paca-setup
The paca-setup skill guides users through configuring the Paca MCP server for Claude Code or Claude Desktop environments. Use it when initially setting up Paca, modifying server configurations, troubleshooting connection issues, or installing Paca skills globally. The skill walks users interactively through prerequisite verification, config file selection, credential setup, testing, and optional global skill installation across different platforms and Claude environments.
git clone --depth 1 https://github.com/Paca-AI/paca /tmp/paca-setup && cp -r /tmp/paca-setup/skills/paca-setup ~/.claude/skills/paca-setupSKILL.md
You are helping the user configure the Paca MCP server for their Claude Code environment.
Walk the user through the setup interactively, step by step. Do not dump all instructions at once — confirm each step before proceeding.
---
## Setup flow
### Step 1 — Check prerequisites
Ask the user to confirm:
- [ ] Paca is running (local: `http://localhost:8080`, or their hosted URL)
- [ ] Node.js 18+ is installed (`node --version`)
- [ ] They have a Paca API key (Settings → API Keys inside Paca UI)
If any prerequisite is missing, guide the user to resolve it before continuing.
### Step 2 — Identify the Claude Code config file
Ask which environment they want to configure:
**A. Claude Code (CLI) — project-level** (recommended for team projects)
→ Create or edit `.claude/mcp.json` in the project root.
**B. Claude Code (CLI) — global**
→ Run: `claude mcp add paca --env PACA_API_KEY=<key> --env PACA_API_URL=<url> -- npx -y @paca-ai/paca-mcp`
**C. Claude Desktop**
→ Edit the config file for your OS:
- **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
- **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
- **Linux**: `~/.config/Claude/claude_desktop_config.json`
### Step 3 — Generate the config snippet
Based on their choice, generate the exact config block. Example for option A (`.claude/mcp.json`):
```json
{
"mcpServers": {
"paca": {
"command": "npx",
"args": ["-y", "@paca-ai/paca-mcp"],
"env": {
"PACA_API_KEY": "<their-api-key>",
"PACA_API_URL": "<their-paca-url>"
}
}
}
}
```
Substitute the actual values the user provides. Remind them:
- **Never commit API keys to git.** Add `.claude/mcp.json` to `.gitignore` if it contains a key, or use environment variable substitution.
### Step 4 — Apply the config
For option A, write the `.claude/mcp.json` file directly (ask permission first).
For options B and C, show the command/snippet and ask the user to apply it.
### Step 5 — Verify
Once configured, ask the user to restart Claude Code / Claude Desktop, then test with:
> "List my Paca projects"
If Paca tools appear and return results, setup is complete. If not, check:
1. JSON syntax is valid
2. API key is correct (no extra spaces)
3. Paca API URL is reachable (`curl <PACA_API_URL>/api/v1/health`)
4. Node.js / npx is in PATH
### Step 6 — Install the Paca skill globally (optional)
Offer to run the global skill installer so `/paca` and related skills are always available:
```bash
curl -fsSL https://raw.githubusercontent.com/Paca-AI/paca/master/scripts/install-claude-skill.sh | bash
```
Review the script before running it — `curl | bash` executes remote code directly.
---
## Environment variables reference
| Variable | Required | Description |
|---|---|---|
| `PACA_API_KEY` | Yes | API key from Paca → Settings → API Keys |
| `PACA_API_URL` | No (default: `http://localhost:8080`) | Your Paca instance URL |Break a large Paca task or epic into smaller, actionable sub-tasks with dependency ordering. Use when decomposing work that is too large to estimate or execute in a single session, when creating an implementation plan, or when a task needs to be split into vertical slices before sprint planning.
Clarify a vague or incomplete Paca task or specification by identifying ambiguities, asking targeted questions, and rewriting the description with explicit acceptance criteria. Use when a task is unclear, missing edge cases, lacks a testable done condition, or when someone asks to improve or flesh out a spec.
Execute a Paca task end-to-end — reading context and acceptance criteria, doing the work (code, writing, research, review), updating task status, and commenting results. Use when asked to start, implement, complete, or work on a specific Paca task. Reads project docs first to understand the codebase and tech stack before acting.
Write or update documentation for a feature, task, or topic in Paca Docs. Use when asked to document a completed feature, write a guide or runbook, update existing docs, create a spec or architecture document, or produce BDD scenarios. Documentation is saved in Paca — never created as local files.
Turn a product requirement or feature description into a structured epic in Paca, with child user stories and a spec document. Use when asked to plan a new feature, break down a high-level requirement into stories, create an epic, or go from "we need X" to a fully structured backlog ready for sprint planning.
Estimate story points for Paca tasks using the Fibonacci scale, calibrated against recently completed reference tasks and project tech stack. Use when tasks are missing estimates, before sprint planning, when the team needs sizing for prioritization, or when asked to size a backlog.
Set or adjust priorities across the Paca backlog, aligned to roadmap goals and business value. Use when the backlog needs sorting, before sprint planning, when tasks need explicit Critical/High/Medium/Low priority labels, or when asked to rank work by importance or urgency.