superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Lightweight 180-minute operating loop, Cofa-Grill alignment, 3-model subagents (Sol/Terra/Luna), and Level-2 dynamic BC/QM/QR verification suite for Codex.
Plugin cofa-loop-graph in itssosunny/cofa-loop-graph. Commands read from the repo's manifest — 6 days ago.
This plugin runs code on your machine — it starts local MCP servers. The exact commands are listed below; read them before installing.
cofa-loop-graphComplete 180-minute hackathon operating loop and Level-2 verification graph for Codex. Covers 2-step Cofa-Grill alignment, Tracer-Bullet vertical slicing with executor (5.6 Terra), System-1 fast verification with luna_checker (6.0 Luna), and final submission fidelity check with architect (6.1 Sol).
cofa-startZero-argument T+01m exam kickoff skill. Immediately runs --inspect-csv, analyzes README.md to generate .cofa/repo_map.md, drafts 3-4 Korean DM questions for 업무 담당자, initializes .cofa/trace.json, and presents the 1-round Frontier grill.
evaluateFast System-1 calibrated evaluation of observable evidence (state) using 6.0 Luna (gpt-6-luna). Evaluates boolean predicates (noul), categorical classifications (choice), and ordered rubric scores (score) with mathematical confidence.
grill-meFast Frontier-style interview to stress-test decisions and lock scope. In time-boxed hackathon settings, defaults to a single fast Frontier round.
qa-briefingGenerate comprehensive Korean 4-part post-submission written Q&A final briefing (UI state architecture, data/CSV error handling, review agent records & rationales, and architecture decisions) for exam defense.
sharpenSharpen a task before starting. Focus on outcome, anti-over-engineering, and right-sizing specifications.
to-questionnaireTurn missing context or ambiguous requirements into progressive, structured questions for a stakeholder or Scenario Agent (업무 담당자).
verification-before-completionIron law of verification before claiming completion or committing. Requires fresh command execution output before declaring status.
evaluateruns: python3 -c import os, sys, glob; c = [os.path.join(os.getcwd(), '.cofa', 'luna_mcp.py'), os.path.expanduser('~/.codex/plugins/cache/cofa-local/cofa/local/.cofa/luna_mcp.py'), os.path.expanduser('~/.co
playwrightruns: npx -y @playwright/mcp@latest --headless
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Use Alibaba Open Code Review from local Codex.
2 skills
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.
12 skills · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.