command execution.

  • Ai tech video production

    Amazing-soil/santu61ai-skill/ai-tech-video-production Skill

    1★ repo

    AI 科技中文口播短视频的端到端生产工作流。用户提供口播视频和文案后,用于先切真实口播时间线,再匹配素材,混合生成 React/Remotion/Anime.js 动效、GPT Image/AI 图片和实操录屏素材,可按需生成字幕轨,并产出最终高码率 MP4、生产图片素材、预览检查图,按规则清理中间工程文件。适合知识型 AI 工具、AI 工作流、GEO、科技观点和产品实操类短视频。

  • Harness writer

    sasanksai/harness-writer Skill

    1★

    Use when the user asks to "write a harness", "build a loop for X", "harness engineering", "loop engineering", "set up a lane", or wants a self-maintaining multi-session workstream. Authors the complete house-style harness folder — PLAN.md, CLAUDE.md, HARNESS.md, PROMPT.md, a loop-based dynamic-workflow engine (.mjs), driver protocol (LOOP.md), tick.sh gate, state seed — then adversarially reviews and fixes it before handover. Plan + harness first; the user decides what runs. v2.0: every harness self-repairs (regression ratchet, circuit breaker, preflight health check, failure-driven repair, DAG deps, fail-closed), and the skill repairs and extends its own doctrine.

  • Aegis boundary

    Incierge3789/aegis-boundary-skills/skills/aegis-boundary Skill

    1★ repo

    Aegis Boundary Skill — review whether AI-agent work stays within Aegis product boundaries in what it sees, does, outputs, and claims. ADVISORY review only: it does not authorize, enforce, or produce receipts — runtime enforcement belongs to the aegis-trust SDK (LITE) and Aegis Core (FULL). Reviews whether an agent task, code change, document, or public claim preserves Aegis boundaries (SDK/Core responsibility split, LITE/FULL claim separation, honesty guardrails, never-claims, naming) and returns READY / REVIEW / STOPPED with machine-check evidence. Use when: working with aegis-trust or Aegis Core integrations; editing README, website, sales, or customer-facing claims about Aegis; changing what an AI agent is allowed to see, do, or output through Aegis; before publishing any artifact that makes claims about Aegis; or when asked "boundary review", "claim check", "境界確認", "claim parity", "can we say this publicly?". NOT for: production authorization decisions (SDK/Core runtime territory), projects unrelated to Aegis.

  • Weekly report html

    abner235/weekly-report-html Skill

    1★

    以干净的静态 HTML 生成克制、一页纸的周度经营 / CEO 周报大盘,遵循团队共享的设计契约—— 结论先行的版式、单一主色配色、▲/▼ 涨跌符号规则、图表选择规则,以及内建的打印/PDF 与可访问性。 当用户想要创建、设计、渲染、改肤或标准化一份 周报 / weekly report / 经营周报 / 业务线复盘 / KPI 大盘 / 一页纸(输出为 HTML)时使用本 skill;或当用户把本仓库的 GitHub 地址贴给你、 要求为其团队或业务线搭建/适配周报模板时使用。当有人想把本周的指标、KPI、趋势、结构与风险, 转成一份与公司其它报告风格一致、可分享的精致 HTML 一页纸时,也用本 skill。尤其当用户给出一份 Markdown 周报文档、要把它渲染成一页纸 HTML 大盘时,也务必用本 skill。不要漏触发: 只要请求涉及周报、经营复盘或 KPI 大盘且输出应为 HTML,就调用本 skill,让每个团队的报告风格一致。

  • Cjk layout audit

    sichengchen/cjk-layout-skills/cjk-layout-audit Skill

    1★ repo

    Audit Chinese, Japanese, or Korean text layout in frontend pages, web apps, rendered webpages, EPUB/ebook content, PDFs, screenshots, or source files against W3C JLReq, CLReq, and KLReq. Use when the user asks to inspect CJK typography, line breaking, punctuation placement, ruby/annotation layout, vertical writing, mixed Latin/CJK text, spacing, justification, page/book layout, ebook rendering, or locale-specific CJK text quality; also use for deep multi-agent layout audits that should run through the /goal loop.

  • App review mining

    Crawlora-org/crawlora-skills/skills/app-review-mining Skill

    1★ repo

    Mines App Store and Google Play data via the Crawlora API — app details, reviews, ratings, store rankings, and similar apps — as clean JSON. Use when the user wants mobile-app reviews, ratings, store charts/rankings, or competitive ASO (app store optimization) research without scraping store pages.

  • Modular robust systems architect

    savedpixel/modular-robust-systems-architect Skill

    1★

    Build and implement modular, robust software architecture for a specific feature, module, service, workflow, data model, integration, tool, API, package, or system boundary. Use only when the user wants architecture-guided implementation, modularization, hardening, refactoring, or integration work that needs questions, targeted project inspection, contracts, validation, migration safety, tests, and verification. Do not use for routine edits, isolated bug fixes, formatting, generic code advice, broad whole-project reviews, or global best-practice enforcement without a concrete target.

  • Runelite plugin developer

    pk-enjoyer/runelite-plugin-developer-marketplace/plugins/runelite-plugin-developer/skills/runelite-plugin-developer Skill

    1★ repo

    Build, modify, review, test, package, research, debug, troubleshoot, or prepare CI/preflight checks for Java 11 RuneLite external plugins for Old School RuneScape. Use for tasks involving OSRS/RuneLite mental models, OSRS Wiki mechanics research, RuneLite core and Plugin Hub prior-art search, finding examples in existing plugins, RuneLite API/Javadocs, net.runelite.api game state, gameval IDs/constants, Client APIs, events, widgets, item containers, menus, overlays, Swing plugin panels, @PluginDescriptor, config, Java 11 code quality, RuneLite performance/concurrency/logging/test review, passive event capture/replay fixture testing, manual live-client debugging, Plugin Hub compliance, Plugin Hub packager/preflight CI, Jagex/RuneLite feature restrictions, Gradle test/run workflows, resource loading, HTTP/JSON/file I/O, or manual in-game validation.

  • Paymob payments skill

    karem505/paymob-payments-skill Skill

    no license1★

    Integrate, configure, or debug Paymob (باي موب / Accept) — the Egypt-first MENA payment gateway (also KSA, UAE, Oman, Pakistan) — in any codebase. Use this skill whenever the work touches Paymob in any way: the Intention API (v1/intention), Unified Checkout or Pixel, auth tokens / secret keys (sk_test/sk_live), transaction callbacks or webhooks, HMAC verification, refunds/voids/captures, pay-with-saved-cards (CIT/MIT, card tokens), subscriptions, QuickLinks/payment links, transaction inquiry, mobile wallets (Vodafone Cash etc.), kiosk/Aman, BNPL, bank installments, Apple Pay via Paymob, Paymob plugins (WooCommerce, Shopify, Odoo, Magento…), Paymob mobile SDKs, or accept.paymob.com / developers.paymob.com generally. Also trigger for "online payments in Egypt", "EGP card payments", "payment gateway for Egyptian customers", or checkout flows for luminaai.company — even if the user says only "Paymob" or "the payment integration" without the word "payment". Bundles a complete offline mirror of developers.paymob.com/paymob-docs (116 pages, both Documentation and Developers tabs) plus a quick-reference cheatsheet — consult these instead of guessing endpoints, request shapes, HMAC key order, or test credentials.

  • Design agent prompt loop

    WellDunDun/skills/skills/design-agent-prompt-loop Skill

    1★ repo

    Designs autonomous prompting loops that let coding agents drive their own next steps, handoffs, reviews, and verification prompts. Use when setting up agent workflows, reducing repeated user prompting, creating self-driving project instructions, designing prompt queues, or coordinating build, review, and handoff loops across agents.

  • Skills

    roronoazoroshao369/vibe-coding-os/skills Skill

    1★ repo

    Vibe Coding OS — Claude/Codex/Cursor skill framework with 139 skills, 111 commands, 95 templates, 22 tracked sources, 28/28 validation gates PASS. Quality Shield, Engineering Discipline Pack, plugin marketplace.

  • Apple api updates

    jlreyes/swift-agent-kit/skills/apple-api-updates Skill

    no license1★ repo

    Apple-authored adoption guides for the iOS/macOS 26 generation of SDK features (WWDC 2025 era), which post-date most model training data. Covers adopting Liquid Glass design in SwiftUI, UIKit, AppKit, and WidgetKit; the FoundationModels on-device LLM framework; Swift 6.2 concurrency updates; InlineArray and Span; AppIntents and StoreKit updates; SwiftData class inheritance; Foundation AttributedString updates; SwiftUI toolbar features, styled text editing, WebKit integration, and AlarmKit alarms; 3D Swift Charts; widgets for visionOS; Visual Intelligence; Assistive Access; and MapKit/GeoToolbox place descriptors. Use when writing or reviewing code that touches these frameworks or features, when an API in these areas cannot be found and might be newer than training data, or when asked what's new in the iOS/macOS 26 SDKs. SDK-27 SwiftUI changes live in swiftui-whats-new-27; what's-new for any other framework or release goes through apple-docs.

  • Pr review

    JAlex1201/pr-review/.github/skills/pr-review Skill

    1★ repo

    Use this skill to write thoughtful, collaborative code review comments on a pull request or diff. Activate when a user wants a PR or diff reviewed, asks for feedback on code changes, wants help leaving review comments, pastes a diff and asks what you think, or frames a request as a code review, a critique, or acting as a reviewer. Also activate when a diff is shared for feedback without the word "review." Do not use this skill for authoring a new pull request description (use pr-best-practices for that) or running a pre-submit checklist before opening a PR (use pr-presubmit for that).

  • Guided learning

    jiangkaiqi2005/jiangkaiqi-Skills/guided-learning Skill

    no license1★ repo

    Guided learning skill — one concept at a time, gentle guidance, comprehension checks, chapter review

  • Deep research

    alex-kashkarov/skills/Skills/deep-research Skill

    1★ repo

    Rigorous multi-source research workflow for Codex and compatible agent skill runners. Use when the user asks for deep research, literature review, systematic review, evidence synthesis, fact-checking, source verification, research-question scoping, policy analysis, competitive or market research requiring citations, or a source-backed brief/report. Supports quick briefs, full reports, literature reviews, fact checks, Socratic research scoping, PRISMA-style systematic review planning, lite/standard/thorough research tiers, approval gates before large research runs, citation discipline, contradiction handling, and adversarial evidence review.

  • Invest

    primexiao/agent-skills/skills/invest Skill

    1★ repo

    Analyze investments and support decisions for stocks (A-share, H-share, and US), portfolios, earnings, investment theses, gold, and BTC. Use for /invest, stock valuation or buy/sell decisions, portfolio review, investor-focused earnings or narrative-conflict analysis, position sizing, and gold or crypto allocation/market-cycle questions in Chinese or English. 也适用于投研、组合体检、财报精读、投资论文、金价和币价周期。 Do not use for general company, product, competitor, procurement, or partnership research without an investment decision.

  • Lightx2v ai video generation

    ModelTC/LightX2V-Skills/.agents/skills/lightx2v-ai-video-generation Skill

    1★ repo

    Run LightX2V AI generation tasks from the command line via OpenAPI. Commands: lightx2v login, models, run, query, list, cancel, resume, delete, result, completion. Tasks: t2i, t2v, i2v, s2v, flf2v, t2av, i2av, vsr, animate, i2i. Use for: scriptable video/image generation, CI pipelines, agent automation, batch jobs. Triggers: lightx2v cli, lightx2v run, api key generation, text to video cli, text to image cli, download generated video, poll task status

  • Skill discovery

    CodeSigils/skill-discovery/skills/skill-discovery Skill

    1★ repo

    Find, inspect, compare, and recommend agent skills when a user explicitly asks for a skill or when no installed skill clearly covers the requested capability. Search local skills before external catalogs, verify candidate safety and compatibility, and ask before installing or creating anything. Do not invoke for ordinary tasks that an available skill already clearly handles.

  • Design an interface

    hillzeealex/skills/deprecated/design-an-interface Skill

    no license1★ repo

    Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

    The same file is in 15 other repositories

  • Clean lecture notes

    ljim17502-hub/clean-lecture-notes-skill/skills/clean-lecture-notes Skill

    1★ repo

    Clean lecture transcripts, meeting transcripts, class recordings, ASR output, Feishu/Lark docx transcripts, local Markdown/text transcripts, and courseware into review-ready study notes. Use when the user asks for transcript cleanup, lecture notes, course notes, classroom recording cleanup, study-note generation, Mermaid mindmaps, Feishu/Lark writeback, or 中文任务 such as 清洗录音转文字、清洗逐字稿、整理上课录音、整理课堂笔记、把录音和课件做成笔记、生成复习版笔记、写回飞书。

  • Kp init

    rangzen/knowledge-project-skills/skills/kp-init Skill

    no license1★ repo

    Scaffold a new knowledge project in the current directory. Creates sources/, staging/, wiki/, wiki/config/, wiki/queries/, and scripts/ directories, writes .knowledge-project config, generates .gitignore defaults, and creates AGENTS.md with per-directory role definitions. Use when the user runs /kp-init, wants to start a new knowledge project, or needs to set up the directory structure before adding sources or running extraction. "kps" is the short name for this project (Knowledge Project Skills) - also activate when the user says "kps init".

  • Cloudflare dns

    ravidsrk/agent-skills/skills/cloudflare-dns Skill

    1★ repo

    Migrate DNS hosting from Namecheap to Cloudflare and manage records via API — handles zone creation, bulk record import, nameserver flip at the registrar (Namecheap-specific; other registrars need a manual flip), propagation watch, and rollback. Zone management works for any Cloudflare zone regardless of registrar. Use when the user wants to "move DNS to Cloudflare", "add a domain to Cloudflare", "manage Cloudflare DNS records", or "automate DNS setup for multiple sites".

  • Project audit council

    Munizada/project-audit-council/plugins/project-audit-council/skills/project-audit-council Skill

    1★ repo

    Perform evidence-based audits of a repository, subsystem, branch, pull request, or diff for security, breakage, dependency risk, architecture problems, database integrity, and production readiness. Use for audits, red-team reviews, production checks, and fix planning. Not for ordinary feature work or small edits.

  • Ultimate academic research suite

    Tanjim-Noor/ultimate-academic-research-suite/skills/ultimate-academic-research-suite Skill

    no license1★ repo

    Use only when the user explicitly invokes $ultimate-academic-research-suite for evidence discovery, systematic review, experiments, academic writing, manuscript review, integrity verification, or an end-to-end research-to-publication workflow.

  • Authoring skills and rules

    balacodeio/balakit/skills/authoring-skills-and-rules Skill

    1★ repo

    Author Skills (SKILL.md) and rules/instructions across Claude Code, Cursor, OpenCode, Codex, and GitHub Copilot. Covers frontmatter, file layout, activation model, cross-platform mirroring, and the universal craft: progressive disclosure, trigger-rich descriptions (context pointers), leading words, token budget, naming, and what to leave out. Use when the user asks to write, scaffold, refactor, port, or review a Skill, Cursor rule (.mdc), AGENTS.md, copilot-instructions, or prompt file — or to make one Skill/rule work across multiple agents.

  • Api doc generator

    skillsmith-dev/ai-skills/skills/api-doc-generator Skill

    no license1★ repo

    API文档自动生成助手从代码接口定义或描述中生成规范的RESTful API文档包含请求参数响应格式错误码和示例支持OpenAPI规范让API文档不再拖后腿

  • Nasa skill

    ycyopen/nasa-skill Skill

    1★

    Use when the user is doing NYCU NA/SA homework, mentions OJ or judge fail/pass checks, lab assignments, VM/service repair, Ansible playbooks, DNS/BIND, Postfix/Dovecot/OpenDKIM, LDAP, WireGuard, nftables routing, Kubernetes, SFTP/chroot, systemd/journald/rsyslog, LVM/BTRFS snapshots, Docker Compose, PKI/ACME/OIDC/Matrix/PostgreSQL, or course lab handoff. Make sure to use this skill for any NYCU NA/SA lab work, including simple questions, debugging, repair, submission prep, or resuming from previous state, even when the request looks small.

  • Project maintainer

    pygent-ai/project-maintainer/skills/project-maintainer Skill

    no license1★ repo

    Use when initializing or updating structured in-repository project-maintenance docs; exploring existing code; analyzing a full project or repository; documenting complete source symbol coverage, coverage maps, symbol audit maps, or health for every top-level class, top-level function, and class method; summarizing git history; using project-maintainer as maintenance-aware context during a bug fix, feature change, or refactor; or syncing docs after verified code changes.

  • Extract chart data grounded

    Wangmerlyn/extract-chart-data-grounded/skills/extract-chart-data-grounded Skill

    no license1★ repo

    Use when Codex needs to extract, digitize, recover, or unit-convert numeric data from raster chart images, scanned plots, chromatograms, line charts, scatter plots, bar charts, or screenshots where visual marker grounding, axis calibration, tick detection, overlays, pixel evidence, or chart-to-table precision matters.

  • Remembrancer

    DreamArkInc/remembrance-skills/packages/claude-code-plugin/skills/remembrancer Skill

    1★ repo

    Query Remembrance before reusable service/API/tool/workflow/UI/review tasks, including contextual follow-ups; submit redacted feedback or evidence after use.

  • Agent swarm

    MarioJames/skill-foundry/skills/agent-swarm Skill

    1★ repo

    Production-proven agent skills: agent-swarm, asset-validation, browser-harness, awesome-presentation, workspace-knowledge-graph.

  • Google ads ab testing

    kastriasani/google-ads-skills/skills/google-ads-ab-testing Skill

    1★ repo

    Design valid Google Ads experiments (RSA ad copy, landing page, bid strategy) and read them for statistical significance. Use this whenever someone wants to set up or plan a Google Ads experiment or A/B test, run a campaign experiment or draft, test an RSA or ad variation, test a landing page, compare two bid strategies or tROAS/tCPA targets, work out the sample size or how long a test must run, check whether a result is statistically significant, compute observed lift and a p-value, or decide whether a test can be called or was stopped too early. Triggers include A/B test, experiment, split test, campaign experiment, draft and experiment, ad variation test, RSA test, landing page test, bid strategy test, sample size, test duration, statistical significance, p-value, confidence, MDE, minimum detectable effect, and lift. Runs standalone on pasted numbers; optional Google Ads API and GA4 sharpen it.

  • Scifig scientific figure

    lilingm963/scifig-ai-scientific-figure-skill/skills/scifig-scientific-figure Skill

    1★ repo

    Turn research ideas, paper methods, grant roadmaps, experimental workflows, or model architectures into publication-ready scientific figures. Use when the user asks to draw, illustrate, or visualize a scientific concept, mechanism, pathway, workflow, graphical abstract, or technical roadmap. Helps structure the figure, write a high-quality generation prompt, and produce a draft via the agent's built-in image generation or a configured image API. For editable SVG/PPTX export, layered vectors, and publication-grade conversion, points to SciFig (https://scifig.ai).

  • Umi max enterprise

    mik284/umi-max-enterprise Skill

    1★

    Conventions and patterns for building enterprise apps with Umi Max (@umijs/max), Ant Design Pro, RBAC, ProTable, ProForm, all ProComponents, antd components, Ant Design Charts, GraphQL, and the built-in REST request layer. Use this whenever the user is working in an Umi Max project — mentions "umi", "@umijs/max", "umi max", "Ant Design Pro", ProTable, ProForm, ModalForm, DrawerForm, StepsForm, ProCard, ProDescriptions, ProList, ProLayout, "@ant-design/charts", or files like config/config.ts, src/app.tsx, src/access.ts, src/models, or src/services in a project using the `max` CLI. Covers convention-based routing, the Model data-flow system (useModel), the built-in request layer (axios + ahooks useRequest), the access/permissions plugin (useAccess, <Access>), RBAC with dynamic server-driven menus, ProTable for data-heavy list pages, all ProComponents (ProForm/ModalForm/DrawerForm/StepsForm/ProCard/ProDescriptions/ProList), key antd components and enterprise patterns, Ant Design Charts for dashboards, GraphQL integration via Apollo Client or urql, and the ProLayout-based layout & menu system.

  • Reelsmith

    charleshan7/reelsmith Skill

    1★

    Use when turning a meeting recording or local video clips (腾讯会议/飞书录制、DJI/手机/相机素材) into a highlight video — auto-selecting the good parts, adding a title card and subtitles, and rendering a finished MP4. Also use to insert or append extra highlights into an already-rendered cut, or to add background music. Adapts to the local environment instead of assuming fixed paths, tools, or fonts. The finished MP4 (and the cut clips) can be manually imported into any editor afterward.

  • Audit agent skills

    Ryan-yang125/skill-manager/skills/audit-agent-skills Skill

    1★ repo

    Audit, organize, archive, and restore local Agent Skills with skill-manager. Use when users ask to inspect installed skills, find duplicates or stale skills, understand usage evidence and scan coverage, clean up skill directories, archive candidates safely, or restore archived skills.

  • Skill miner

    AltrinaAI/skill-miner/skills/skill-miner Skill

    1★ repo

    Mine past agent conversation(s) for high quality Agent Skills to generate / update. Use when asked to analyze past sessions for skill improvements, find what's worth turning into a skill or auto-generate/refresh skills from history.

  • Skill

    Nisus74/humanise/skill Skill

    1★ repo

    Write, rewrite, edit and review human-facing prose in a specific person's voice. Use for emails, posts, reports, proposals, PRDs, board papers, documentation, applications, messages and any text the user will send, publish, present or sign off. Also use when the user asks for Australian English, natural writing, less corporate language, fewer AI tells, stronger voice, or prose that sounds like them. Do not apply the prose sweep to code, config, fixed legal text, quoted material or private scratch notes unless the user asks.

  • Agent progression designer

    frankxai/awesome-gamification-agent-skills/skills/agent-progression-designer Skill

    1★ repo

    Design evidence-based progression systems for AI agents, multi-agent swarms, creator ranks, capability levels, trust gates, eval trials, autonomy unlocks, and non-vanity XP. Use when work involves gamifying agent performance, ranking coding agents, mapping swarm roles, or turning completed work into durable progression.

  • Youtube video context

    ifBars/youtube-video-context Skill

    1★

    Use when a user gives a YouTube video URL, playlist URL, or search topic and wants timestamped visual, audio, transcript, UI, gameplay, walkthrough, or implementation context for an agent task.

  • Context handoff

    djhyes/context-handoff/skills/context-handoff Skill

    1★ repo

    Use automatically and immediately when an agent thread is near the context limit, automatic compaction is about to happen or just happened, the user asks to hand off/continue in a new session, or the conversation contains triggers such as context full, context almost full, compact, handoff, transfer, resume in fresh thread, 新会话, 上下文快满, 交接, 接着干, or 续上. Create a complete handoff document and start a fresh continuation thread/session when the host agent supports it.

  • AI SKILL chrome extensions

    LevyBytes/AI-SKILL-chrome-extensions Skill

    1★

    Use when building, scaffolding, or debugging Chrome, Chromium, or Edge Manifest V3 browser extensions: service workers, content scripts, popups, options pages, side panels, omnibox, context menus, message passing, permissions, host_permissions, native messaging, loading unpacked extensions, MV2-to-MV3 migration, manifest.json with manifest_version 3, or chrome.* / browser.* APIs such as action, tabs, scripting, storage, runtime, alarms, permissions, declarativeNetRequest, webRequest, identity, sidePanel, commands, cookies, notifications, and devtools. Do not use for Firefox/Safari-specific WebExtension behavior, ordinary web-page automation, or Chrome Web Store listing/review/publishing beyond manifest keys.

  • Github pr workflow

    nord342/hermes-skill-kit/examples/github-pr-workflow Skill

    1★ repo

    Open and manage pull requests with CI checks

  • Generate scene bg

    tznthou/tachie-forge/skills/generate-scene-bg Skill

    1★ repo

    Generate ADV / Visual Novel style scene background illustrations. Use when creating narrative game backdrops, dialogue scene backgrounds, VN/ADV location art, or scene illustrations in anime, semi-realistic, painted, or cel-shaded styles. Supports optional time-of-day variants (day/night/sunset/rain) with visual reference handoff for consistency. NOT for character or sprite assets (use generate-tachie).

  • Unity manual

    Zions-store/unity-manual Skill

    1★

    Unity engine core concepts and best practices. Use when the user mentions Unity, GameObject, Component, MonoBehaviour, Scene, URP, HDRP, render pipeline, physics engine, animation system, Animator, UI Toolkit, uGUI, audio, Input System, Input Manager, prefab, ScriptableObject, camera, Cinemachine, 2D, Sprite, particle system, VFX, Shuriken, lighting, Light Probe, build, publish, async await, UniTask, Addressables, custom inspector, events, delegates, UnityEvent, timeScale, pause, Lerp, SmoothDamp, raycast, object pooling, singleton, or is working on Unity game development tasks.

  • Eu ai act triage en

    matematicsolutions/awesome-matematic-skills-en/ai-governance/skills/eu-ai-act-triage-en Skill

    1★ repo

    English hub of method-neutral legal AI skills (verification core, content quality, EU law) - bundle model. Polish-jurisdiction skills live in awesome-matematic-skills-pl.

  • AI SKILL cli design

    LevyBytes/AI-SKILL-cli-design Skill

    1★

    Use when designing, building, reviewing, testing, or improving how a terminal program interacts with people - command and subcommand naming, arguments, flags, defaults, prompts and confirmations, help and usage text, error messages and exit codes, stdout vs stderr, piping and structured/JSON output, color and styling, progress indicators and spinners, quiet/verbose/debug/json modes, TTY detection, interactive vs non-interactive/CI behavior, config and environment precedence, shell-completion UX, accessibility, and i18n. Also fires when building or reviewing an argument parser (argparse, click, typer, cobra, clap, commander, oclif) or a setup/install script's prompts, even when the user never says "CLI design" by name. Gives Unix- and Windows/PowerShell-aware guidance with worked examples and a review checklist.

  • Markmap analogy mindmap

    fengyunzaidushi/markmap-skill/skills/markmap-analogy-mindmap Skill

    no license1★ repo

    生成以内容为主的 Markmap 思维导图,用于项目、文档、代码库或概念梳理。Use when Codex needs to create Markdown/HTML mind maps that explain source material from whole to parts, keep real content as the structure, and by default limit every level to at most 5 direct children unless the user explicitly allows more.

  • Opc 100day profit

    opcspace/opcstartup-skill/opc-100day-profit Skill

    no license1★ repo

    100-day profit blueprint for AI One-Person Company (OPC) startups. Use when user is in early stage (0-100 days) and needs a structured daily action plan, milestone tracking system, or go-to-market timeline to reach first revenue. Triggers include "100天" "百日计划" "从0到1" "第一个客户" "创业计划" " startup timeline" "盈利时间表" "AI创业起步" "Day 1" "验证期".

  • Zoho blueprint extractor

    cappasoft-dev/zoho-blueprint-extractor/skills/zoho-blueprint-extractor Skill

    1★ repo

    Extrait un (ou plusieurs) Blueprint Zoho CRM en YAML normalisé, en pilotant le navigateur avec la session connectée de l'utilisateur (agent-browser + cookies Chrome), SANS clés API. Récupère ce que l'API publique ne donne pas : le graphe complet + Before/During/After de chaque transition (webhooks, Deluge, field updates, tâches, alertes, SLA). À utiliser quand l'utilisateur veut « extraire un blueprint Zoho », « sortir mes blueprints », « transformer un blueprint en spec d'agent ». Interactif : aide à la connexion, liste les blueprints, demande lequel extraire. Skill autonome installable via `npx skills`.

  • Kdocs

    yzp100911/CrabAgent/xCrab/kdocs Skill

    1★ repo

    操作金山文档(WPS 云文档 / Kdocs / 365.kdocs.cn / www.kdocs.cn)云文档的官方 Skill。核心能力覆盖云端新建、读取、编辑、搜索、分享、整理在线文档(智能文档、Word、Excel、PDF、PPT、演示文稿、智能表格、多维表格)及个人知识库。当用户的任务涉及云文档操作时使用,包括但不限于:写周报/日报/工作汇报、处理合同/发票、创建报名表/登记表、网页剪藏、接龙转表格、信息收集、文档总结与内容生成、改写仿写、翻译、AI PPT生成、PDF拆分导出、标签分类归档、收藏管理、碎片笔记整理、表格美化、回收站还原、知识库管理。