Reorganize: Move all skills to skills/ folder

- Created skills/ directory
- Moved 272 skills to skills/ subfolder
- Kept agents/ at root level
- Kept installation scripts and docs at root level

Repository structure:
- skills/           - All 272 skills from skills.sh
- agents/           - Agent definitions
- *.sh, *.ps1       - Installation scripts
- README.md, etc.   - Documentation

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
admin
2026-01-23 18:05:17 +00:00
Unverified
parent 2b4e974878
commit b723e2bd7d
4083 changed files with 1056 additions and 1098063 deletions

View File

@@ -0,0 +1,155 @@
---
name: setup
description: Configure claude-delegator with Codex MCP server
allowed-tools: Bash, Read, Write, Edit, AskUserQuestion
timeout: 60000
---
# Setup
Configure Codex (GPT) as specialized expert subagents via native MCP. Five domain experts that can advise OR implement.
## Step 1: Check Codex CLI
```bash
which codex 2>/dev/null && codex --version 2>&1 | head -1 || echo "CODEX_MISSING"
```
### If Missing
Tell user:
```
Codex CLI not found.
Install with: npm install -g @openai/codex
Then authenticate: codex login
After installation, re-run /claude-delegator:setup
```
**STOP here if Codex is not installed.**
## Step 2: Read Current Settings
```bash
cat ~/.claude/settings.json 2>/dev/null || echo "{}"
```
## Step 3: Configure MCP Server
Merge into `~/.claude/settings.json`:
```json
{
"mcpServers": {
"codex": {
"type": "stdio",
"command": "codex",
"args": ["-m", "gpt-5.2-codex", "mcp-server"]
}
}
}
```
Note: Use `gpt-5.2-codex` explicitly for the latest model.
**CRITICAL**:
- Merge with existing settings, don't overwrite
- Preserve any existing `mcpServers` entries
## Step 4: Install Orchestration Rules
```bash
mkdir -p ~/.claude/rules/delegator && cp ${CLAUDE_PLUGIN_ROOT}/rules/*.md ~/.claude/rules/delegator/
```
## Step 5: Verify Installation
Run these checks and report results:
```bash
# Check 1: Codex CLI version
codex --version 2>&1 | head -1
# Check 2: MCP server configured
cat ~/.claude/settings.json | jq -r '.mcpServers.codex.args | join(" ")' 2>/dev/null
# Check 3: Rules installed (count files)
ls ~/.claude/rules/delegator/*.md 2>/dev/null | wc -l
# Check 4: Auth status (check if logged in)
codex login status 2>&1 | head -1 || echo "Run 'codex login' to authenticate"
```
## Step 6: Report Status
Display actual values from the checks above:
```
claude-delegator Status
───────────────────────────────────────────────────
Codex CLI: ✓ [version from check 1]
Model: ✓ gpt-5.2-codex (or ✗ if not configured)
MCP Config: ✓ ~/.claude/settings.json (or ✗ if missing)
Rules: ✓ [N] files in ~/.claude/rules/delegator/
Auth: [status from check 4]
───────────────────────────────────────────────────
```
If any check fails, report the specific issue and how to fix it.
## Step 7: Final Instructions
```
Setup complete!
Next steps:
1. Restart Claude Code to load MCP server
2. Authenticate: Run `codex login` in terminal (if not already done)
Five GPT experts available:
┌──────────────────┬─────────────────────────────────────────────┐
│ Architect │ "How should I structure this service?" │
│ │ "What are the tradeoffs of Redis vs X?" │
│ │ → System design, architecture decisions │
├──────────────────┼─────────────────────────────────────────────┤
│ Plan Reviewer │ "Review this migration plan" │
│ │ "Is this implementation plan complete?" │
│ │ → Plan validation before execution │
├──────────────────┼─────────────────────────────────────────────┤
│ Scope Analyst │ "Clarify the scope of this feature" │
│ │ "What am I missing in these requirements?" │
│ │ → Pre-planning, catches ambiguities │
├──────────────────┼─────────────────────────────────────────────┤
│ Code Reviewer │ "Review this PR" │
│ │ "Find issues in this implementation" │
│ │ → Code quality, bugs, maintainability │
├──────────────────┼─────────────────────────────────────────────┤
│ Security Analyst │ "Is this authentication flow secure?" │
│ │ "Harden this endpoint" │
│ │ → Vulnerabilities, threat modeling │
└──────────────────┴─────────────────────────────────────────────┘
Every expert can advise (read-only) OR implement (write).
Expert is auto-detected based on your request.
Explicit: "Ask GPT to review..." or "Have GPT fix..."
```
## Step 8: Ask About Starring
Use AskUserQuestion to ask the user if they'd like to ⭐ star the claude-delegator repository on GitHub to support the project.
Options: "Yes, star the repo" / "No thanks"
**If yes**: Check if `gh` CLI is available and run:
```bash
gh api -X PUT /user/starred/jarrodwatts/claude-delegator
```
If `gh` is not available or the command fails, provide the manual link:
```
https://github.com/jarrodwatts/claude-delegator
```
**If no**: Thank them and complete setup without starring.

View File

@@ -0,0 +1,38 @@
---
name: uninstall
description: Uninstall claude-delegator (remove MCP config and rules)
allowed-tools: Bash, Read, Write, Edit, AskUserQuestion
timeout: 30000
---
# Uninstall
Remove claude-delegator from Claude Code.
## Confirm Removal
**Question**: "Remove Codex MCP configuration and plugin rules?"
**Options**:
- "Yes, uninstall"
- "No, cancel"
If cancelled, stop here.
## Remove MCP Configuration
Read `~/.claude/settings.json`, delete `mcpServers.codex` entry, write back.
## Remove Installed Rules
```bash
rm -rf ~/.claude/rules/delegator/
```
## Confirm Completion
```
✓ Removed 'codex' from MCP servers
✓ Removed rules from ~/.claude/rules/delegator/
To reinstall: /claude-delegator:setup
```