Guide for building modern, accessible, and composable UI components. Use when building new components, implementing accessibility, creating composable APIs,…
Updated 2026-08-20 17:04:42 +08:00
pexo-agent: AI video generation skill with auto model selection across Seedance 2, Kling 3.0, HappyHorse, and 10+ models. Produces finished multi-shot videos (5–120s) from…; videoagent-video-studio: Generate short AI videos from text or images — text-to-video, image-to-video, and reference-based generation — with zero API key setup. Use when the user wants…; videoagent-image-studio: Tired of juggling 8 API keys? This skill gives you one-command access to Midjourney, Flux, Ideogram, and more, wi…
Updated 2026-08-20 15:44:24 +08:00
Use when a request involves Ethereum, the EVM, or blockchain systems. Applies to building, auditing, deploying, or interacting with smart contracts, dApps,…
Updated 2026-08-20 12:00:23 +08:00
通过 agently-cli 命令行工具操作邮件：发送、回复、转发、搜索、读取、下载附件、管理收件箱。当用户需要进行任何邮件相关操作时使用此 skill。
Updated 2026-08-19 17:14:55 +08:00
所有联网操作必须通过此 skill 处理，包括：搜索、网页抓取、登录后操作、网络交互等。 触发场景：用户要求搜索信息、查看网页内容、访问需要登录的网站、操作网页界面、抓取社交媒体内容（小红书、微博、推特等）、读取动态渲染页面、以及任何需要真实浏览器环境的网络任务。
Updated 2026-08-19 09:36:33 +08:00
Invoke the `groundcover` Go CLI to manage Groundcover resources (dashboards, monitors, silences, connected apps, notification routes, API keys, policies,…
Updated 2026-08-18 22:42:18 +08:00
design-md: Analyze Stitch projects and synthesize a semantic design system into DESIGN.md files; enhance-prompt: Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures…; stitch-loop: Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern; shadcn-ui: Expert guidance for integrating and building applications with shadcn/ui components, including comp…
Updated 2026-08-18 04:20:22 +08:00
fastify-best-practices: Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify…; fastify-best-practices: Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify…; node: Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error han…
Updated 2026-08-18 00:47:06 +08:00
zod: Zod schema validation best practices for type safety, parsing, and error handling. This skill should be used when defining z.object schemas, using z.string…; vitest: Vitest testing framework patterns for test setup, async testing, mocking with vi.*, snapshots, and test performance (formerly test-vitest). This skill should…; react-hook-form: React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, useFieldArray, the subscribe() API, an…
Updated 2026-08-16 01:52:01 +08:00
ci-cd-security: Scan GitHub Actions workflow files for security vulnerabilities by reading the YAML and reporting findings directly — no external tools, no installation, no…; skill-security: Audit an AI agent skill for security risks before installing or trusting it. Runs a deterministic scanner (regex patterns, Python AST analysis, source-to-sink…
Updated 2026-08-15 20:47:01 +08:00
genshijin: 超圧縮コミュニケーションモード。原始人のように話してトークン使用量を約75%削減。 技術的正確性は完全に維持。強度レベル: 丁寧・通常（デフォルト）・極限の3段階。 「原始人モード」「短く」「簡潔に」「トークン節約」と言うか、/genshijin で起動。; genshijin-commit: 超圧縮コミットメッセージ生成。Conventional Commits形式で件名≤50文字、 「何を」より「なぜ」を重視。日本語・英語両対応。 「コミットメッセージ作って」「/commit」「/genshijin-commit」で起動。 ステージング変更時に自動起動候補。; genshijin-compress: 自然言語メモリファイル（CLAUDE.md, todos, 設定）を原始人形式に圧縮し入力トークン削減。 技術内容・コード・URL・構造は完全保持。圧縮版が原ファイルを上書き、人間可読版は FILE.original.md として保存。「/genshijin-compress…; genshijin-review: 超圧縮PRレビューコメント。1行1指摘: 位置…
Updated 2026-08-15 19:55:54 +08:00
Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with…
Updated 2026-08-15 18:07:23 +08:00
Use when exploring unfamiliar codebases, before searching for code, or after editing files. Builds a structural AST index (classes, functions, imports, call…
Updated 2026-08-15 17:10:32 +08:00
caveman: Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build,
/check. Cuts tokens ~75% vs prose while staying precise. Triggers on any…; build: Plan-then-execute implementation against SPEC.md. Native single-thread
loop, no sub-agents. On test or build failure, auto-invokes the backprop
skill before…; spec: Create, amend, or backprop bugs into SPEC.md at repo root. Sole mutator
of the project spec. Triggers when the user asks to write a spec, start
a new spec,…; check…
Updated 2026-08-15 06:07:51 +08:00
parallel-deep-research: ONLY use when user explicitly says 'deep research', 'exhaustive', 'comprehensive report', or 'thorough investigation'. Slower and more expensive than…; parallel-web-search: DEFAULT for all research and web queries. Use for any lookup, research, investigation, or question needing current info. Fast and cost-effective. Only use…; parallel-web-extract: URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs…
Updated 2026-08-15 02:21:22 +08:00