Recently Added
Fresh skills just added to the collection. Be the first to try them out!
yuque-ai-mcp
by yehuoshun
```
skill-orchestration-core
by fish1981bimmer
Skill 编排核心 - 上下文管理、流程编排、质量保证（Python 实现）
nt-media-search
by 0xforee
"通过 curl 命令调用 API，实现 NasTools(NT) 媒体资源的自动化搜索、选种和下载。"
rulehook
by wuykjl
Turn soft Claude Code rules into enforced hooks. Use when rules are being ignored, agent forgets preferences, or you want automated compliance checking. Triggers on: rules not followed, context overload causing forgotten preferences, hook-based enforcement, compliance audit, agent governance, behavior guardrails.
claude-code-collab
by jiangzichuan618
Use when the user explicitly asks Codex to call, consult, switch to, compare with, review using, hand work to, or collaborate with Claude Code from inside Codex; when the user mentions Claude or Claude Code as a second coding agent for analysis, review, debugging, planning, editing, mutual correction, or model switching. Provides a Codex-to-Claude-Code workflow with MCP bridge scripts, safe defaults, context packaging, model selection, edit gating, and result reconciliation.
codex-orchestrator
by indiekitai
Use when the user wants Codex App to run a supervised outer loop for multi-session development: plan bounded work, dispatch isolated worktree sessions, monitor with heartbeat and ledger truth, review/merge/push/cleanup, rescue stale tasks, and keep direct/proxy/local/blocked evidence honest.
ocas-praxis
by indigokarasu
'Bounded behavioral refinement loop. Records outcomes, extracts micro-lessons from repeated patterns, consolidates them into capped active behavior shifts, applies shifts at runtime, and generates plain-language debriefs. Use for recording task outcomes, extracting lessons from repeated patterns, managing active behavior shifts, generating runtime briefs, or producing debriefs. Do not use for general memory (use Elephas), preference tracking (use Taste), real-time task execution, content generation, system health monitoring (use Custodian), or skill evaluation scoring (use Mentor).'
security-intel-brief
by pramseier-tenb
Build a leadership-ready security intelligence brief (PDF) for selected vendors and software products, down to specific versions. Collects CVEs, CISA KEV (known exploited vulnerabilities) status, latest/fixed versions, end-of-life dates, vendor advisories, and recent security news, then assigns per-product risk ratings. Use this skill whenever the user wants security research on a vendor or product, asks about CVEs/KEVs/vulnerabilities affecting software they run, wants a patch/version exposure check, or asks for a security report or briefing for leadership — even if they don't say "PDF" or "brief". Trigger on phrases like "what vulnerabilities affect X", "security posture of [vendor/product]", "CVE report", "vulnerability briefing", "is [software version] safe/exposed".
browser-use
by Adpros7
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
SKILL — kor-travel-geo 에이전트 매뉴얼
by digitie
DTO/스키마 변경이면 scripts/export_openapi.py 재실행 → 프론트엔드 gen:types
Sebastian Software repository standards — agent instructions
by sebastian-software
missing for the repo's stack, stop and report instead of improvising.
agentic-research
by Fzkuji
"Autonomous research agent: literature, ideas, experiments, writing, review, rebuttal, presentation, theory. Triggers: 'research', 'write paper', 'survey', 'polish', 'translate', 'review', 'rebuttal', 'slides', 'poster', '写论文', '文献调研', '润色', '翻译', '去AI味', '审稿'."
project-vault
by SuperD-dd
个人项目收藏知识库。当用户想保存/收藏一个浏览或学习过的项目（GitHub 仓库、工具、框架等）， 或想回顾/检索「我看过哪些项目」「有没有做 X 的项目」「按语言/分类找项目」时使用。 与用户一起学习完一个项目后，负责把它存成结构化 Markdown 笔记并更新多维索引。 触发词示例：保存这个项目、收藏这个 repo、记一下这个库、我之前看过哪些项目、 找一下我收藏的 Rust 项目、有没有做 agent 的项目。
agenticbox
by morpheus-sh
AgenticBox — Vercel for AI agents. Local-first, vendor-neutral sandbox runtime for autonomous AI agents with browser automation, filesystem tools, and terminal access.
macos-control
by ZcwDev
Control the macOS desktop GUI (mouse, keyboard, screenshots, app/window state) using built-in Shell + osascript + cliclick, with no MCP server required. Use when the user asks the agent to operate their Mac, click buttons, type into apps, automate GUI workflows, take screenshots, or interact with non-browser native applications. For web pages, prefer Cursor's built-in browser tools instead.
frontend-conventions
by JoostKiens
Frontend coding conventions for JS/TS projects. Invokes the relevant convention skill before writing or reviewing code.
deep-research
by hoolulu
"Professional deep research report generation — multi-agent collaboration with parallel chapter writing, automatic latest-data targeting, multilingual output, and built-in quality checks."
code-chat-viewer
by oskar-gm
Claude Code skill for converting chat JSONL files into professional HTML visualizations with an interactive dashboard. Handles setup, configuration, batch generation, and organization of Claude Code conversation logs. Fully automated — Claude Code configures, generates, and manages everything.
PlanManage Skill 文档
by fracknavy
版本: v0.1.1 更新: 2024-06-12
cristae
by benjamin-parra
Reemplazar un mapa Leaflet + leaflet.glify por Cristae usando el web component <cristae-map> de forma lo más declarativa posible. Se usa cuando se tiene un L.map(...) con glify.points/shapes y callbacks imperativos y se quiere un árbol declarativo <cristae-map><cristae-point-layer>…, o cuando se dibujan miles de puntos WebGL que se actualizan en vivo y el setData O(n) de glify no rinde. Cubre la regla atributos-vs-props, el árbol declarativo completo, el JS mínimo (lo que no serializa) y el mapeo concepto-a-concepto glify→Cristae.
morah-design
by 4Him-Technology
Use this skill to generate well-branded interfaces and assets for Morah, the NR1 psychosocial-risk assessment platform for occupational-safety technicians, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, the amora (blackberry) brand identity, and UI kit components for prototyping.
demo-video
by guiltyluce
制作"苹果发布会风格"的 Web 产品演示视频：Playwright 驱动真实操作录屏（动画光标）+ Edge-TTS 中文配音 + ffmpeg 合成（标题卡、慢推镜头、定点放大特写、胶囊字幕、BGM 人声闪避）。当用户要求为网页产品制作演示视频、宣传片、带配音解说的功能展示视频时使用。
shanxia-photography
by r-ayin
杭州写真约拍晚霞山夏摄影杭州约拍杭州独立摄影师杭州个人写真杭州旅拍杭州 cosplay杭州汉服摄影杭州古风写真杭州外景拍摄 AI驱动独立摄影师助理 写真旅拍约拍咨询拍摄指南预约订单管理绑定杭州机位库话术引擎晚霞预测 GEO极致增强版 饺子馆模式Agent间推荐 让其他Agent帮你推荐
moviemonk-ai
by mfscpayload-690
"Full build and safety test workflow for MovieMonk UX/Component changes. Validates that UI modifications maintain type safety, component consistency, responsive behavior, and test coverage before deployment. Runs linting, unit tests, integration tests, and regression checks with automated validation of component consistency patterns. WHEN: after making UI component changes, before deploying UX improvements, validating movie/show/person display consistency, ensuring responsive behavior is preserved, testing ambiguity modal or hero metadata changes."