admin/GLM-Tools-Skills-Agents
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Add community skills, agents, system prompts from 22+ sources

Browse Source 
Community Skills (32):
- jat: jat-start, jat-verify, jat-complete
- pi-mono: codex-cli, codex-5.3-prompting, interactive-shell
- picoclaw: github, weather, tmux, summarize, skill-creator
- dyad: 18 skills (swarm-to-plan, multi-pr-review, fix-issue, lint, etc.)
- dexter: dcf valuation skill

Agents (23):
- pi-mono subagents: scout, planner, reviewer, worker
- toad: 19 agent configs (Claude, Codex, Gemini, Copilot, OpenCode, etc.)

System Prompts (91):
- Anthropic: 15 Claude prompts (opus-4.6, code, cowork, etc.)
- OpenAI: 49 GPT prompts (gpt-5 series, o3, o4-mini, tools)
- Google: 13 Gemini prompts (2.5-pro, 3-pro, workspace, cli)
- xAI: 5 Grok prompts
- Other: 9 misc prompts (Notion, Raycast, Warp, Kagi, etc.)

Hooks (9):
- JAT hooks for session management, signal tracking, activity logging

Prompts (6):
- pi-mono templates for PR review, issue analysis, changelog audit

Sources analyzed: jat, ralph-desktop, toad, pi-mono, cmux, pi-interactive-shell,
craft-agents-oss, dexter, picoclaw, dyad, system_prompts_leaks, Prometheus,
zed, clawdbot, OS-Copilot, and more
This commit is contained in:
uroma
2026-02-13 10:58:17 +00:00
Unverified
parent 5889d3428b
commit b60638f0a3
186 changed files with 38926 additions and 325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

460
README.md
View File

@@ -1,6 +1,6 @@
# GLM Tools, Skills & Agents
**Comprehensive collection of AI platform skills, expert agents, and development tooling** from MiniMax, Super Z (GLM), z.ai, and the open-source community.
**Comprehensive collection of AI platform skills, expert agents, system prompts, and development tooling** from MiniMax, Super Z (GLM), z.ai, and the open-source community.
---
@@ -10,12 +10,14 @@
|----------|-------|
| **Original Skills** | 4 |
| **External Skills** | 44 |
| **Agents** | 8 |
| **Community Skills** | 32 |
| **Agents** | 31 |
| **System Prompts** | 91 |
| **Commands** | 23 |
| **Hooks** | 23 |
| **MCP Integrations** | 9 |
| **Codebases** | 1 |
| **Registries** | 1 |
| **Total Files** | 300+ |
| **Total Files** | 500+ |
---
@@ -28,37 +30,34 @@ GLM-Tools-Skills-Agents/
│ ├── glm-skills/ # Super Z/GLM multimodal skills
│ ├── zai-tooling-reference/ # Next.js 16 patterns
│ ├── ai-platforms-consolidated/ # Cross-platform reference
│ └── external/ # 44 external skills
│ ├── ui-ux-pro-max/ # UI/UX design intelligence
│ ├── brainstorming/ # Design collaboration
│ ├── test-driven-development/ # TDD methodology
│ ├── systematic-debugging/ # Debugging workflow
│ ├── writing-plans/ # Implementation planning
│ └── ... (39 more)
│ ├── external/ # 44 external skills (superpowers, etc.)
│ └── community/ # 32 community skills
│ ├── jat/ # JAT task management (3 skills)
│ ├── pi-mono/ # Pi coding agent (3 skills)
│ ├── picoclaw/ # Go-based AI assistant (5 skills)
│ ├── dyad/ # Local AI app builder (18 skills)
│ └── dexter/ # Financial research CLI (1 skill)
├── agents/ # Autonomous agents
│ └── claude-codex-settings/
│ ├── github-dev-commit-creator.md
│ ├── github-dev-pr-creator.md
│ ├── github-dev-pr-reviewer.md
│ └── ... (5 more)
├── commands/ # Slash commands
│ └── claude-codex-settings/
│ ├── github-dev-commit-staged.md
│ ├── github-dev-create-pr.md
│ └── ... (21 more)
├── hooks/ # Hook configurations
│ ├── claude-codex-settings/ # 8 agents
│ └── community/ # 19 community agents
│ ├── pi-mono/ # 4 subagents (scout, planner, reviewer, worker)
│ └── toad/ # 15 agent configs
├── system-prompts/ # Leaked system prompts
│ ├── anthropic/ # 15 Claude prompts
│ ├── openai/ # 49 GPT prompts
│ ├── google/ # 13 Gemini prompts
│ ├── xai/ # 5 Grok prompts
│ └── other/ # 9 misc prompts
├── commands/ # Slash commands (23)
├── hooks/ # Hook scripts (23)
│ ├── claude-codex-settings/ # 14 scripts
│ └── community/jat/ # 9 scripts
├── prompts/ # Prompt templates
│ └── community/pi-mono/ # 6 templates
├── mcp-configs/ # MCP server configs
├── codebases/ # Reference codebases
│ └── z-ai-tooling/ # Full Next.js 16 project
├── codebases/z-ai-tooling/ # Full Next.js 16 project
├── original-docs/ # Source documentation
│ ├── minimax_experts_data.md
│ ├── MINIMAX_EXPERT_CATALOG.md
│ └── GLM5_AGENTS_AND_SKILLS.md
├── registries/ # Skill registries
│ └── awesome-openclaw-skills-registry.md
├── src/ # Next.js 16 app source
├── prisma/ # Prisma schema
└── examples/ # WebSocket examples
└── registries/ # Skill registries
```
---
@@ -67,329 +66,150 @@ GLM-Tools-Skills-Agents/
### Original Skills (4)
#### 1. MiniMax Experts (`skills/minimax-experts/`)
40 AI experts from the MiniMax platform (agent.minimax.io):
| Category | Count | Top Experts |
|----------|-------|-------------|
| Content Creation | 12 | Landing Page Builder, Visual Lab, Video Story Generator |
| Finance | 7 | Hedge Fund Expert Team, Crypto Trading Agent |
| Development | 5 | Mini Coder Max, Peak Coder, Prompt Development Studio |
| Career | 5 | Job Hunter Agent, CV Optimization Expert |
| Business | 3 | PRD Assistant, SaaS Niche Finder, CEO Assistant |
| Marketing | 2 | Social Media Marketing Expert, Creative Director For Ads |
**Auto-Triggers:** `agent design`, `hedge fund`, `landing page`, `PRD`, `CV optimization`, `trading`
#### 2. GLM Skills (`skills/glm-skills/`)
Super Z (z.ai) multimodal capabilities using `z-ai-web-dev-sdk`:
| Skill | Command | Description |
|-------|---------|-------------|
| ASR | `ASR` | Speech-to-text transcription |
| TTS | `TTS` | Text-to-speech synthesis |
| LLM | `LLM` | Large language model chat |
| VLM | `VLM` | Vision language model |
| Image Generation | `image-generation` | AI image creation |
| Video Generation | `video-generation` | AI video creation |
| PDF | `pdf` | PDF processing toolkit |
| DOCX | `docx` | Word document processing |
| XLSX | `xlsx` | Spreadsheet processing |
| PPTX | `pptx` | Presentation processing |
| Web Search | `web-search` | Real-time web search |
| Web Reader | `web-reader` | Web content extraction |
| Podcast | `podcast-generate` | Podcast episode generation |
**Auto-Triggers:** `ASR`, `TTS`, `image/video generation`, `PDF/DOCX`, `multimodal`
#### 3. Z.AI Tooling Reference (`skills/zai-tooling-reference/`)
Production-ready Next.js 16 development patterns:
| Category | Technology |
|----------|------------|
| Framework | Next.js 16.1.1 + React 19 |
| Language | TypeScript 5 |
| Styling | Tailwind CSS 4 |
| UI Components | shadcn/ui (50+ components) |
| Database | Prisma + SQLite |
| State | Zustand |
| Data Fetching | TanStack Query |
| AI SDK | z-ai-web-dev-sdk |
| Auth | NextAuth |
| Package Manager | Bun |
**Auto-Triggers:** `Next.js`, `shadcn/ui`, `Prisma`, `WebSocket`, `React 19`
#### 4. AI Platforms Consolidated (`skills/ai-platforms-consolidated/`)
Cross-platform comparison and quick reference.
**Auto-Triggers:** `platform comparisons`, `SDK patterns`, `cross-platform`
---
| Skill | Source | Description |
|-------|--------|-------------|
| minimax-experts | MiniMax | 40 AI experts (Content, Finance, Dev, Career, Business, Marketing) |
| glm-skills | Super Z/GLM | Multimodal capabilities (ASR, TTS, VLM, Image/Video, PDF/DOCX/XLSX) |
| zai-tooling-reference | z.ai | Next.js 16, React 19, shadcn/ui, Prisma patterns |
| ai-platforms-consolidated | Various | Cross-platform comparison reference |
### External Skills (44)
#### From obra/superpowers (14 Skills)
From obra/superpowers, ui-ux-pro-max, claude-codex-settings:
- Development workflow: brainstorming, writing-plans, test-driven-development, systematic-debugging
- Git workflow: commit-workflow, pr-workflow, using-git-worktrees
- Quality assurance: verification-before-completion, requesting-code-review
- Tool integrations: azure-usage, gcloud-usage, supabase-usage, mongodb-usage, tavily-usage
- Plugin development: agent-development, command-development, hook-development, mcp-integration
| Skill | Purpose | Category |
|-------|---------|----------|
| `brainstorming` | Design collaboration before creative work | Collaboration |
| `writing-plans` | Planning multi-step tasks | Planning |
| `executing-plans` | Execute plans with review checkpoints | Execution |
| `subagent-driven-development` | Independent task execution | Workflow |
| `test-driven-development` | TDD methodology - RED-GREEN-REFACTOR | Testing |
| `systematic-debugging` | Root cause investigation before fixes | Debugging |
| `requesting-code-review` | Verify work meets requirements | Quality |
| `receiving-code-review` | Implement review feedback | Quality |
| `finishing-a-development-branch` | Merge/PR/keep/discard decisions | Git |
| `dispatching-parallel-agents` | Run 2+ independent tasks | Workflow |
| `verification-before-completion` | Verify before claiming done | Quality |
| `using-git-worktrees` | Isolated feature branches | Git |
| `writing-skills` | Create and edit skills | Meta |
| `using-superpowers` | Getting started guide | Meta |
### Community Skills (32)
#### From nextlevelbuilder/ui-ux-pro-max-skill (1 Skill)
| Skill | Purpose | Features |
|-------|---------|----------|
| `ui-ux-pro-max` | UI/UX design intelligence | 67 styles, 96 color palettes, 57 font pairings, 99 UX guidelines, 25 chart types, 13 tech stacks |
**Supported Platforms:** Claude Code, Cursor, Windsurf, Codex CLI, OpenCode, GitHub Copilot, and 10+ more
#### From fcakyon/claude-codex-settings (29 Skills)
| Skill | Plugin | Purpose |
|-------|--------|---------|
| `azure-tools-azure-usage` | azure-tools | Azure MCP (40+ services) |
| `gcloud-tools-gcloud-usage` | gcloud-tools | Google Cloud observability |
| `github-dev-commit-workflow` | github-dev | Git commit workflow |
| `github-dev-pr-workflow` | github-dev | Pull request workflow |
| `linear-tools-linear-usage` | linear-tools | Issue tracking integration |
| `mongodb-tools-mongodb-usage` | mongodb-tools | Database exploration (read-only) |
| `paper-search-tools-paper-search-usage` | paper-search | Academic paper search |
| `playwright-tools-playwright-testing` | playwright-tools | Browser automation & testing |
| `slack-tools-slack-usage` | slack-tools | Slack integration |
| `supabase-tools-supabase-usage` | supabase-tools | Supabase database patterns |
| `tavily-tools-tavily-usage` | tavily-tools | Web search & extraction |
| `plugin-dev-agent-development` | plugin-dev | Build autonomous agents |
| `plugin-dev-command-development` | plugin-dev | Create custom commands |
| `plugin-dev-hook-development` | plugin-dev | Create hooks |
| `plugin-dev-mcp-integration` | plugin-dev | Configure MCP servers |
| `plugin-dev-plugin-settings` | plugin-dev | Per-project configuration |
| `plugin-dev-plugin-structure` | plugin-dev | Plugin layout |
| `plugin-dev-skill-development` | plugin-dev | Create reusable skills |
| `*-setup` | Various | Setup guides for each tool |
| Source | Skills | Focus |
|--------|--------|-------|
| **jat** | 3 | Task management (jat-start, jat-verify, jat-complete) |
| **pi-mono** | 3 | Coding agents (codex-cli, codex-5.3-prompting, interactive-shell) |
| **picoclaw** | 5 | Go assistant (github, weather, tmux, summarize, skill-creator) |
| **dyad** | 18 | Local app builder (swarm-to-plan, multi-pr-review, fix-issue, lint, etc.) |
| **dexter** | 1 | Financial research (dcf valuation) |
---
## Agents Catalog (8)
## Agents Catalog (31)
### From claude-codex-settings
### From claude-codex-settings (8)
- commit-creator, pr-creator, pr-reviewer (GitHub workflow)
- code-simplifier (pattern consistency)
- responsive-tester (viewport testing)
- agent-creator, plugin-validator, skill-reviewer (plugin dev)
| Agent | Plugin | Purpose | Triggers |
|-------|--------|---------|----------|
| `commit-creator` | github-dev | Intelligent Git commit workflow | staged files, commit message |
| `pr-creator` | github-dev | Pull request creation | create PR, make pull request |
| `pr-reviewer` | github-dev | Code review (bugs, security, performance) | review PR, code review |
| `code-simplifier` | general-dev | Pattern consistency enforcer | Auto-triggers after TodoWrite |
| `responsive-tester` | playwright-tools | Viewport testing (375px to 1536px) | test responsiveness |
| `agent-creator` | plugin-dev | AI-assisted agent generation | create agent |
| `plugin-validator` | plugin-dev | Plugin structure validation | validate plugin |
| `skill-reviewer` | plugin-dev | Improve skill quality | review skill |
### From Community (23)
- **pi-mono subagents** (4): scout, planner, reviewer, worker
- **toad agent configs** (19): Claude, Codex, Gemini, Copilot, OpenCode, Goose, Kimi, etc.
---
## Commands Catalog (23)
## System Prompts Catalog (91)
### Git/GitHub Commands
### Anthropic (15)
- claude-opus-4.6.md, claude-code.md, claude-cowork.md
- claude-in-chrome.md, claude-for-excel.md
- Historical: claude-3.7-sonnet, claude-4.5-sonnet, claude-opus-4.5
| Command | Description |
|---------|-------------|
| `/github-dev-commit-staged` | Commit staged changes with semantic messages |
| `/github-dev-create-pr` | Create pull request |
| `/github-dev-review-pr` | Review pull request |
| `/github-dev-clean-gone-branches` | Clean deleted remote branches |
| `/github-dev-update-pr-summary` | Update PR summary |
### OpenAI (49)
- GPT-5 series: gpt-5-thinking, gpt-5.1 (default/professional/nerdy/friendly/etc.), gpt-5.2-thinking
- Reasoning models: o3, o4-mini, o4-mini-high
- Tools: tool-python, tool-web-search, tool-deep-research, tool-canvas, tool-memory
### Claude Tools Commands
### Google (13)
- gemini-2.5-pro, gemini-2.5-flash, gemini-3-pro, gemini-3-flash
- gemini-workspace, gemini-cli, gemini-diffusion
| Command | Description |
|---------|-------------|
| `/claude-tools-load-claude-md` | Load CLAUDE.md context |
| `/claude-tools-load-frontend-skill` | Load frontend skill |
| `/claude-tools-sync-allowlist` | Sync permissions allowlist |
| `/claude-tools-sync-claude-md` | Sync CLAUDE.md to project |
### xAI (5)
- grok-4, grok-4.1-beta, grok-3, grok-personas
### Plugin Development Commands
### Other (9)
- Notion AI, Raycast AI, Warp 2.0 Agent, Kagi Assistant, Sesame AI Maya
| Command | Description |
|---------|-------------|
| `/plugin-dev-create-plugin` | 8-phase guided plugin workflow |
| `/plugin-dev-load-skills` | Load plugin development skills |
---
### Setup Commands
## Hooks Catalog (23)
| Command | Description |
|---------|-------------|
| `/azure-tools-setup` | Configure Azure MCP |
| `/gcloud-tools-setup` | Configure Google Cloud MCP |
| `/linear-tools-setup` | Configure Linear MCP |
| `/mongodb-tools-setup` | Configure MongoDB MCP |
| `/paper-search-tools-setup` | Configure paper search |
| `/playwright-tools-setup` | Configure Playwright |
| `/slack-tools-setup` | Configure Slack MCP |
| `/supabase-tools-setup` | Configure Supabase MCP |
| `/tavily-tools-setup` | Configure Tavily MCP |
| `/statusline-tools-setup` | Configure statusline |
| `/ccproxy-tools-setup` | Configure CC proxy |
### From claude-codex-settings (14)
- Code formatting: format_python_docstrings.py, prettier_formatting.py, markdown_formatting.py
- Git workflow: git_commit_confirm.py, gh_pr_create_confirm.py
- Web tools: websearch_to_tavily_search.py, webfetch_to_tavily_extract.py
- Notifications: notify.sh
### From JAT (9)
- Session management: session-start-agent-identity.sh, pre-compact-save-agent.sh
- Signal tracking: post-bash-jat-signal.sh, user-prompt-signal.sh
- Activity logging: log-tool-activity.sh
---
## Prompts/Templates (6)
From pi-mono:
- **pr.md** - Review PRs with structured analysis
- **is.md** - Analyze GitHub issues
- **cl.md** - Audit changelog entries
- **codex-review-plan.md** - Launch Codex to review plans
- **codex-implement-plan.md** - Codex implementation workflow
- **codex-review-impl.md** - Codex code review workflow
---
## MCP Integrations (9)
| MCP Server | Package | Features |
|------------|---------|----------|
| Azure | `@azure/mcp@latest` | 40+ Azure services |
| Google Cloud | `gcloud-observability-mcp` | Logs, metrics, traces |
| Server | Package | Features |
|--------|---------|----------|
| Azure | @azure/mcp | 40+ Azure services |
| Google Cloud | gcloud-observability-mcp | Logs, metrics, traces |
| GitHub | Built-in | PRs, issues, workflows |
| Linear | `linear-mcp` | Issue tracking |
| MongoDB | `mongodb-mcp-server` | Database exploration (read-only) |
| Playwright | `@playwright/mcp@latest` | Browser automation |
| Slack | `slack-mcp-server` | Message search, channel history |
| Linear | linear-mcp | Issue tracking |
| MongoDB | mongodb-mcp-server | Database exploration |
| Playwright | @playwright/mcp | Browser automation |
| Slack | slack-mcp-server | Message search |
| Supabase | HTTP endpoint | Database, Auth, RLS |
| Tavily | `tavily-mcp@latest` | Web search & extraction |
| Tavily | tavily-mcp | Web search & extraction |
---
## Codebase Reference
## Sources
### Z.AI Tooling (`codebases/z-ai-tooling/`)
Full Next.js 16 project with:
- **50+ shadcn/ui components** in `src/components/ui/`
- **Prisma schema** with User and Post models
- **WebSocket example** (Socket.io)
- **z-ai-web-dev-sdk integration**
- **Complete project structure**
```bash
cd codebases/z-ai-tooling
bun install
bun run dev
bun run db:push # Push schema changes
bun run db:generate # Generate Prisma client
```
| Source | Type | Content |
|--------|------|---------|
| MiniMax Experts | Platform | 40 AI experts |
| Super Z/GLM | Platform | Multimodal skills |
| obra/superpowers | GitHub | 14 workflow skills |
| ui-ux-pro-max-skill | GitHub | 1 design skill |
| claude-codex-settings | GitHub | 29 skills, 8 agents, 23 commands |
| jat | GitHub | 3 skills, 9 hooks |
| pi-mono | GitHub | 3 skills, 4 agents, 6 prompts |
| picoclaw | GitHub | 5 skills |
| dyad | GitHub | 18 skills |
| dexter | GitHub | 1 skill |
| toad | GitHub | 19 agent configs |
| system_prompts_leaks | GitHub | 91 system prompts |
| awesome-openclaw-skills | GitHub | 3,002 skills registry |
| OS-Copilot | GitHub | Self-improvement framework |
| Prometheus | GitHub | Multi-agent bug fixing |
| zed | GitHub | Editor AI with MCP |
| skills.sh | Web | 40+ skills catalog |
| buildwithclaude.com | Web | 117 subagents |
---
## Installation
### For Claude Code
```bash
# Copy all skills
cp -r skills/* ~/.claude/skills/
# Copy specific skill categories
cp -r skills/minimax-experts ~/.claude/skills/
cp -r skills/glm-skills ~/.claude/skills/
cp -r skills/external/* ~/.claude/skills/
```
### From skills.sh
```bash
npx skills add vercel-labs/agent-skills
npx skills add obra/superpowers
npx skills add nextlevelbuilder/ui-ux-pro-max-skill
```
---
## SDK Quick Reference
### z-ai-web-dev-sdk
```javascript
import ZAI from 'z-ai-web-dev-sdk';
const zai = await ZAI.create();
// LLM Chat
const completion = await zai.chat.completions.create({
messages: [
{ role: 'system', content: 'You are helpful.' },
{ role: 'user', content: 'Hello\!' }
]
});
// Image Generation
const image = await zai.images.generations.create({
prompt: 'A sunset over mountains',
size: '1024x1024'
});
// Web Search
const results = await zai.functions.invoke("web_search", {
query: "latest AI news",
num: 10
});
```
---
## Sources
| Source | Platform | URL |
|--------|----------|-----|
| MiniMax Experts | MiniMax Agent | https://agent.minimax.io/experts |
| GLM Skills | Super Z (z.ai) | Internal platform |
| Z.AI Tooling | z.ai Development | Internal platform |
| Superpowers | obra/superpowers | https://github.com/obra/superpowers |
| UI/UX Pro Max | nextlevelbuilder | https://github.com/nextlevelbuilder/ui-ux-pro-max-skill |
| Claude Codex Settings | fcakyon | https://github.com/fcakyon/claude-codex-settings |
| OpenClaw Skills | VoltAgent | https://github.com/VoltAgent/awesome-openclaw-skills |
| Skills.sh | Vercel Labs | https://skills.sh/ |
| Build with Claude | Community | https://www.buildwithclaude.com |
---
## Technology Stack (Root Project)
| Category | Technology |
|----------|------------|
| Framework | Next.js 16 + React 19 |
| Language | TypeScript 5 |
| Styling | Tailwind CSS 4 |
| UI | shadcn/ui (50+ components) |
| State | Zustand |
| Data | TanStack Query |
| Database | Prisma + SQLite |
| Auth | NextAuth.js |
| Forms | React Hook Form + Zod |
---
## Quick Start
```bash
# Install dependencies
bun install
# Start development server
bun run dev
# Database operations
bun run db:push # Push schema changes
bun run db:generate # Generate Prisma client
# Build for production
bun run build
npx skills add <skill-name>
```
---
@@ -400,20 +220,10 @@ bun run build
|------|---------|
| 2026-02-13 | Initial repository with GLM skills |
| 2026-02-13 | Added obra/superpowers (14 skills) |
| 2026-02-13 | Added ui-ux-pro-max-skill (1 skill) |
| 2026-02-13 | Added claude-codex-settings (29 skills, 8 agents, 23 commands) |
| 2026-02-13 | Added awesome-openclaw-skills registry (3,002 skills referenced) |
---
## Quick Links
- **MiniMax Platform**: https://agent.minimax.io
- **Skills.sh**: https://skills.sh/
- **shadcn/ui**: https://ui.shadcn.com
- **Next.js**: https://nextjs.org
- **Prisma**: https://prisma.io
- **Superpowers**: https://github.com/obra/superpowers
| 2026-02-13 | Added ui-ux-pro-max-skill, claude-codex-settings |
| 2026-02-13 | Added community repos: jat, pi-mono, picoclaw, dyad, dexter |
| 2026-02-13 | Added 91 leaked system prompts (Anthropic, OpenAI, Google, xAI) |
| 2026-02-13 | Added toad agent configs, JAT hooks, pi-mono prompts |
---