setup-workflow
Initial setup workflow for claude-pilot plugin - directory creation, statusline configuration, documentation sync, GitHub star request
Best use case
setup-workflow is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Initial setup workflow for claude-pilot plugin - directory creation, statusline configuration, documentation sync, GitHub star request
Teams using setup-workflow should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/setup-workflow/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How setup-workflow Compares
| Feature / Agent | setup-workflow | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Initial setup workflow for claude-pilot plugin - directory creation, statusline configuration, documentation sync, GitHub star request
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# SKILL: Setup (Plugin Initialization Workflow)
> **Purpose**: Initialize claude-pilot plugin for new projects with proper directory structure and configuration
> **Target**: User running `/pilot:setup` for first time in a project
---
## Quick Start
### When to Use This Skill
- First-time plugin setup in a new project
- Reset plugin directory structure
- Configure statusline for project
### Quick Reference
```bash
# Full workflow
/pilot:setup
# Steps: Directories → Statusline → Documentation → GitHub Star
```
## Execution Steps
Execute ALL steps in sequence. Do NOT pause between steps unless explicitly marked as user interaction.
### Step 1: Create Directories
**Purpose**: Initialize .pilot directory structure for plan management
```bash
mkdir -p .pilot/plan/{draft,pending,in_progress,done}
mkdir -p .pilot/state
echo "✓ .pilot directories created"
```
**Verification**:
```bash
test -d .pilot/plan/draft && echo "draft: ✓" || echo "draft: ✗"
test -d .pilot/plan/pending && echo "pending: ✓" || echo "pending: ✗"
test -d .pilot/plan/in_progress && echo "in_progress: ✓" || echo "in_progress: ✗"
test -d .pilot/plan/done && echo "done: ✓" || echo "done: ✗"
test -d .pilot/state && echo "state: ✓" || echo "state: ✗"
```
### Step 2: Configure Statusline
**Purpose**: Copy statusline script from plugin and configure settings.json
```bash
# Detect plugin installation path
PLUGIN_PATH=$(jq -r '.plugins["claude-pilot@claude-pilot"][0].installPath // empty' ~/.claude/plugins/installed_plugins.json 2>/dev/null || true)
SOURCE=""
# Always prefer plugin version to ensure latest
# Note: In distributed plugin, scripts are at $PLUGIN_PATH/scripts/ (no .claude prefix)
[[ -n "$PLUGIN_PATH" && -f "$PLUGIN_PATH/scripts/statusline.sh" ]] && SOURCE="$PLUGIN_PATH/scripts/statusline.sh"
if [[ -n "$SOURCE" ]]; then
# Copy statusline script
mkdir -p .claude/scripts
cp "$SOURCE" .claude/scripts/statusline.sh
chmod +x .claude/scripts/statusline.sh
# Configure settings.json
SETTINGS=".claude/settings.json"
STATUSLINE='{"type":"command","command":"\"$CLAUDE_PROJECT_DIR\"/.claude/scripts/statusline.sh"}'
if [[ -f "$SETTINGS" ]]; then
# Update existing settings
jq --argjson sl "$STATUSLINE" '. + {statusLine: $sl}' "$SETTINGS" > /tmp/settings.json && mv /tmp/settings.json "$SETTINGS"
else
# Create new settings
echo "{\"statusLine\": $STATUSLINE}" > "$SETTINGS"
fi
# Show version
PLUGIN_VERSION=$(jq -r '.version' "$PLUGIN_PATH/.claude-plugin/plugin.json" 2>/dev/null || echo 'unknown')
echo "✓ Statusline configured (from plugin v$PLUGIN_VERSION)"
else
echo "⚠ Statusline script not found in plugin, skipping"
fi
```
**Verification**:
```bash
test -f .claude/scripts/statusline.sh && echo "statusline.sh: ✓" || echo "statusline.sh: ✗"
test -f .claude/settings.json && echo "settings.json: ✓" || echo "settings.json: ✗"
```
### Step 3: MCP Servers (Informational)
**Purpose**: Inform user about recommended MCP servers
**Display to user**:
```
📦 Recommended MCP Servers:
- context7: Latest library documentation (@upstash/context7-mcp)
- sequential-thinking: Step-by-step reasoning (@modelcontextprotocol/server-sequential-thinking)
Configuration: Add to ~/.claude.json under projects.<project-path>.mcpServers
```
**No action required** - informational only.
### Step 4: Initial Documentation (Optional)
**Purpose**: Ask user if they want to generate initial documentation
**User Interaction** (use AskUserQuestion):
- Question: "Generate initial documentation (3-tier docs sync)?"
- Options: "Yes, generate docs" / "No, skip"
**If yes**:
```bash
echo "📚 Running documentation sync..."
echo "Invoke the three-tier-docs skill to generate initial documentation."
```
**If no**:
```bash
echo "⏭️ Skipping documentation sync"
```
### Step 5: GitHub Star Request (Optional)
**Purpose**: Ask user if they want to star the repository
**User Interaction** (use AskUserQuestion):
- Question: "Star the claude-pilot repository on GitHub?"
- Options: "Yes, star the repo" / "No thanks"
**If yes**:
```bash
# Check if gh CLI is available
if command -v gh &> /dev/null; then
if gh api -X PUT /user/starred/changoo89/claude-pilot 2>&1; then
echo "⭐ Thank you for starring claude-pilot!"
else
echo "⚠️ Could not star via gh CLI"
echo " Manual link: https://github.com/changoo89/claude-pilot"
fi
else
echo "⚠️ gh CLI not found"
echo " Star manually: https://github.com/changoo89/claude-pilot"
fi
```
**If no**:
```bash
echo "👋 Thanks for using claude-pilot!"
```
### Step 6: Complete
**Purpose**: Show completion message and next steps
```bash
echo ""
echo "✓ claude-pilot setup complete"
echo " Run /00_plan to start planning"
```
## What This Skill Covers
### In Scope
- Directory creation (.pilot structure)
- Statusline configuration (copy from plugin)
- MCP server recommendations
- Optional documentation generation
- Optional GitHub star request
### Out of Scope
- MCP server installation → User responsibility
- Plugin installation → Already completed before setup
- Documentation generation logic → @.claude/skills/three-tier-docs/SKILL.md
## Further Reading
**Internal**: @.claude/skills/setup/REFERENCE.md - Advanced setup patterns | @.claude/skills/three-tier-docs/SKILL.md - Documentation synchronization | CLAUDE.md - Plugin overview
**External**: [Claude Code MCP Configuration](https://docs.anthropic.com/claude-code/mcp) | [GitHub CLI Authentication](https://cli.github.com/manual/gh_auth_login)Related Skills
julien-workflow-advice-codex
Get OpenAI Codex CLI's opinion on code, bugs, or implementation. Use when you want a second AI perspective during coding sessions.
fal-workflow
Generate workflow JSON files for chaining AI models
create-workflow
Create Jazz workflow automation files (WORKFLOW.md). Use this for scheduling Jazz agents to run recurring tasks. For OS-level scripts/commands, use create-system-routine.
airflow-workflows
Apache Airflow DAG design, operators, and scheduling best practices.
ai-annotation-workflow
Эксперт по data annotation. Используй для ML labeling, annotation workflows и quality control.
agent-setup
Configure AI coding agents like Cursor, GitHub Copilot, or Claude Code with project-specific patterns, coding guidelines, and MCP servers for consistent AI-assisted development.
agent-canvas-setup
Dependency checker and installer for agent-canvas, agent-eyes, and canvas-edit skills. Use BEFORE running any canvas skill for the first time, or when canvas skills fail with import/browser errors. Triggers on "setup agent canvas", "install canvas dependencies", "canvas not working", "playwright not found", or any setup/installation request for canvas skills.
adaptive-workflows
Self-learning workflow system that tracks what works best for your use cases. Records experiment results, suggests optimizations, creates custom templates, and builds a personal knowledge base. Use to learn from experience and optimize your LLM workflows over time.
academic-course-setup-automator
When the user needs to set up multiple academic courses in a learning management system (Canvas/LMS) from structured data sources. This skill automates the entire workflow extracting course schedules from emails/attachments, matching instructors from CSV files, creating courses, enrolling teachers, publishing announcements with class details, uploading syllabi, enabling resource sharing for instructors teaching multiple courses, and publishing all courses. Triggers include course schedule setup, Canvas/LMS administration, academic term preparation, instructor assignment, syllabus distribution, and multi-course management.
workflows-expert
Activate when requests involve workflow execution, CI/CD pipelines, git automation, or multi-step task orchestration. This skill provides workflows-mcp MCP server integration with tag-based workflow discovery, DAG-based execution, and variable syntax expertise. Trigger on phrases like "run workflow", "execute workflow", "orchestrate tasks", "automate CI/CD", or "workflow information".
workflow-orchestration
Design and implement DAG-based workflows with parallel execution, retries, and error handling. Use when building complex multi-step agent workflows.
workflow-integration-git
Git commit workflow with conventional commits, artifact cleanup, and optional push/PR creation