piter-setup

Guide for setting up the PITER framework elements to enable AFK (Away From Keyboard) agent systems.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "piter-setup" with this command: npx skills add melodic-software/claude-code-plugins/melodic-software-claude-code-plugins-piter-setup

PITER Setup

Guide for setting up the PITER framework elements to enable AFK (Away From Keyboard) agent systems.

When to Use

  • Configuring GitHub as prompt input source

  • Setting up webhook or cron triggers

  • Preparing a dedicated agent environment

  • Designing the review process

  • Moving from in-loop to out-of-loop agentic coding

PITER Overview

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

Setup Workflow

  1. Configure Prompt Input (P)

GitHub Issues Setup

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..."

  1. Configure Classification (I)

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

  1. Configure Trigger (T)

Option A: Cron Polling

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"

Option B: Webhook

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:

  • Set up tunnel (ngrok/cloudflare)

  • Configure webhook in GitHub repo settings

  • Select events: Issues, Issue comments

  1. Configure Environment (E)

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

  1. Configure Review (R)

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):

  • Require pull request reviews

  • Require status checks to pass

  • Require linear history

Validation Checklist

Prompt Input (P)

  • GitHub CLI authenticated

  • Can create issues

  • Can fetch issue details

  • Issue format understood

Classification (I)

  • /classify-issue command works

  • Correctly classifies chores

  • Correctly classifies bugs

  • Correctly classifies features

Trigger (T)

  • Trigger method chosen (cron/webhook)

  • Trigger script running

  • Events detected correctly

  • ADW invoked on trigger

Environment (E)

  • Dedicated environment available

  • API keys configured

  • Claude Code accessible

  • Templates tested

  • Permissions configured

Review (R)

  • PR creation works

  • Issue linking works

  • Branch protection configured

  • Review process documented

Quick Test Workflow

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>

Common Issues

Authentication Failures

Refresh GitHub auth

gh auth login

Verify API key

curl -H "x-api-key: $ANTHROPIC_API_KEY"
https://api.anthropic.com/v1/models

Webhook Not Receiving

  • Check tunnel is running

  • Verify webhook URL in GitHub settings

  • Check webhook secret matches

  • Look at GitHub webhook delivery logs

Classification Accuracy

  • Improve prompt with examples

  • Add edge case handling

  • Consider multi-label issues

Related Memory Files

  • @piter-framework.md - Full PITER reference

  • @adw-anatomy.md - ADW structure

  • @outloop-checklist.md - Deployment checklist

Version History

  • v1.0.0 (2025-12-26): Initial release

Last Updated

Date: 2025-12-26 Model: claude-opus-4-5-20251101

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

design-thinking

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

plantuml-syntax

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

system-prompt-engineering

No summary provided by upstream source.

Repository SourceNeeds Review
Coding

resume-optimization

No summary provided by upstream source.

Repository SourceNeeds Review