Two files, one repository
joabgonzalez/ai-agents-skills ships 1 format across 3 indexed files. The question worth asking is whether the second one says anything the first does not.
| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 9 | 18 | 6 | 27% |
| Commands | 0 | 5 | 0 | 0% |
| Section tags | 5 | 6 | 1 | 42% |
What each file covers
Sections
9 shared · 18 only in A · 6 only in B- − AI Agents Skills Framework
- − Mandatory Skills
- − Project Structure
- − Skills Storage Architecture
- − Create a Skill
- − Create an Agent
- − Update Website
- − Install Skills
- − Git & Release Workflow
- − Branching
- − Commit Strategy
- − Merge to Main (Squash)
- − Versioning & Release
- − CodeGraph
- − When to prefer codegraph over native search
- − Rules of thumb
- − If `.codegraph/` doesn't exist
- − References
- + Alpha Template Agent
- + Purpose
- + Project Structure & Skills Storage
- + Supported Stack
- + Feature Development
- + Code Review
- How to Use Skills (MANDATORY WORKFLOW)
- Step 1: Find the Trigger
- Step 2: Read the Skill
- Step 3: Read Dependencies
- Step 4: Apply Patterns
- Example Workflow
- Skills Reference
- Workflows
- Policies
Commands
0 shared · 5 only in A · 0 only in B- − npx ai-agents-skills local
- − npx ai-agents-skills local --models claude
- − npx ai-agents-skills validate --all
- − npx ai-agents-skills validate --skill {name}
- − npm version <type>
Section tags
5 shared · 6 only in A · 1 only in B- − setup
- − build
- − test
- − deployment
- − do-not
- − docs
- + types
- code-style
- architecture
- git-pr
- dependencies
- agent-behaviour
Line diff
joabgonzalez/ai-agents-skills · AGENTS.md
@@ −1 @@
1---
2name: ai-agents-skills
3description: "CLI framework for managing and distributing 50+ AI agent skills across 11 AI agents (3 dedicated + 8 universal)."
4license: "Apache 2.0"
5metadata:
6 version: "1.0"
7 skills:
8 - skill-creation
9 - agent-creation
10 - typescript
11 - nodejs
12 - nodejs-best-practices
13 - code-conventions
14 - critical-partner
15 - unit-testing
16 - jest
17 - brainstorming
18 - astro
19 - astro-best-practices
20 - tailwindcss
21 - css-best-practices
22 - a11y
23 - frontend-dev
24 - interface-design
25 - technical-communication
26 - reference-creation
27 - skill-sync
28 - systematic-debugging
29 - html
30 - css
31 - javascript
32 - english-writing
33 - code-review
34 - receiving-code-review
35 - writing-plans
36 - verification-protocol
37 - prompt-creation
38 - sharp-execution
39 - lean-output
40 - ship-branch
41 - grill-me
42 - context-handoff
43---
44
45# AI Agents Skills Framework
46
47CLI for creating, managing, and distributing AI agent skills across 11 AI agents. Local-first architecture with symlink-based installation, dependency resolution, and token-efficient model instructions.
48
49## How to Use Skills (MANDATORY WORKFLOW)
50
51This project has skills installed in your model's skills directory. Follow this protocol for ALL coding tasks:
52
53### Step 1: Find the Trigger
54
55Check the "Mandatory Skills" table below. Match your task to the "Trigger" column.
56
57### Step 2: Read the Skill
58
59Find your agent below and use the corresponding path:
60
61| Agent | Skills path |
62|-------|------------|
63| Claude Code | `.claude/skills/{skill-name}/SKILL.md` |
64| Antigravity | `.agent/skills/{skill-name}/SKILL.md` |
65| OpenClaw | `skills/{skill-name}/SKILL.md` |
66| Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode | `.agents/skills/{skill-name}/SKILL.md` |
67
68**Shortcut:** All skill source files live at `skills/{skill-name}/SKILL.md` — if your agent can't resolve symlinks, read from there directly.
69
70### Step 3: Read Dependencies
71
@@ −86 @@
86**Task:** "Create TypeScript interface for User model"
87
881. **Check table below** → Trigger: "TypeScript types/interfaces" → Skill: `typescript`
892. **Read:** `skills/typescript/SKILL.md` (or your agent's path from Step 2)
903. **Check frontmatter** → Dependencies: `javascript`
914. **Read dependency:**
92 - `skills/javascript/SKILL.md` (which depends on `code-conventions`)
935. **Apply patterns:** Use `interface` (not `type`), PascalCase names, export from `types/` directory
94
95## Mandatory Skills
96
97**Path:** Use the table in Step 2 above to find the correct path for your agent.
98
99| Trigger | Skill |
100| -------------------------------- | ---------------- |
101| Create or modify skills | skill-creation |
102| Create agent definitions | agent-creation |
103| Code review or improvements | critical-partner |
104| Coding standards | code-conventions |
105| TypeScript code | typescript |
106| Node.js / CLI development | nodejs |
107| Writing unit tests | unit-testing |
108| Jest test suite or config | jest |
109| Exploring ideas or approaches | brainstorming |
110| Astro pages, layouts, components | astro |
111| Tailwind utilities or styling | tailwindcss |
112| Accessibility or UI components | a11y |
113| Frontend workflow or components | frontend-dev |
114| UI/UX decisions or design review | interface-design |
115| Writing architecture or spike docs | tech-docs |
116| Commit messages or documentation | technical-communication|
117| Creating reference files | reference-creation |
118| Syncing skills across models | skill-sync |
119| Debugging errors or root cause | systematic-debugging |
120| HTML markup or structure | html |
121| CSS properties or animations | css |
122| JavaScript patterns or scripts | javascript |
123| Writing skill content in English | english-writing |
124| Formal code review checklist | code-review |
125| Processing incoming review feedback | receiving-code-review |
126| Planning implementation tasks | writing-plans |
127| Verifying task completion | verification-protocol |
128| Creating model prompt files | prompt-creation |
129| Agent overthinking or hesitation | sharp-execution |
130| Minimize response tokens | lean-output |
131| Shipping or closing a branch | ship-branch |
132| Clarify requirements before acting | grill-me |
133| Summarize session for new chat | context-handoff |
134| Auth, JWT, OAuth, password hashing | authentication |
135| Dockerfiles or containerization | docker |
136| GraphQL schemas or resolvers | graphql |
137| Documenting a design system | design-system-spec |
138| React code quality review | react-best-practices |
139| Astro site quality review | astro-best-practices |
140| CSS architecture review | css-best-practices |
141| Node.js service quality review | nodejs-best-practices |
142
143## Skills Reference
144
14550+ skills organized by category (exact count shown as nearest lower multiple of 50: 50+, 100+, 150+, etc.):
146
147- **Frameworks:** React, Next.js, Astro, Express, Nest, Hono, React Native, Expo
148- **Best Practices:** React Best Practices, Astro Best Practices, CSS Best Practices, Node.js Best Practices
149- **Testing:** Jest, Playwright, React Testing Library, React Native Testing Library, E2E Testing, Unit Testing, Testing Strategy
150- **Standards:** TypeScript, JavaScript, HTML, CSS, TailwindCSS, A11y
151- **Backend & Infrastructure:** Node.js, Express, Nest, Hono, Bun, Backend Development, Authentication, Docker, GraphQL
152- **Web:** Web Performance, Web SEO, Design System Spec
153- **Build Tools:** Vite, Webpack
154- **Libraries:** MUI, AG Grid, Redux Toolkit, Stagehand
155- **Quality & Architecture:** Code Conventions, Code Quality, Form Validation, Critical Partner, Code Refactoring
156- **Architecture Patterns:** Architecture Patterns, SOLID, Clean Architecture, Domain-Driven Design, Hexagonal Architecture, Result Pattern, DRY Principle, Mediator Pattern, Sidecar Pattern, Composition Pattern, Circuit Breaker Pattern, State Machines Pattern, Screaming Architecture
157- **Documentation:** Tech Docs
158- **Behavioral:** English Writing, Technical Communication, Humanizer, Frontend Development, Brainstorming, Systematic Debugging, Interface Design, Writing Plans, Code Review, Receiving Code Review, Verification Protocol, Plan Execution, Subagent Orchestration, Sharp Execution, Lean Output, Ship Branch, Grill Me, Context Handoff
159- **Meta:** Skill Creation, Agent Creation, Reference Creation, Prompt Creation, Skill Sync
160
161## Project Structure
162
163```
164ai-agents-skills/
165├── skills/ # 50+ skill definitions (SKILL.md format) - SOURCE OF TRUTH
166│ ├── react/
167│ │ ├── SKILL.md
168│ │ └── references/ # Progressive disclosure for complex skills
169│ ├── typescript/
170│ │ └── SKILL.md
171│ └── ...
172├── .agents/skills/ # Canonical symlinks → skills/ (universal: 8 agents read here natively)
173│ ├── react/ → ../../skills/react/
174│ ├── typescript/ → ../../skills/typescript/
175│ └── ...
176├── .claude/skills/ # Claude Code symlinks → .agents/skills/
177│ ├── react/ → ../../.agents/skills/react/
178│ └── typescript/ → ../../.agents/skills/typescript/
179├── .agent/skills/ # Antigravity symlinks → .agents/skills/
180├── presets/ # Project Starter Preset (AGENTS.md + skills bundle)
181├── src/ # TypeScript CLI source
182│ ├── commands/ # CLI commands (local, add, remove, sync, validate, list)
183│ ├── core/ # Dependency resolver, installer, skill parser
184│ └── utils/ # Logger, YAML parser, instruction generator
185├── templates/ # Model instruction templates
186├── website/ # Astro SSG skill catalog website
187│ ├── src/
188│ │ ├── content/ # Content collections (skills, references)
189│ │ ├── layouts/ # BaseLayout, SkillLayout
190│ │ ├── pages/ # Index, getting-started, skills/[name], references/[ref]
191│ │ ├── components/ # SkillMeta, ReferenceSidebar, TableOfContents, etc.
192│ │ └── styles/ # global.css (Tailwind v4 CSS-based config)
193│ ├── astro.config.mjs
194│ └── package.json
195└── AGENTS.md # This file
196```
197
198**IMPORTANT FOR LLMs:** When reading skills, you will encounter a 3-layer symlink structure:
199
2001. **Source of truth:** `skills/<skill-name>/SKILL.md` (real files, always read from here)
2012. **Canonical layer:** `.agents/skills/<skill-name>/` → `skills/<skill-name>/` (shared symlinks)
2023. **Model-specific layer:** `.claude/skills/` and `.agent/skills/` → `.agents/skills/` (dedicated model symlinks)
203
204**How to access skills:**
205
206- **Preferred:** Read directly from `skills/<skill-name>/SKILL.md` (bypasses symlinks — always works)
207- **Alternative:** Use your agent's path from Step 2 if your IDE resolves symlinks automatically
208- **If symlinks fail:** All real skill files are in `skills/` directory
209
210### Skills Storage Architecture
211
212**Why 3 layers?**
213
2141. **Layer 1 (skills/):** Single source of truth — edit once, affects all agents
2152. **Layer 2 (.agents/skills/):** Canonical shared location — 8 universal agents read here natively
2163. **Layer 3 (.claude/skills/, .agent/skills/):** Dedicated model symlinks for Claude Code and Antigravity
217
218**Benefits:**
219
220- **Zero duplication:** Skills stored once, available to all 11 agents
221- **Always up-to-date:** Changes propagate instantly (symlinks reference same files)
222- **Token-efficient:** Models read only the skills they need
223
224**Example flow:**
225
226```
227User edits: skills/react/SKILL.md
228 ↓
229Symlink: .agents/skills/react/ → skills/react/
230 ↓
231Universal agents (Amp, Cline, Codex, Cursor, Gemini, Copilot, Kimi, OpenCode)
232 read: .agents/skills/react/ directly
233 ↓
234Dedicated agents get additional symlinks:
235 .claude/skills/react/ → .agents/skills/react/ (Claude Code)
236 .agent/skills/react/ → .agents/skills/react/ (Antigravity)
237 ↓
238OpenClaw reads: skills/react/ directly (project root, no symlink needed)
239 ↓
240All 11 agents see updated react skill instantly
241```
242
243## Workflows
244
245### Create a Skill
246
2471. Read `skills/skill-creation/SKILL.md`
2482. `mkdir skills/{name}` + copy SKILL-TEMPLATE.md
2493. Write SKILL.md with frontmatter and sections
2504. Validate: `npx ai-agents-skills validate --skill {name}`
2515. Install: `npx ai-agents-skills local`
252
253### Create an Agent
254
2551. Read `skills/agent-creation/SKILL.md`
2562. Gather context (9 questions)
2573. Create `presets/{project-name}/AGENTS.md`
2584. Validate all referenced skills exist
259
260### Update Website
261
262The website (`website/`) is an Astro SSG site that auto-renders skills from `skills/` via content collections.
263
2641. Read `skills/astro/SKILL.md` and `skills/tailwindcss/SKILL.md`
2652. Pages live in `website/src/pages/` — skills rendered via `[name]/index.astro`
2663. Layouts: `BaseLayout.astro` (shell), `SkillLayout.astro` (two-column with sidebar)
2674. Components: `SkillMeta`, `ReferenceSidebar`, `TableOfContents`, `Breadcrumb`
2685. Styles: Tailwind v4 via `@theme` in `website/src/styles/global.css` (no `tailwind.config.*`)
2696. Build: `cd website && npm run build` — deploys via GitHub Actions on push to `main`
270
271**Key conventions:**
272- Reference sidebar uses `{slug, title}[]` — titles extracted from H1 of each reference file
273- Skills H1: topic name only, no "Skill" suffix (e.g., `# React`, not `# React Skill`)
274- `---` separator required before every `##` section except the first
275
276### Install Skills
277
278```bash
279npx ai-agents-skills local # Install to all detected models
280npx ai-agents-skills local --models claude # Install to specific model
281npx ai-agents-skills validate --all # Validate all skills
282```
283
284## Policies
285
286- **Explicit dependencies:** Skills declare all their dependencies in `metadata.skills` — no hidden auto-includes
287- **Dependency resolution:** Auto-resolve with cycle detection and topological sort
288- **Two-tier model architecture:**
289 - **Dedicated models** — require their own skills directory:
290 - Claude Code (`.claude/skills/`), Antigravity (`.agent/skills/`), OpenClaw (`skills/`)
291 - **Universal models** — read `.agents/skills/` natively, no extra directory needed:
292 - Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode
293- **Symlink architecture:** 3-layer structure for zero duplication:
294 - **Layer 1:** `skills/` (source of truth — real files; also OpenClaw's native path)
295 - **Layer 2:** `.agents/skills/` → `skills/` (canonical shared symlinks — universal coverage)
296 - **Layer 3:** `.claude/skills/` and `.agent/skills/` → `.agents/skills/` (dedicated model symlinks)
297 - **Individual skill symlinks:** Each skill gets its own symlink (NOT directory-level)
298 - **Instant propagation:** Changes to source files visible to all agents immediately
299- **Auto-generated instructions:** Each model gets an instruction file listing all installed skills with their metadata
300- **Dependency-safe removal:** `remove` command validates dependencies before removing skills
301- **11 agents supported:** 3 dedicated (Claude Code, Antigravity, OpenClaw) + 8 universal (Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode)
302
303## Git & Release Workflow
304
305### Branching
306
307- **`main`** — production, always stable, tagged releases only
308- **`development`** — integration branch, all feature work merges here first
309- Feature branches off `development`, never off `main`
310
311### Commit Strategy
312
313- **Use skill:** `technical-communication` for all commit messages
314- **Format:** single line, imperative, no co-author
315- **Examples:**
316 - `fix: show interactive selector when all AGENTS.md skills installed`
317 - `feat: add PostHog analytics for web and CLI`
318 - `chore: update OG image to match logo`
319- **Group by feature:** separate commits per logical change, never batch unrelated changes
320
321### Merge to Main (Squash)
322
323Merges from `development` → `main` use **squash merge**. The squash commit message format encodes the release type and triggers the auto-release pipeline:
324
325```
326release(patch|minor|major): {brief summary of what's in the squash}
327```
328
329Examples:
330- `release(patch): telemetry + PostHog analytics + CI release pipeline`
331- `release(minor): preset system overhaul + new skills`
332
333### Versioning & Release
334
335Versions follow **semver**: `MAJOR.MINOR.PATCH`
336
337| Change type | Squash merge prefix | Example |
338|---|---|---|
339| Bug fix, small improvement | `release(patch): ...` | 1.6.0 → 1.6.1 |
340| New feature, backwards-compatible | `release(minor): ...` | 1.6.0 → 1.7.0 |
341| Breaking change | `release(major): ...` | 1.6.0 → 2.0.0 |
342
343**Release flow:**
3441. Work on `development`, commit with single-line messages
3452. Squash merge to `main` with a `release(patch|minor|major): {summary}` message
3463. `auto-release.yml` detects the prefix on push to `main`, runs `npm version <type>`, and pushes the version commit + tag — no manual command needed
3474. `auto-release.yml` bumps the version, builds, publishes to npm, updates the README badge, and syncs back to `development` — all in one pipeline
348
349**Tags always go on `main`**, never on `development`.
350
351## CodeGraph
352
353This project has a CodeGraph MCP server (`codegraph_*` tools) configured. CodeGraph is a tree-sitter-parsed knowledge graph of every symbol, edge, and file. Reads are sub-millisecond and return structural information grep cannot.
354
355### When to prefer codegraph over native search
356
357Use codegraph for **structural** questions — what calls what, what would break, where is X defined, what is X's signature. Use native grep/read only for **literal text** queries (string contents, comments, log messages) or after you already have a specific file open.
358
359| Question | Tool |
360|---|---|
361| "Where is X defined?" / "Find symbol named X" | `codegraph_search` |
362| "What calls function Y?" | `codegraph_callers` |
363| "What does Y call?" | `codegraph_callees` |
364| "What would break if I changed Z?" | `codegraph_impact` |
365| "Show me Y's signature / source / docstring" | `codegraph_node` |
366| "Give me focused context for a task/area" | `codegraph_context` |
367| "Survey an unfamiliar module/topic" | `codegraph_explore` |
368| "What files exist under path/" | `codegraph_files` |
369| "Is the index healthy?" | `codegraph_status` |
370
371### Rules of thumb
372
373- **Trust codegraph results.** They come from a full AST parse. Do NOT re-verify them with grep — that's slower, less accurate, and wastes context.
374- **Don't grep first** when looking up a symbol by name. `codegraph_search` is faster and returns kind + location + signature in one call.
375- **Don't chain `codegraph_search` + `codegraph_node`** when you just want context — `codegraph_context` is one call.
376- **`codegraph_explore` is the heavy hitter** for unfamiliar areas — returns full source from all relevant files in one call, but is token-heavy.
377- **Index lag**: the file watcher debounces ~500ms behind writes; don't re-query immediately after editing a file in the same turn.
378
379### If `.codegraph/` doesn't exist
380
381The MCP server returns "not initialized." Ask the user: *"I notice this project doesn't have CodeGraph initialized. Want me to run `codegraph init -i` to build the index?"*
382
383## References
384
385- [AGENTS.md Spec](https://agents.md/)
386- [Agent Skills](https://agentskills.io/)
387
joabgonzalez/ai-agents-skills · presets/project-alpha/AGENTS.md
@@ +1 @@
1---
2name: alpha-template
3description: "Development assistant for a web application. TypeScript/React with strict typing, MUI, Redux Toolkit, AG Grid, form validation."
4metadata:
5 version: "1.0"
6 skills:
7 - typescript
8 - javascript
9 - react
10 - webpack
11 - redux-toolkit
12 - mui
13 - ag-grid
14 - form-validation
15 - html
16 - a11y
17 - code-conventions
18 - technical-communication
19 - critical-partner
20 - interface-design
21 - frontend-dev
22---
23
24# Alpha Template Agent
25
26## Purpose
27
28Primary development assistant for a web application. Ensures strict typing, MUI best practices, accessibility, and version compatibility across Redux Toolkit, AG Grid, and form validation integrations.
29
30## How to Use Skills (MANDATORY WORKFLOW)
31
32This project has skills installed in your model's skills directory. Follow this protocol for ALL coding tasks:
33
34### Step 1: Find the Trigger
35
36Check the "Skills Reference" table below. Match your task to the "Trigger" column.
37
38### Step 2: Read the Skill
39
40**Path format:** `.{model}/skills/{skill-name}/SKILL.md`
41
42Replace `{model}` with your coding agent:
43
44- **Cursor:** `.cursor/skills/typescript/SKILL.md`
45- **Claude:** `.claude/skills/typescript/SKILL.md`
46- **Copilot:** `.github/skills/typescript/SKILL.md`
47- **Gemini:** `.gemini/skills/typescript/SKILL.md`
48- **Codex:** `.codex/skills/typescript/SKILL.md`
49
50### Step 3: Read Dependencies
51
@@ +66 @@
66**Task:** "Create TypeScript interface for User model"
67
681. **Check table below** → Trigger: "TypeScript types/interfaces" → Skill: `typescript`
692. **Read:** `.{model}/skills/typescript/SKILL.md`
703. **Check frontmatter** → Dependencies: `javascript`
714. **Read dependency:**
72 - `.{model}/skills/javascript/SKILL.md` (which depends on `code-conventions`)
735. **Apply patterns:** Use `interface` (not `type`), PascalCase names, export from `types/` directory
74
75## Skills Reference
76
77**Path format:** `.{model}/skills/{skill-name}/SKILL.md` (see Step 2 above)
78
79| Trigger | Skill |
80| ----------------------------- | ----------------------- |
81| TypeScript types/interfaces | typescript |
82| JavaScript (ES2020+) | javascript |
83| React components/hooks | react |
84| Webpack build config | webpack |
85| Redux state / RTK Query | redux-toolkit |
86| MUI components/theming | mui |
87| AG Grid tables | ag-grid |
88| Forms, validation schemas | form-validation |
89| Commit messages, PRs, docs | technical-communication |
90| Code review | critical-partner |
91| Semantic HTML | html |
92| Accessibility | a11y |
93| Coding standards | code-conventions |
94| UI/UX design, flows | interface-design |
95| Frontend development workflow | frontend-dev |
96
97## Project Structure & Skills Storage
98
99**IMPORTANT FOR LLMs:** Skills use a 3-layer symlink structure:
100
101```
102your-project/
103├── .agents/skills/ # Canonical symlinks to framework skills/ (shared across models)
104│ ├── react/ → ../../skills/react/
105│ ├── typescript/ → ../../skills/typescript/
106│ └── ...
107├── .claude/skills/ # Claude-specific symlinks to .agents/skills/
108│ ├── react/ → ../../.agents/skills/react/
109│ └── typescript/ → ../../.agents/skills/typescript/
110├── .cursor/skills/ # Cursor-specific symlinks to .agents/skills/
111├── .github/skills/ # Copilot-specific symlinks to .agents/skills/
112├── .gemini/skills/ # Gemini-specific symlinks to .agents/skills/
113├── .codex/skills/ # Codex-specific symlinks to .agents/skills/
114└── AGENTS.md # This file
115```
116
117**How to access skills:**
118
119- **Preferred:** Read from `.{model}/skills/<skill-name>/SKILL.md` (your model's directory)
120- **If symlinks fail:** Skills are stored in the ai-agents-skills framework installation (referenced via symlinks)
121- **Real files location:** All source skills are in the framework's `skills/` directory
122
123**Why 3 layers?**
124
1251. **Layer 1 (framework skills/):** Source of truth maintained by framework
1262. **Layer 2 (.agents/skills/):** Canonical shared location in your project
1273. **Layer 3 (.{model}/skills/):** Model-specific access for your AI assistant
128
129**Benefits:**
130
131- **Zero duplication:** Skills installed once, available to all 5 AI models
132- **Always up-to-date:** Changes propagate instantly via symlinks
133- **Token-efficient:** Your AI reads only the skills it needs
134
135## Supported Stack
136
137- **Languages:** TypeScript 5.6.2, JavaScript (ES2020+)
138- **Frameworks:** React 18.3.1, Webpack (latest)
139- **State:** Redux 5.0.1, React-Redux 9.2.0, Redux Toolkit 2.5.1, RTK Query
140- **UI:** MUI 5.15.14, MUI X Charts 7.7.1, MUI X Date Pickers Pro 5.0.20
141- **Data:** AG Grid (latest stable)
142- **Forms:** Context-aware (see form-validation skill — checks package.json for installed library)
143- **Build:** Webpack
144- **Code Quality:** Context-aware (see code-quality skill — checks package.json for installed tools)
145
146## Workflows
147
148### Feature Development
149
1501. Gather requirements and clarify acceptance criteria
1512. Design component architecture with TypeScript interfaces
1523. Implement React components using MUI
1534. Configure Redux Toolkit slices / RTK Query endpoints
1545. Implement forms with validation (see form-validation skill)
1556. Ensure accessibility (semantic HTML, ARIA, keyboard nav)
1567. Test with strict TypeScript, document changes, request review
157
158### Code Review
159
1601. Verify strict TypeScript (no `any`, explicit return types)
1612. Check MUI usage, theming consistency, accessibility
1623. Review Redux patterns and RTK Query cache config
1634. Confirm version compatibility with supported stack
164
165## Policies
166
167**Typing:** strict mode, no `any` (use `unknown`/generics), explicit return types, prefer interfaces
168
169**Code quality:** Context-aware linting and formatting (see code-quality skill), format before committing
170
171**Accessibility:** Semantic MUI components, keyboard-accessible elements, proper heading hierarchy, labeled form fields
172
173**Versions:**
174
175- Exact: TypeScript 5.6.2, React 18.3.1, RTK 2.5.1, MUI 5.15.14
176- Ranges: TS >=5.4 <6.0, React >=18.0 <19.0, RTK >=1.8 <3.0, MUI >=5.0 <6.0
177
@@ −1 +1 @@
11 ---
2−name: ai-agents-skills
3−description: "CLI framework for managing and distributing 50+ AI agent skills across 11 AI agents (3 dedicated + 8 universal)."
4−license: "Apache 2.0"
2+name: alpha-template
3+description: "Development assistant for a web application. TypeScript/React with strict typing, MUI, Redux Toolkit, AG Grid, form validation."
54 metadata:
65 version: "1.0"
76 skills:
8− - skill-creation
9− - agent-creation
107 - typescript
11− - nodejs
12− - nodejs-best-practices
8+ - javascript
9+ - react
10+ - webpack
11+ - redux-toolkit
12+ - mui
13+ - ag-grid
14+ - form-validation
15+ - html
16+ - a11y
1317 - code-conventions
18+ - technical-communication
1419 - critical-partner
15− - unit-testing
16− - jest
17− - brainstorming
18− - astro
19− - astro-best-practices
20− - tailwindcss
21− - css-best-practices
22− - a11y
23− - frontend-dev
2420 - interface-design
25− - technical-communication
26− - reference-creation
27− - skill-sync
28− - systematic-debugging
29− - html
30− - css
31− - javascript
32− - english-writing
33− - code-review
34− - receiving-code-review
35− - writing-plans
36− - verification-protocol
37− - prompt-creation
38− - sharp-execution
39− - lean-output
40− - ship-branch
41− - grill-me
42− - context-handoff
21+ - frontend-dev
4322 ---
4423
45−# AI Agents Skills Framework
24+# Alpha Template Agent
4625
47−CLI for creating, managing, and distributing AI agent skills across 11 AI agents. Local-first architecture with symlink-based installation, dependency resolution, and token-efficient model instructions.
26+## Purpose
4827
28+Primary development assistant for a web application. Ensures strict typing, MUI best practices, accessibility, and version compatibility across Redux Toolkit, AG Grid, and form validation integrations.
29+
4930 ## How to Use Skills (MANDATORY WORKFLOW)
5031
5132 This project has skills installed in your model's skills directory. Follow this protocol for ALL coding tasks:
5233
5334 ### Step 1: Find the Trigger
5435
55−Check the "Mandatory Skills" table below. Match your task to the "Trigger" column.
36+Check the "Skills Reference" table below. Match your task to the "Trigger" column.
5637
5738 ### Step 2: Read the Skill
5839
59−Find your agent below and use the corresponding path:
40+**Path format:** `.{model}/skills/{skill-name}/SKILL.md`
6041
61−| Agent | Skills path |
62−|-------|------------|
63−| Claude Code | `.claude/skills/{skill-name}/SKILL.md` |
64−| Antigravity | `.agent/skills/{skill-name}/SKILL.md` |
65−| OpenClaw | `skills/{skill-name}/SKILL.md` |
66−| Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode | `.agents/skills/{skill-name}/SKILL.md` |
42+Replace `{model}` with your coding agent:
6743
68−**Shortcut:** All skill source files live at `skills/{skill-name}/SKILL.md` — if your agent can't resolve symlinks, read from there directly.
44+- **Cursor:** `.cursor/skills/typescript/SKILL.md`
45+- **Claude:** `.claude/skills/typescript/SKILL.md`
46+- **Copilot:** `.github/skills/typescript/SKILL.md`
47+- **Gemini:** `.gemini/skills/typescript/SKILL.md`
48+- **Codex:** `.codex/skills/typescript/SKILL.md`
6949
7050 ### Step 3: Read Dependencies
7151
@@ −86 +66 @@
8666 **Task:** "Create TypeScript interface for User model"
8767
8868 1. **Check table below** → Trigger: "TypeScript types/interfaces" → Skill: `typescript`
89−2. **Read:** `skills/typescript/SKILL.md` (or your agent's path from Step 2)
69+2. **Read:** `.{model}/skills/typescript/SKILL.md`
9070 3. **Check frontmatter** → Dependencies: `javascript`
9171 4. **Read dependency:**
92− - `skills/javascript/SKILL.md` (which depends on `code-conventions`)
72+ - `.{model}/skills/javascript/SKILL.md` (which depends on `code-conventions`)
9373 5. **Apply patterns:** Use `interface` (not `type`), PascalCase names, export from `types/` directory
9474
95−## Mandatory Skills
96−
97−**Path:** Use the table in Step 2 above to find the correct path for your agent.
98−
99−| Trigger | Skill |
100−| -------------------------------- | ---------------- |
101−| Create or modify skills | skill-creation |
102−| Create agent definitions | agent-creation |
103−| Code review or improvements | critical-partner |
104−| Coding standards | code-conventions |
105−| TypeScript code | typescript |
106−| Node.js / CLI development | nodejs |
107−| Writing unit tests | unit-testing |
108−| Jest test suite or config | jest |
109−| Exploring ideas or approaches | brainstorming |
110−| Astro pages, layouts, components | astro |
111−| Tailwind utilities or styling | tailwindcss |
112−| Accessibility or UI components | a11y |
113−| Frontend workflow or components | frontend-dev |
114−| UI/UX decisions or design review | interface-design |
115−| Writing architecture or spike docs | tech-docs |
116−| Commit messages or documentation | technical-communication|
117−| Creating reference files | reference-creation |
118−| Syncing skills across models | skill-sync |
119−| Debugging errors or root cause | systematic-debugging |
120−| HTML markup or structure | html |
121−| CSS properties or animations | css |
122−| JavaScript patterns or scripts | javascript |
123−| Writing skill content in English | english-writing |
124−| Formal code review checklist | code-review |
125−| Processing incoming review feedback | receiving-code-review |
126−| Planning implementation tasks | writing-plans |
127−| Verifying task completion | verification-protocol |
128−| Creating model prompt files | prompt-creation |
129−| Agent overthinking or hesitation | sharp-execution |
130−| Minimize response tokens | lean-output |
131−| Shipping or closing a branch | ship-branch |
132−| Clarify requirements before acting | grill-me |
133−| Summarize session for new chat | context-handoff |
134−| Auth, JWT, OAuth, password hashing | authentication |
135−| Dockerfiles or containerization | docker |
136−| GraphQL schemas or resolvers | graphql |
137−| Documenting a design system | design-system-spec |
138−| React code quality review | react-best-practices |
139−| Astro site quality review | astro-best-practices |
140−| CSS architecture review | css-best-practices |
141−| Node.js service quality review | nodejs-best-practices |
142−
14375 ## Skills Reference
14476
145−50+ skills organized by category (exact count shown as nearest lower multiple of 50: 50+, 100+, 150+, etc.):
77+**Path format:** `.{model}/skills/{skill-name}/SKILL.md` (see Step 2 above)
14678
147−- **Frameworks:** React, Next.js, Astro, Express, Nest, Hono, React Native, Expo
148−- **Best Practices:** React Best Practices, Astro Best Practices, CSS Best Practices, Node.js Best Practices
149−- **Testing:** Jest, Playwright, React Testing Library, React Native Testing Library, E2E Testing, Unit Testing, Testing Strategy
150−- **Standards:** TypeScript, JavaScript, HTML, CSS, TailwindCSS, A11y
151−- **Backend & Infrastructure:** Node.js, Express, Nest, Hono, Bun, Backend Development, Authentication, Docker, GraphQL
152−- **Web:** Web Performance, Web SEO, Design System Spec
153−- **Build Tools:** Vite, Webpack
154−- **Libraries:** MUI, AG Grid, Redux Toolkit, Stagehand
155−- **Quality & Architecture:** Code Conventions, Code Quality, Form Validation, Critical Partner, Code Refactoring
156−- **Architecture Patterns:** Architecture Patterns, SOLID, Clean Architecture, Domain-Driven Design, Hexagonal Architecture, Result Pattern, DRY Principle, Mediator Pattern, Sidecar Pattern, Composition Pattern, Circuit Breaker Pattern, State Machines Pattern, Screaming Architecture
157−- **Documentation:** Tech Docs
158−- **Behavioral:** English Writing, Technical Communication, Humanizer, Frontend Development, Brainstorming, Systematic Debugging, Interface Design, Writing Plans, Code Review, Receiving Code Review, Verification Protocol, Plan Execution, Subagent Orchestration, Sharp Execution, Lean Output, Ship Branch, Grill Me, Context Handoff
159−- **Meta:** Skill Creation, Agent Creation, Reference Creation, Prompt Creation, Skill Sync
79+| Trigger | Skill |
80+| ----------------------------- | ----------------------- |
81+| TypeScript types/interfaces | typescript |
82+| JavaScript (ES2020+) | javascript |
83+| React components/hooks | react |
84+| Webpack build config | webpack |
85+| Redux state / RTK Query | redux-toolkit |
86+| MUI components/theming | mui |
87+| AG Grid tables | ag-grid |
88+| Forms, validation schemas | form-validation |
89+| Commit messages, PRs, docs | technical-communication |
90+| Code review | critical-partner |
91+| Semantic HTML | html |
92+| Accessibility | a11y |
93+| Coding standards | code-conventions |
94+| UI/UX design, flows | interface-design |
95+| Frontend development workflow | frontend-dev |
16096
161−## Project Structure
97+## Project Structure & Skills Storage
16298
99+**IMPORTANT FOR LLMs:** Skills use a 3-layer symlink structure:
100+
163101 ```
164−ai-agents-skills/
165−├── skills/ # 50+ skill definitions (SKILL.md format) - SOURCE OF TRUTH
166−│ ├── react/
167−│ │ ├── SKILL.md
168−│ │ └── references/ # Progressive disclosure for complex skills
169−│ ├── typescript/
170−│ │ └── SKILL.md
171−│ └── ...
172−├── .agents/skills/ # Canonical symlinks → skills/ (universal: 8 agents read here natively)
102+your-project/
103+├── .agents/skills/ # Canonical symlinks to framework skills/ (shared across models)
173104 │ ├── react/ → ../../skills/react/
174105 │ ├── typescript/ → ../../skills/typescript/
175106 │ └── ...
176−├── .claude/skills/ # Claude Code symlinks → .agents/skills/
107+├── .claude/skills/ # Claude-specific symlinks to .agents/skills/
177108 │ ├── react/ → ../../.agents/skills/react/
178109 │ └── typescript/ → ../../.agents/skills/typescript/
179−├── .agent/skills/ # Antigravity symlinks → .agents/skills/
180−├── presets/ # Project Starter Preset (AGENTS.md + skills bundle)
181−├── src/ # TypeScript CLI source
182−│ ├── commands/ # CLI commands (local, add, remove, sync, validate, list)
183−│ ├── core/ # Dependency resolver, installer, skill parser
184−│ └── utils/ # Logger, YAML parser, instruction generator
185−├── templates/ # Model instruction templates
186−├── website/ # Astro SSG skill catalog website
187−│ ├── src/
188−│ │ ├── content/ # Content collections (skills, references)
189−│ │ ├── layouts/ # BaseLayout, SkillLayout
190−│ │ ├── pages/ # Index, getting-started, skills/[name], references/[ref]
191−│ │ ├── components/ # SkillMeta, ReferenceSidebar, TableOfContents, etc.
192−│ │ └── styles/ # global.css (Tailwind v4 CSS-based config)
193−│ ├── astro.config.mjs
194−│ └── package.json
110+├── .cursor/skills/ # Cursor-specific symlinks to .agents/skills/
111+├── .github/skills/ # Copilot-specific symlinks to .agents/skills/
112+├── .gemini/skills/ # Gemini-specific symlinks to .agents/skills/
113+├── .codex/skills/ # Codex-specific symlinks to .agents/skills/
195114 └── AGENTS.md # This file
196115 ```
197116
198−**IMPORTANT FOR LLMs:** When reading skills, you will encounter a 3-layer symlink structure:
199−
200−1. **Source of truth:** `skills/<skill-name>/SKILL.md` (real files, always read from here)
201−2. **Canonical layer:** `.agents/skills/<skill-name>/` → `skills/<skill-name>/` (shared symlinks)
202−3. **Model-specific layer:** `.claude/skills/` and `.agent/skills/` → `.agents/skills/` (dedicated model symlinks)
203−
204117 **How to access skills:**
205118
206−- **Preferred:** Read directly from `skills/<skill-name>/SKILL.md` (bypasses symlinks — always works)
207−- **Alternative:** Use your agent's path from Step 2 if your IDE resolves symlinks automatically
208−- **If symlinks fail:** All real skill files are in `skills/` directory
119+- **Preferred:** Read from `.{model}/skills/<skill-name>/SKILL.md` (your model's directory)
120+- **If symlinks fail:** Skills are stored in the ai-agents-skills framework installation (referenced via symlinks)
121+- **Real files location:** All source skills are in the framework's `skills/` directory
209122
210−### Skills Storage Architecture
211−
212123 **Why 3 layers?**
213124
214−1. **Layer 1 (skills/):** Single source of truth — edit once, affects all agents
215−2. **Layer 2 (.agents/skills/):** Canonical shared location — 8 universal agents read here natively
216−3. **Layer 3 (.claude/skills/, .agent/skills/):** Dedicated model symlinks for Claude Code and Antigravity
125+1. **Layer 1 (framework skills/):** Source of truth maintained by framework
126+2. **Layer 2 (.agents/skills/):** Canonical shared location in your project
127+3. **Layer 3 (.{model}/skills/):** Model-specific access for your AI assistant
217128
218129 **Benefits:**
219130
220−- **Zero duplication:** Skills stored once, available to all 11 agents
221−- **Always up-to-date:** Changes propagate instantly (symlinks reference same files)
222−- **Token-efficient:** Models read only the skills they need
131+- **Zero duplication:** Skills installed once, available to all 5 AI models
132+- **Always up-to-date:** Changes propagate instantly via symlinks
133+- **Token-efficient:** Your AI reads only the skills it needs
223134
224−**Example flow:**
135+## Supported Stack
225136
226−```
227−User edits: skills/react/SKILL.md
228− ↓
229−Symlink: .agents/skills/react/ → skills/react/
230− ↓
231−Universal agents (Amp, Cline, Codex, Cursor, Gemini, Copilot, Kimi, OpenCode)
232− read: .agents/skills/react/ directly
233− ↓
234−Dedicated agents get additional symlinks:
235− .claude/skills/react/ → .agents/skills/react/ (Claude Code)
236− .agent/skills/react/ → .agents/skills/react/ (Antigravity)
237− ↓
238−OpenClaw reads: skills/react/ directly (project root, no symlink needed)
239− ↓
240−All 11 agents see updated react skill instantly
241−```
137+- **Languages:** TypeScript 5.6.2, JavaScript (ES2020+)
138+- **Frameworks:** React 18.3.1, Webpack (latest)
139+- **State:** Redux 5.0.1, React-Redux 9.2.0, Redux Toolkit 2.5.1, RTK Query
140+- **UI:** MUI 5.15.14, MUI X Charts 7.7.1, MUI X Date Pickers Pro 5.0.20
141+- **Data:** AG Grid (latest stable)
142+- **Forms:** Context-aware (see form-validation skill — checks package.json for installed library)
143+- **Build:** Webpack
144+- **Code Quality:** Context-aware (see code-quality skill — checks package.json for installed tools)
242145
243146 ## Workflows
244147
245−### Create a Skill
148+### Feature Development
246149
247−1. Read `skills/skill-creation/SKILL.md`
248−2. `mkdir skills/{name}` + copy SKILL-TEMPLATE.md
249−3. Write SKILL.md with frontmatter and sections
250−4. Validate: `npx ai-agents-skills validate --skill {name}`
251−5. Install: `npx ai-agents-skills local`
150+1. Gather requirements and clarify acceptance criteria
151+2. Design component architecture with TypeScript interfaces
152+3. Implement React components using MUI
153+4. Configure Redux Toolkit slices / RTK Query endpoints
154+5. Implement forms with validation (see form-validation skill)
155+6. Ensure accessibility (semantic HTML, ARIA, keyboard nav)
156+7. Test with strict TypeScript, document changes, request review
252157
253−### Create an Agent
158+### Code Review
254159
255−1. Read `skills/agent-creation/SKILL.md`
256−2. Gather context (9 questions)
257−3. Create `presets/{project-name}/AGENTS.md`
258−4. Validate all referenced skills exist
160+1. Verify strict TypeScript (no `any`, explicit return types)
161+2. Check MUI usage, theming consistency, accessibility
162+3. Review Redux patterns and RTK Query cache config
163+4. Confirm version compatibility with supported stack
259164
260−### Update Website
261−
262−The website (`website/`) is an Astro SSG site that auto-renders skills from `skills/` via content collections.
263−
264−1. Read `skills/astro/SKILL.md` and `skills/tailwindcss/SKILL.md`
265−2. Pages live in `website/src/pages/` — skills rendered via `[name]/index.astro`
266−3. Layouts: `BaseLayout.astro` (shell), `SkillLayout.astro` (two-column with sidebar)
267−4. Components: `SkillMeta`, `ReferenceSidebar`, `TableOfContents`, `Breadcrumb`
268−5. Styles: Tailwind v4 via `@theme` in `website/src/styles/global.css` (no `tailwind.config.*`)
269−6. Build: `cd website && npm run build` — deploys via GitHub Actions on push to `main`
270−
271−**Key conventions:**
272−- Reference sidebar uses `{slug, title}[]` — titles extracted from H1 of each reference file
273−- Skills H1: topic name only, no "Skill" suffix (e.g., `# React`, not `# React Skill`)
274−- `---` separator required before every `##` section except the first
275−
276−### Install Skills
277−
278−```bash
279−npx ai-agents-skills local # Install to all detected models
280−npx ai-agents-skills local --models claude # Install to specific model
281−npx ai-agents-skills validate --all # Validate all skills
282−```
283−
284165 ## Policies
285166
286−- **Explicit dependencies:** Skills declare all their dependencies in `metadata.skills` — no hidden auto-includes
287−- **Dependency resolution:** Auto-resolve with cycle detection and topological sort
288−- **Two-tier model architecture:**
289− - **Dedicated models** — require their own skills directory:
290− - Claude Code (`.claude/skills/`), Antigravity (`.agent/skills/`), OpenClaw (`skills/`)
291− - **Universal models** — read `.agents/skills/` natively, no extra directory needed:
292− - Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode
293−- **Symlink architecture:** 3-layer structure for zero duplication:
294− - **Layer 1:** `skills/` (source of truth — real files; also OpenClaw's native path)
295− - **Layer 2:** `.agents/skills/` → `skills/` (canonical shared symlinks — universal coverage)
296− - **Layer 3:** `.claude/skills/` and `.agent/skills/` → `.agents/skills/` (dedicated model symlinks)
297− - **Individual skill symlinks:** Each skill gets its own symlink (NOT directory-level)
298− - **Instant propagation:** Changes to source files visible to all agents immediately
299−- **Auto-generated instructions:** Each model gets an instruction file listing all installed skills with their metadata
300−- **Dependency-safe removal:** `remove` command validates dependencies before removing skills
301−- **11 agents supported:** 3 dedicated (Claude Code, Antigravity, OpenClaw) + 8 universal (Amp, Cline, Codex, Cursor, Gemini CLI, GitHub Copilot, Kimi, OpenCode)
167+**Typing:** strict mode, no `any` (use `unknown`/generics), explicit return types, prefer interfaces
302168
303−## Git & Release Workflow
169+**Code quality:** Context-aware linting and formatting (see code-quality skill), format before committing
304170
305−### Branching
171+**Accessibility:** Semantic MUI components, keyboard-accessible elements, proper heading hierarchy, labeled form fields
306172
307−- **`main`** — production, always stable, tagged releases only
308−- **`development`** — integration branch, all feature work merges here first
309−- Feature branches off `development`, never off `main`
173+**Versions:**
310174
311−### Commit Strategy
312−
313−- **Use skill:** `technical-communication` for all commit messages
314−- **Format:** single line, imperative, no co-author
315−- **Examples:**
316− - `fix: show interactive selector when all AGENTS.md skills installed`
317− - `feat: add PostHog analytics for web and CLI`
318− - `chore: update OG image to match logo`
319−- **Group by feature:** separate commits per logical change, never batch unrelated changes
320−
321−### Merge to Main (Squash)
322−
323−Merges from `development` → `main` use **squash merge**. The squash commit message format encodes the release type and triggers the auto-release pipeline:
324−
325−```
326−release(patch|minor|major): {brief summary of what's in the squash}
327−```
328−
329−Examples:
330−- `release(patch): telemetry + PostHog analytics + CI release pipeline`
331−- `release(minor): preset system overhaul + new skills`
332−
333−### Versioning & Release
334−
335−Versions follow **semver**: `MAJOR.MINOR.PATCH`
336−
337−| Change type | Squash merge prefix | Example |
338−|---|---|---|
339−| Bug fix, small improvement | `release(patch): ...` | 1.6.0 → 1.6.1 |
340−| New feature, backwards-compatible | `release(minor): ...` | 1.6.0 → 1.7.0 |
341−| Breaking change | `release(major): ...` | 1.6.0 → 2.0.0 |
342−
343−**Release flow:**
344−1. Work on `development`, commit with single-line messages
345−2. Squash merge to `main` with a `release(patch|minor|major): {summary}` message
346−3. `auto-release.yml` detects the prefix on push to `main`, runs `npm version <type>`, and pushes the version commit + tag — no manual command needed
347−4. `auto-release.yml` bumps the version, builds, publishes to npm, updates the README badge, and syncs back to `development` — all in one pipeline
348−
349−**Tags always go on `main`**, never on `development`.
350−
351−## CodeGraph
352−
353−This project has a CodeGraph MCP server (`codegraph_*` tools) configured. CodeGraph is a tree-sitter-parsed knowledge graph of every symbol, edge, and file. Reads are sub-millisecond and return structural information grep cannot.
354−
355−### When to prefer codegraph over native search
356−
357−Use codegraph for **structural** questions — what calls what, what would break, where is X defined, what is X's signature. Use native grep/read only for **literal text** queries (string contents, comments, log messages) or after you already have a specific file open.
358−
359−| Question | Tool |
360−|---|---|
361−| "Where is X defined?" / "Find symbol named X" | `codegraph_search` |
362−| "What calls function Y?" | `codegraph_callers` |
363−| "What does Y call?" | `codegraph_callees` |
364−| "What would break if I changed Z?" | `codegraph_impact` |
365−| "Show me Y's signature / source / docstring" | `codegraph_node` |
366−| "Give me focused context for a task/area" | `codegraph_context` |
367−| "Survey an unfamiliar module/topic" | `codegraph_explore` |
368−| "What files exist under path/" | `codegraph_files` |
369−| "Is the index healthy?" | `codegraph_status` |
370−
371−### Rules of thumb
372−
373−- **Trust codegraph results.** They come from a full AST parse. Do NOT re-verify them with grep — that's slower, less accurate, and wastes context.
374−- **Don't grep first** when looking up a symbol by name. `codegraph_search` is faster and returns kind + location + signature in one call.
375−- **Don't chain `codegraph_search` + `codegraph_node`** when you just want context — `codegraph_context` is one call.
376−- **`codegraph_explore` is the heavy hitter** for unfamiliar areas — returns full source from all relevant files in one call, but is token-heavy.
377−- **Index lag**: the file watcher debounces ~500ms behind writes; don't re-query immediately after editing a file in the same turn.
378−
379−### If `.codegraph/` doesn't exist
380−
381−The MCP server returns "not initialized." Ask the user: *"I notice this project doesn't have CodeGraph initialized. Want me to run `codegraph init -i` to build the index?"*
382−
383−## References
384−
385−- [AGENTS.md Spec](https://agents.md/)
386−- [Agent Skills](https://agentskills.io/)
175+- Exact: TypeScript 5.6.2, React 18.3.1, RTK 2.5.1, MUI 5.15.14
176+- Ranges: TS >=5.4 <6.0, React >=18.0 <19.0, RTK >=1.8 <3.0, MUI >=5.0 <6.0
387177
