SUMMARY AI summary by gpt-5-mini
Idea Harness は、非プログラマーが出す「こんなアプリを作りたい」程度の曖昧な入力を、LLM が勝手に推測して不適切な実装を始めないように「要件を明確化」するためのスキル集です。想定ユーザーは技術的に未整理なアイデアを持つ人、あるいは LLM エージェントに正確な要求を渡したい開発者／運用者。 主な機能は、決定木に基づく「7つの澄清門」、4つの精度チェック、状態遷移（gathering → needs-precision → blocked → ready）による厳密な要件確認、そして「一度に最重要の質問だけを投げる」運用ルールです。全門を通過すると要件サマリを出力し、実行用プロンプトはユーザーが明示的に要求したときのみ生成します。Claude、Cursor、OpenAI Codex、Hermes、OpenClaw 等のエージェント向けにスキルとして配布され、ランタイム依存なしの「skill-only」構成です。使用に適した場面（曖昧な一文のアイデア、最小で正しい第一版を目指す等）と不向きな場面（既に明確な PRD、即コード生成が必要等）も明記されています。貢献は実例対話の PR を歓迎。
AI Coding Tools Used
This repository contains config files from these AI coding tools, indicating AI-assisted development.
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
GitHub Topics
Language breakdown (by bytes)
Owner
Sun Yat-sen University，major in software engineering.
Dates
| Created on GitHub | 2026-04-29 |
| Last push | 2026-05-09 |
| First seen here | 2026-05-09 |
| Last fetched | 2026-05-09 18:21 |
Similar repos (same language)
Multi-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.
Cyrene963/hermes-patchesHermes Agent 社区补丁合集 - Community patches for Hermes Agent
tenondecrpc/cc-statuslineClaude Statusline: a lightweight Bash + jq statusline for Claude Code with model, context, rate limit, git/worktree, cost, duration, and install/uninstall support. No heavy runtime required.
JinPLu/agent-roundtableAgent Roundtable — a local, file-based substrate for multi-agent work. Humans, Cursor chat, Codex (codex exec) and Claude Code (claude -p) take turns on one shared THREAD.md under your repo so you can plan, execute, review, and discuss without losing context or locking in to a single CLI.
ryga-test/playwright-ai-workflow-playgroundAI-driven E2E testing with Playwright. An 8-step slash-command pipeline that discovers UI snapshots, generates POM, drafts GWT test specs, runs Playwright tests, and self-heals knowledge — all with human approval gates for quality control.
walidboulanouar/ay-frameworkAgent swarm framework for Claude Code. Plan, build, review, test, ship -- with human-in-the-loop gates.
itchernetski/claude-code-token-watchClaude Code hooks that warn when a session starts burning tokens on repeated Reads, recursive greps, or WebFetch streaks
chaloemphongseatiao/Claude-Code-Projects-Structure