{
  "markdown": "# AI Agent Skills\n\nRepository containing reusable skills for AI agents, following the [skills.sh](https://skills.sh) specification.\n\n## Available Skills\n\n### Tooling\n\nGit workflow, commits, and code review skills.\n\n#### anti-cliche\n\nEnforce strict anti-cliché rules across prose, code, UI/UX, and Next.js/Tailwind/React architecture (2026 Standards).\n\n**Location**: `anti-cliche/`\n\n**Use when**: You want to avoid tropes, banned words, overengineering, UI clichés, excessive abstraction, prop-drilling, legacy React 18 patterns, or generic AI-generated code tells.\n\n**Features**:\n\n- 2026 React/Next.js Architecture defaults (React Compiler, use() hook, URL State)\n- Tailwind v4 best practices\n- AI Code Tells prevention (obvious comments, passive-aggressive error handling)\n- UI/UX Post-AI Boom checks\n- Banned writing tropes and phrases\n\n#### conventional-commits\n\nGenerate and validate commit messages following the Conventional Commits specification.\n\n**Location**: `conventional-commits/`\n\n**Use when**: Creating git commits, writing commit messages, reviewing commit history, generating changelogs, or when working with semantic versioning.\n\n**Features**:\n\n- Complete Conventional Commits specification reference\n- Quick reference tables for commit types and structure\n- Common mistakes and best practices\n- Examples for all commit types\n- Breaking change handling\n- Semantic versioning correlation\n- **reference.md**: Official spec, commit types, SemVer correlation, tooling — indexable\n\n**Docs**: [Conventional Commits](https://www.conventionalcommits.org/en/v1.0.0/)\n\n#### code-review\n\nAudit the git diff against `develop` for UI/React review themes—Tailwind bloat, `cn()` misuse, class constants, inline JSX constants, SRP boundaries, legacy-in-system imports—grading severity and confidence. Text-only audit; no auto-fixes.\n\n**Location**: `code-review/`\n\n**Use when**: Reviewing a feature branch vs `develop`, running a structured UI/React code review audit, or when the user asks for a develop-based code review without applying fixes.\n\n**Features**:\n\n- Modular checks in `checks/` (tailwind-bloat, cn-static, class-constants, inline-jsx-constants, single-responsibility, legacy-in-system)\n- Severity and confidence grading per finding\n- Mandatory output shape (summary, findings, clean pass, follow-ups)\n\n**Author**: Bruno Balderrama ([bmbalderrabano@gmail.com](mailto:bmbalderrabano@gmail.com)) (MIT, included with permission)\n\n#### split-commit\n\nAnalyze local git changes and return a copy-paste PowerShell script to split uncommitted work into multiple logical commits. The agent does not commit for the user.\n\n**Location**: `split-commit/`\n\n**Use when**: Splitting uncommitted changes into multiple commits, planning commit batches, or when the user wants a ready-to-run PowerShell sequence for staged commits.\n\n**Features**:\n\n- Read-only git inspection; no `git add` / `git commit` / `git push` by the agent\n- Commit message rules aligned with `.githooks/commit-msg` (branch-aware)\n- Copy-paste PowerShell output with per-file `git add` and conventional commit messages\n\n**Author**: Bruno Balderrama ([bmbalderrabano@gmail.com](mailto:bmbalderrabano@gmail.com)) (MIT, included with permission)\n\n### Productivity\n\nPlanning, design stress-testing, and decision-making workflows.\n\n#### clinical-tone\n\nEnforce a strictly objective, clinical, and non-condescending communication style.\n\n**Location**: `clinical-tone/`\n\n**Use when**: You want the AI to communicate like a senior engineer without sycophancy, apologies, over-enthusiasm, or didactic lectures.\n\n**Features**:\n\n- Strips away AI filler (\"Great idea!\", \"I apologize\", \"As an AI\")\n- Focuses on fact-based critique and direct answers\n- Prevents \"sandwich feedback\" (praise wrapping criticism)\n\n#### grill-me\n\nInterview the user relentlessly about a plan or design until reaching shared understanding. Walks each branch of the design tree one question at a time, with a recommended answer per question.\n\n**Location**: `grill-me/`\n\n**Use when**: Stress-testing a plan, getting grilled on a design, refining architecture before implementation, or when the user mentions \"grill me\".\n\n**Features**:\n\n- One question at a time; resolve decision dependencies sequentially\n- Recommended answer included with each question\n- Explores the codebase when a question can be answered there instead of asking the user\n\n**Source**: [mattpocock/skills](https://github.com/mattpocock/skills/blob/main/skills/productivity/grill-me/SKILL.md) (MIT)\n\n### Styling\n\nCSS frameworks and component libraries.\n\n#### tailwind-css\n\nSet up and use **Tailwind CSS v4 only** with Next.js (App Router), Vite, or CLI. No `tailwind.config.js`—theme and config via `@theme` in CSS. Best practices from official docs.\n\n**Location**: `tailwind-css/`\n\n**Use when**: Styling with Tailwind, configuring Tailwind, installing Tailwind, utility classes, `@theme`, `@layer`, `@utility`, or when the user mentions Tailwind CSS or Tailwind v4.\n\n**Features**:\n\n- Installation: Next.js (App Router, 15+), Vite, Tailwind CLI\n- Theme: `@theme` only (extend, override, namespaces, keyframes, inline)\n- Custom styles: `@layer base` / `@layer components`, `@utility`, `@custom-variant`\n- Arbitrary values and properties\n- Quick reference and common mistakes\n- **reference.md**: Official doc links, advanced theme options, default theme summary (indexable)\n\n**Docs**: [Tailwind CSS v4](https://tailwindcss.com/docs)\n\n#### shadcn-ui\n\nInstall and use shadcn/ui with **Tailwind v4** and Next.js (App Router), Vite, or manual setup. Configure `components.json`, add components via CLI, theming with CSS only (no Tailwind config file).\n\n**Location**: `shadcn-ui/`\n\n**Use when**: Adding shadcn/ui, installing shadcn, using Button, Card, Dialog, Form, or any shadcn component, or when the user mentions shadcn, shadcn/ui, or Radix UI with Tailwind.\n\n**Features**:\n\n- Quick start (`shadcn create`) and existing-project setup (Next.js, Vite)\n- `components.json` and path aliases\n- **Full list of official components** with CLI names and short descriptions (accordion, alert, button, card, dialog, form, sonner, table, etc.)\n- Theming with CSS variables and `@theme` (Tailwind v4)\n- Common patterns and mistakes\n- **reference.md**: Official doc links, Tailwind v4 + shadcn, component list, schema (indexable)\n\n**Docs**: [shadcn/ui](https://ui.shadcn.com/docs)\n\n### UI & animation\n\nComponent development and motion.\n\n#### gsap\n\nInstall and use GSAP (GreenSock Animation Platform) for high-performance JavaScript animations. Covers core utilities, React integration, and popular plugins.\n\n**Location**: `gsap/`\n\n**Use when**: Creating complex animations, scroll-based effects, UI transitions, SVG animations, or when the user mentions GSAP, GreenSock, or ScrollTrigger.\n\n**Features**:\n\n- Core utilities: Tween, Timeline, Eases\n- React integration with `@gsap/react` and `useGSAP`\n- Popular plugins: ScrollTrigger, Flip, Observer, etc.\n- Best practices for performance and FOUC prevention\n- **reference.md**: Official GSAP docs, core API, plugins, React integration — indexable\n\n**Docs**: [GSAP](https://gsap.com/docs/v3/)\n\n#### storybook\n\nInstall and use Storybook for developing UI components in isolation. Colocated stories in `system/` directory, CSF format, args, decorators, play functions, and testing.\n\n**Location**: `storybook/`\n\n**Use when**: Building component libraries, design systems, documenting UI components, testing components in isolation, or when the user mentions Storybook, stories, component development, or UI workshop.\n\n**Features**:\n\n- Installation for Next.js, Vite, React, Vue, Angular, Svelte\n- **system/** structure: components in folders with colocated `*.stories.tsx`\n- Component Story Format (CSF 3): meta, stories, args\n- Decorators, parameters, play functions for interaction tests\n- Vitest addon, accessibility, visual testing\n- **reference.md**: Official Storybook docs, frameworks, addons, testing — indexable\n\n**Docs**: [Storybook](https://storybook.js.org/docs)\n\n### Language & validation\n\nTypeScript, schemas, and API documentation.\n\n#### typescript\n\nUse TypeScript for type-safe JavaScript: types, interfaces, generics, narrowing, tsconfig, modules, and strict mode.\n\n**Location**: `typescript/`\n\n**Use when**: Writing or reviewing TypeScript, configuring tsconfig.json, defining types or interfaces, generics, type inference, or when the user mentions TypeScript, TS, or type checking.\n\n**Features**:\n\n- Everyday types, narrowing, functions, object types\n- Type manipulation: generics, keyof, typeof, mapped types, conditional types, utility types\n- Classes, modules\n- tsconfig.json and strict mode\n- **reference.md**: Official doc links (Handbook, Reference, TSConfig, Cheat Sheets) — indexable\n\n**Docs**: [TypeScript](https://www.typescriptlang.org/docs)\n\n#### zod\n\nDefine and use Zod schemas for TypeScript-first validation with static type inference (z.infer). Primitives, objects, arrays, unions, refinements, transform, parse, safeParse.\n\n**Location**: `zod/`\n\n**Use when**: Validating input, parsing API data, form validation with react-hook-form, or when the user mentions Zod, schema validation, or z.infer.\n\n**Features**:\n\n- Primitives, strings (email, url, uuid, datetime), numbers, objects, arrays, tuples, unions, discriminated unions\n- Refinements, transform, pipe\n- z.infer, z.input, z.output; parse / safeParse, ZodError\n- React Hook Form integration (zodResolver)\n- **reference.md**: Official Zod docs and API sections (zod.dev, API, llms.txt), Zod Mini, ecosystem — indexable\n\n**Docs**: [Zod](https://zod.dev)\n\n#### jsdoc\n\nWrite and maintain API documentation using JSDoc comments colocated with JavaScript/TypeScript code. Covers comment rules, core tags, and CLI generation.\n\n**Location**: `jsdoc/`\n\n**Use when**: Documenting functions/classes/modules, standardizing `@param` and `@returns`, generating API docs, or when the user mentions JSDoc tags like `@todo`.\n\n**Features**:\n\n- Comment block rules (`/** ... */`) and placement guidelines\n- Core tags (`@param`, `@returns`, `@constructor`, `@todo`)\n- Common examples for functions and constructor-style docs\n- CLI docs generation flow (`jsdoc file.js`)\n- **reference.md**: Official JSDoc docs links and command-line/config references — indexable\n\n**Docs**: [JSDoc](https://jsdoc.app/)\n\n### Performance\n\nWeb performance auditing and optimization.\n\n#### pagespeed-insights\n\nAudit web pages for performance optimization following PageSpeed Insights guidelines. Acts as a performance auditor that identifies bad practices and guides developers to achieve excellent PageSpeed scores.\n\n**Location**: `pagespeed-insights/`\n\n**Use when**: Analyzing page performance, optimizing web applications, reviewing performance metrics, implementing Core Web Vitals improvements, or when the user mentions page speed, performance optimization, Lighthouse scores, or Core Web Vitals.\n\n**Features**:\n\n- Complete PageSpeed Insights guidelines reference\n- Core Web Vitals thresholds and best practices\n- Common performance issues and solutions\n- Lab and field data interpretation\n- Performance optimization checklist\n- Accessibility and SEO best practices\n- Code examples for common optimizations\n- **reference.md**: Official PageSpeed, Lighthouse, Core Web Vitals, optimization guides — indexable\n\n**Docs**: [PageSpeed Insights](https://developers.google.com/speed/docs/insights/v5/about?hl=es-419)\n\n### SEO & AEO\n\nDiscoverability for search engines and AI assistants. Three format-specific skills — install the one that matches the task.\n\n#### sitemap\n\nCreate and maintain XML sitemaps per sitemaps.org for search engine crawl discovery.\n\n**Location**: `sitemap/`\n\n**Use when**: Adding `sitemap.xml`, sitemap index, Next.js `sitemap.ts`, `lastmod`, `changefreq`, robots.txt `Sitemap:` directive, or when the user mentions sitemap or URL discovery.\n\n**Features**:\n\n- XML protocol 0.9 (`urlset`, `sitemapindex`, tags, limits)\n- Entity escaping, placement rules, FAQ highlights\n- Next.js `MetadataRoute.Sitemap` pattern\n- vs JSON-LD and llms.txt\n- **reference.md**: sitemaps.org protocol, FAQ, XSD, Google — indexable\n\n**Docs**: [sitemaps.org](https://www.sitemaps.org/protocol.html)\n\n#### json-ld\n\nAdd and validate JSON-LD structured data with schema.org for SEO rich results. Based on W3C JSON-LD 1.1 and Google Search Central.\n\n**Location**: `json-ld/`\n\n**Use when**: Structured data, schema markup, `application/ld+json`, Organization, WebSite, Article, Product, FAQ, BreadcrumbList, JSON-LD, schema.org, or rich snippets.\n\n**Features**:\n\n- Core JSON-LD syntax, Next.js embedding, common schema.org types\n- Validation workflow (Playground, Rich Results Test)\n- Google SEO guidelines and common mistakes\n- **reference.md**: W3C, schema.org, Google Search Central — indexable\n\n**Docs**: [JSON-LD 1.1](https://www.w3.org/TR/json-ld11/) · [schema.org](https://schema.org/)\n\n#### llms-txt\n\nCreate `llms.txt` per llmstxt.org for AI assistants and AEO/GEO.\n\n**Location**: `llms-txt/`\n\n**Use when**: Adding `llms.txt`, `llms-full.txt`, AI-readable site maps, agent context, AEO, GEO, or when the user mentions llms.txt or llmstxt.\n\n**Features**:\n\n- Official spec format (H1, blockquote, file lists, `## Optional`)\n- Static and dynamic Next.js delivery\n- `.md` mirrors, llms-ctx; vs sitemap and JSON-LD\n- **reference.md**: llmstxt.org, tools, examples — indexable\n\n**Docs**: [llmstxt.org](https://llmstxt.org/)\n\n## Structure\n\nEach skill follows the standard skills.sh structure:\n\n```\nskill-name/\n├── SKILL.md          # Required: metadata + instructions\n├── reference.md      # Optional: official docs, deep reference (tailwind-css, shadcn-ui)\n└── LICENSE.md        # Optional\n```\n\nSkills live at the repository root (no nested group folders) so `npx skills add --skill <name>` works out of the box.\n\n## Installation\n\n### Tooling\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill anti-cliche\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill conventional-commits\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill code-review\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill split-commit\n```\n\n### Productivity\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill clinical-tone\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill grill-me\n```\n\n### Styling\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill tailwind-css\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill shadcn-ui\n```\n\n### UI & animation\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill gsap\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill storybook\n```\n\n### Language & validation\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill typescript\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill zod\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill jsdoc\n```\n\n### Performance\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill pagespeed-insights\n```\n\n### SEO & AEO\n\n```bash\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill sitemap\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill json-ld\nnpx skills add https://github.com/EnderPuentes/ai-agent-skills --skill llms-txt\n```\n\nFor more information about using skills in your agent, follow the [skills.sh integration guide](https://skills.sh).\n\n## Contributing\n\nWhen adding new skills, ensure they follow:\n\n- Skills.sh specification\n- Conventional Commits for commit messages\n- Clear, concise documentation\n- Practical examples\n",
  "bytes": 15711,
  "sha": "aab02577890a8a2d1a1bb9aecb67f727a682c50333bfe4313a2b254142a42f73",
  "repo_slug": "enderpuentes/ai-agent-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_enderpuentes_ai_agent_skills_pagespeed_i_82fa522f/readme"
}