Menu
Run the repositorys test, lint, and typecheck commands, then summarize failures and next actions for coding agents.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Generate an initial operating contract for autonomous Copilot work. Use when starting a new task stream, kickoff session, issue burndown, or multi-step implementation where scope, stop conditions, constraints, acceptance criteria, and execution policy must be explicit before coding.
Bootstrap or maintain a repo-specific Copilot, Codex, and Claude agent stack by inventorying docs, commands, workflows, and existing AI assets before scaffolding managed guidance.
Analyze connected repositories and deliver end-to-end web deployment strategy with GitHub-native defaults. Use when Codex must (1) research repository structure, workflows, Pages setup, and .github configuration, (2) build a scored decision matrix for deployment options, (3) pause for explicit approval before mutating changes, and (4) implement and verify deployment with local checks plus GitHub CI smoke.
Audit curriculum coverage against instructor runbook structure and repository naming rules for Basics and Advanced modules. Use when Codex needs to detect missing or misnamed Day/Hour lecture files, missing daily assignment artifacts, missing quiz artifacts, autograder-readiness gaps, or when scaffolding standardized placeholders for missing course files.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.
| name | repo-quality-gates |
| description | Run the repositorys test, lint, and typecheck commands, then summarize failures and next actions for coding agents. |
Use this skill when you need to validate a change or interpret failing automation for this repository.
python -m pip install nbconvert├── criteria.json # Test specs: command, stdin, expected_stdout, points