Set up PITER framework elements for AFK agent systems. Use when configuring prompt input sources, triggers, environments, and review processes for autonomous agent workflows.
Sets up PITER framework elements for autonomous agent workflows. Use when configuring GitHub issue prompts, classification commands, webhook/cron triggers, dedicated environments, and PR-based review processes for AFK agent systems.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install google-ecosystem@melodic-softwareThis skill is limited to using the following tools:
Guide for setting up the PITER framework elements to enable AFK (Away From Keyboard) agent systems.
| Element | Question | Common Implementation |
|---|---|---|
| P | Where do tasks come from? | GitHub Issues |
| I | What type of work is this? | LLM Classification |
| T | When does work start? | Webhooks / Cron |
| E | Where do agents run? | Dedicated VM/Sandbox |
| R | How is work validated? | Pull Requests |
# Verify GitHub CLI is authenticated
gh auth status
# Test issue creation
gh issue create --title "Test Issue" --body "Testing ADW prompt input"
# Test issue fetching
gh issue view 1 --json title,body,labels
Issue structure becomes the prompt:
Title: Add user authentication
Body: We need OAuth with Google provider...
Labels: feature, priority-high
→ Becomes: "/feature Add user authentication..."
Create /classify-issue command:
# Issue Classification
Analyze the issue and respond with exactly one of:
- /chore - for maintenance, updates, cleanup
- /bug - for defects, errors, unexpected behavior
- /feature - for new functionality
## Issue
$ARGUMENTS
Test classification:
claude -p "/classify-issue 'Fix login button not working'"
# Expected: /bug
claude -p "/classify-issue 'Update dependencies'"
# Expected: /chore
# trigger_cron.py (simplified)
import time
POLL_INTERVAL = 20 # seconds
while True:
issues = get_unprocessed_issues()
for issue in issues:
run_adw(issue.number)
time.sleep(POLL_INTERVAL)
Unprocessed = no comments OR latest comment is "adw"
# trigger_webhook.py (simplified)
from flask import Flask, request
app = Flask(__name__)
@app.route("/gh-webhook", methods=["POST"])
def handle_webhook():
event = request.json
if is_new_issue(event):
run_adw(event["issue"]["number"])
return "OK"
Webhook setup:
Environment checklist:
# Verify Claude Code
claude --version
# Verify API key
echo $ANTHROPIC_API_KEY | head -c 10
# Verify GitHub access
gh auth status
# Verify repository
git remote -v
# Test templates
claude -p "/chore test" --dry-run
Create .env file (never commit):
ANTHROPIC_API_KEY=sk-ant-...
GITHUB_TOKEN=ghp_...
CLAUDE_CODE_PATH=claude
PR-based review:
# Test PR creation
gh pr create \
--title "Test PR" \
--body "Testing ADW review process" \
--base main \
--head feature-test
Branch protection (recommended):
/classify-issue command works# 1. Create test issue
gh issue create --title "Test: Update README" --body "Add installation section"
# 2. Manually run ADW
python adws/adw_plan_build.py <issue_number>
# 3. Verify PR created
gh pr list --state open
# 4. Review and close
gh pr view <pr_number>
# Refresh GitHub auth
gh auth login
# Verify API key
curl -H "x-api-key: $ANTHROPIC_API_KEY" \
https://api.anthropic.com/v1/models
Date: 2025-12-26 Model: claude-opus-4-5-20251101
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.