anbeime/skill / skills/awesome-jev/awesome-jev
awesome-jev
VerifiedFind and compare JEV-related GitHub projects for a user's task, language or agent workflow using the curated Awesome JEV catalogue and scenario references. Use for project discovery and implementation research, not for executing JEV API calls.
scripts/curate-star50-expansion-2026-09-22.mjs
View on GitHubimport { readFile, writeFile } from 'node:fs/promises';
const catalogueFile = new URL('../data/projects.json', import.meta.url);
const catalogue = JSON.parse(await readFile(catalogueFile, 'utf8'));
const g = (repo, sha, path) => `https://github.com/${repo}/blob/${sha}/${path}`;
const p = ({ repo, sha, path, ...project }) => {
const evidenceUrl = g(repo, sha, path);
return {
...project,
repoUrl: `https://github.com/${repo}`,
evidenceUrl,
source: { type: 'github', label: 'GitHub source', url: evidenceUrl },
verification: 'source-reviewed',
runtimeVerified: false,
};
};
const additions = [
p({ id: 'sub2api-jev-moderation', name: 'Sub2API · JEV Moderation', owner: 'Wei-Shaw', category: 'safety-review', repo: 'Wei-Shaw/sub2api', sha: '1c0a69c0ceddb2fd21581c17ab09f6c500b89ba1', path: 'backend/internal/pkg/typesafe/client.go', starsAtCapture: 42323, language: 'Go', license: 'LGPL-3.0', summary: { en: 'A subscription-to-API gateway with a native TypeSafe client for content moderation.', zh: '在订阅转 API 网关中内置 TypeSafe 客户端,用于内容审核。', ja: 'サブスクリプションを API 化するゲートウェイに、コンテンツ審査用 TypeSafe クライアントを内蔵。' }, decision: { en: 'Batches Noul questions, validates every probability, and returns moderation scores to local risk-control policy.', zh: '批量提交 Noul 问题,校验每个概率,再把审核分数交给本地风控策略。', ja: 'Noul 質問をまとめて送信し、各確率を検証してからローカルのリスク制御へ審査スコアを返します。' } }),
p({ id: 'openviking-jev-rerank', name: 'OpenViking · JEV Rerank', owner: 'volcengine', category: 'search-data', repo: 'volcengine/OpenViking', sha: 'b8bed5a1ad3a1c524b5e1fd0fa591df51ca9b7cc', path: 'openviking/models/rerank/jev_rerank.py', starsAtCapture: 38371, language: 'Python', license: 'AGPL-3.0', summary: { en: 'OpenViking can use JEV as a calibrated reranker for agent memory and context retrieval.', zh: 'OpenViking 可用 JEV 对 Agent 记忆与上下文检索结果做校准重排。', ja: 'OpenViking は JEV を使い、Agent の記憶・コンテキスト検索結果を較正して再順位付けできます。' }, decision: { en: 'Asks one Noul relevance question per document and falls back to vector scores when evaluation fails.', zh: '为每篇文档提出一个 Noul 相关性问题,判断失败时回退到向量分数。', ja: '文書ごとに Noul の関連性質問を行い、評価に失敗した場合はベクトルスコアへフォールバックします。' } }),
p({ id: 'hindsight-typesafe-rerank', name: 'Hindsight · TypeSafe Rerank', owner: 'vectorize-io', category: 'search-data', repo: 'vectorize-io/hindsight', sha: '680406b3dd9cca2108c7f0e204820a09b4e30906', path: 'hindsight-api-slim/hindsight_api/engine/cross_encoder.py', starsAtCapture: 24801, language: 'Python', license: 'MIT', summary: { en: 'An agent-memory system with a TypeSafe reranker that can prune irrelevant recall candidates.', zh: '在 Agent 记忆系统中加入 TypeSafe 重排器,可剔除无关召回候选。', ja: 'Agent メモリに TypeSafe リランカーを追加し、無関係な検索候補を除外できます。' }, decision: { en: 'Uses calibrated relevance decisions to score and optionally prune retrieved memories under bounded retry policy.', zh: '用校准后的相关性判断评分并按需剪枝召回记忆,同时受有限重试策略约束。', ja: '較正済みの関連性判断で記憶を採点・必要に応じて除外し、再試行回数も制限します。' } }),
p({ id: 'bifrost-typesafe-provider', name: 'Bifrost · TypeSafe Provider', owner: 'maximhq', category: 'sdk-integrations', repo: 'maximhq/bifrost', sha: '40c3f7ee3a1a4277c5b269b850ca7725d419907f', path: 'core/providers/typesafe/typesafe.go', starsAtCapture: 8227, language: 'Go', license: 'Apache-2.0', summary: { en: 'Bifrost exposes TypeSafe as a native provider through its shared decision operation.', zh: 'Bifrost 通过统一 Decision 操作把 TypeSafe 接成原生 Provider。', ja: 'Bifrost は共通の Decision 操作を通じて TypeSafe をネイティブ Provider として公開します。' }, decision: { en: 'Maps Bifrost decision requests to System One while preserving aliases, usage, errors, and typed answers.', zh: '把 Bifrost 决策请求映射到 System One,并保留别名、用量、错误与类型化答案。', ja: 'Bifrost の判断リクエストを System One に変換し、別名・使用量・エラー・型付き回答を保持します。' } }),
p({ id: 'gpt-load-jev-provider', name: 'GPT-Load · JEV Provider', owner: 'tbphp', category: 'sdk-integrations', repo: 'tbphp/gpt-load', sha: '93502ced3a650018a35ed76c54573e90742b8ccc', path: 'internal/channel/modules/jev.go', starsAtCapture: 6942, language: 'Go', license: 'MIT', summary: { en: 'A self-hosted AI gateway with a first-class JEV channel and native Decisions routes.', zh: '自托管 AI 网关内置一等 JEV 渠道与原生 Decisions 路由。', ja: 'セルフホスト AI ゲートウェイに、JEV 専用チャネルとネイティブ Decisions ルートを搭載。' }, decision: { en: 'Registers the fixed TypeSafe endpoint and routes decision creation, model listing, and probes through the native protocol.', zh: '注册固定 TypeSafe 端点,并通过原生协议处理决策创建、模型列表与探测。', ja: '固定 TypeSafe エンドポイントを登録し、判断作成・モデル一覧・プローブをネイティブプロトコルで処理します。' } }),
p({ id: 'greptimedb-jev-sql', name: 'GreptimeDB · JEV SQL', owner: 'GreptimeTeam', category: 'search-data', repo: 'GreptimeTeam/greptimedb', sha: 'b5199bc59a199875187d808158357a33b09e5f60', path: 'src/common/function/src/scalars/jev.rs', starsAtCapture: 6697, language: 'Rust', license: 'Apache-2.0', summary: { en: 'GreptimeDB adds an experimental SQL predicate backed by JEV judgments.', zh: 'GreptimeDB 增加由 JEV 判断驱动的实验性 SQL 谓词。', ja: 'GreptimeDB に JEV 判断を利用する実験的 SQL 述語を追加。' }, decision: { en: 'Evaluates each non-null row as a Noul question and compares its probability with a caller-supplied threshold.', zh: '把每个非空行作为 Noul 问题评估,并与调用方给定阈值比较。', ja: '各非 null 行を Noul 質問として評価し、呼び出し側指定の閾値と確率を比較します。' } }),
p({ id: 'open-connector-typesafe', name: 'Open Connector · TypeSafe', owner: 'oomol-lab', category: 'sdk-integrations', repo: 'oomol-lab/open-connector', sha: '4e6d8533ae436cba4781b6fb69d1bf31e5fb5ffe', path: 'src/providers/typesafe_ai/runtime.ts', starsAtCapture: 5858, language: 'TypeScript', license: 'Apache-2.0', summary: { en: 'Open Connector exposes TypeSafe evaluation through its provider runtime.', zh: 'Open Connector 通过 Provider Runtime 暴露 TypeSafe 评估能力。', ja: 'Open Connector は Provider Runtime 経由で TypeSafe 評価を公開します。' }, decision: { en: 'Validates Noul, Choice, and Score questions and responses before returning them to connector workflows.', zh: '在返回 Connector 工作流前,校验 Noul、Choice、Score 问题及其响应。', ja: 'Noul・Choice・Score の質問と応答を検証してから Connector ワークフローへ返します。' } }),
p({ id: 'kiln-jev-adapter', name: 'Kiln · JEV Adapter', owner: 'Kiln-AI', category: 'sdk-integrations', repo: 'Kiln-AI/Kiln', sha: '5992e2e51ec6782fce33f277145954ba3ae8467e', path: 'libs/core/kiln_ai/adapters/model_adapters/jev_adapter.py', starsAtCapture: 5078, language: 'Python', license: 'NOASSERTION', summary: { en: 'Kiln maps compatible JSON schemas to JEV questions for structured single-turn tasks.', zh: 'Kiln 把兼容的 JSON Schema 映射为 JEV 问题,用于结构化单轮任务。', ja: 'Kiln は互換 JSON Schema を JEV 質問へ変換し、構造化された単発タスクを実行します。' }, decision: { en: 'Converts enums, booleans, bounded integers, and probabilities into typed questions, then reconstructs schema-valid output.', zh: '把枚举、布尔值、有限整数与概率转成类型化问题,再重建符合 Schema 的输出。', ja: '列挙・真偽・範囲付き整数・確率を型付き質問へ変換し、Schema 適合の出力を復元します。' } }),
p({ id: 'http4k-typesafe-client', name: 'http4k · TypeSafe Client', owner: 'http4k', category: 'sdk-integrations', repo: 'http4k/http4k', sha: '528ef94c9533b42be9010396bd1828ed1c84c9d2', path: 'connect/ai/typesafe/client/src/main/kotlin/org/http4k/connect/typesafe/action/SystemOne.kt', starsAtCapture: 2789, language: 'Kotlin', license: 'NOASSERTION', summary: { en: 'A typed Kotlin client and fake implementation for the TypeSafe System One API.', zh: '面向 TypeSafe System One API 的 Kotlin 类型化客户端与 Fake 实现。', ja: 'TypeSafe System One API 向けの型付き Kotlin クライアントと Fake 実装。' }, decision: { en: 'Builds model, state, and typed question maps and posts them to the native System One endpoint.', zh: '构建模型、状态和类型化问题映射,并提交到原生 System One 端点。', ja: 'モデル・状態・型付き質問のマップを作成し、ネイティブ System One エンドポイントへ送信します。' } }),
p({ id: 'agent-router-typesafe', name: 'Agent Router · TypeSafe', owner: 'theagentrouter', category: 'routing-optimization', repo: 'theagentrouter/agent-router', sha: '7d7c07ffdb14241362def2f7d3f76cbd06d518cc', path: 'internal/translator/typesafe_systemone.go', starsAtCapture: 2127, language: 'Go', license: 'Apache-2.0', summary: { en: 'Agent Router provides a native TypeSafe System One translator in its Envoy-based gateway.', zh: 'Agent Router 在 Envoy 网关中提供原生 TypeSafe System One 转换器。', ja: 'Agent Router は Envoy ベースのゲートウェイに TypeSafe System One トランスレータを備えます。' }, decision: { en: 'Passes typed requests through with optional model overrides while retaining usage, errors, and resolved model identity.', zh: '在可选模型覆盖下透传类型化请求,并保留用量、错误与解析后的模型身份。', ja: '任意のモデル上書きを適用しつつ型付きリクエストを透過し、使用量・エラー・解決済みモデルを保持します。' } }),
p({ id: 'llmgateway-system-one', name: 'LLMGateway · System One', owner: 'theopenco', category: 'routing-optimization', repo: 'theopenco/llmgateway', sha: '24de43b5f307ecbdee9aad386b68aee76de4ae8c', path: 'apps/gateway/src/systemone/systemone.ts', starsAtCapture: 1651, language: 'TypeScript', license: 'NOASSERTION', summary: { en: 'LLMGateway implements a native System One route with typed schemas and provider mappings.', zh: 'LLMGateway 实现带类型化 Schema 与 Provider 映射的原生 System One 路由。', ja: 'LLMGateway は型付き Schema と Provider マッピングを備えたネイティブ System One ルートを実装。' }, decision: { en: 'Validates Noul, Choice, and Score requests, resolves aliases to priced models, and routes them through decision-capable providers.', zh: '校验 Noul、Choice、Score 请求,将别名解析到已定价模型,再路由到支持决策的 Provider。', ja: 'Noul・Choice・Score を検証し、別名を価格設定済みモデルへ解決して、判断対応 Provider にルーティングします。' } }),
p({ id: 'jev-chat-jarvis', name: 'JEV Chat Jarvis', owner: 'jev-chat', category: 'interfaces', repo: 'jev-chat/jev-chat-jarvis', sha: 'd8720521fa13aa5172a891cba95c5dd8aeb44a11', path: 'app/src/main/java/com/jev/probe/jev/JevClient.kt', starsAtCapture: 1645, language: 'Kotlin', license: 'MIT', summary: { en: 'An Android conversation copilot that reads visible chat context and proposes replies without auto-sending.', zh: '读取可见聊天上下文、给出候选回复但不自动发送的 Android 对话副驾。', ja: '表示中の会話を読み、候補返信を提案するが自動送信しない Android 会話コパイロット。' }, decision: { en: 'Uses JEV to judge conversation state and bounded reply choices while the user retains the send action.', zh: '用 JEV 判断会话状态与有限回复选项,最终发送仍由用户控制。', ja: 'JEV で会話状態と限定された返信候補を判断し、送信操作はユーザーに残します。' } }),
p({ id: 'rnskill-jev-office-gate', name: 'RNSkill · JEV Office Gate', owner: 'Pluviobyte', category: 'agent-workflows', repo: 'Pluviobyte/rnskill', sha: '83d1783b892bbaa29a137895ff8338264b6872fa', path: 'skills/jev-office-gate/scripts/jev_office_gate.py', starsAtCapture: 1591, language: 'Python', license: 'NOASSERTION', summary: { en: 'An agent-skill collection containing a JEV gate for bounded office-document checks.', zh: 'Agent Skill 合集中包含一个用于有限办公文档检查的 JEV Gate。', ja: 'Agent Skill 集に、限定されたオフィス文書チェック用 JEV ゲートを収録。' }, decision: { en: 'Turns configured document-review conditions into typed judgments before the workflow proceeds.', zh: '把配置好的文档审查条件转成类型化判断,再决定工作流是否继续。', ja: '設定済みの文書レビュー条件を型付き判断へ変換し、ワークフロー継続可否を決めます。' } }),
p({ id: 'distill-jev-runtime', name: 'Distill · JEV Runtime', owner: 'samuelfaj', category: 'agent-workflows', repo: 'samuelfaj/distill', sha: 'd5f031153cb817f023138a9a0b3fce5516f727c4', path: 'crates/codegen/distill-shell/src/jev.rs', starsAtCapture: 683, language: 'Rust', license: 'Apache-2.0', summary: { en: 'A coding-agent runtime with JEV lanes for routing, compaction, memory, and tool-result handling.', zh: '编码 Agent Runtime 使用 JEV 分支处理路由、压缩、记忆与工具结果。', ja: 'コーディング Agent Runtime が JEV レーンでルーティング・圧縮・記憶・ツール結果を処理。' }, decision: { en: 'Chooses among bounded runtime policies before local code performs context and tool operations.', zh: '在本地代码执行上下文与工具操作前,从有限 Runtime 策略中做选择。', ja: 'ローカルコードが文脈・ツール操作を行う前に、限定された Runtime 方針から選択します。' } }),
p({ id: 'siftrank-jev', name: 'SiftRank · JEV', owner: 'noperator', category: 'search-data', repo: 'noperator/siftrank', sha: '03e7afe3289a204ea3dcc51613cea91877a651de', path: 'pkg/siftrank/jev_provider.go', starsAtCapture: 202, language: 'Go', license: 'MIT', summary: { en: 'A command-line ranking tool that uses JEV to find relevant items in large collections.', zh: '使用 JEV 在大型集合中寻找相关条目的命令行排序工具。', ja: 'JEV を使って大規模コレクションから関連項目を探す CLI ランキングツール。' }, decision: { en: 'Scores candidates in batches and applies convergence rules before returning the highest-value subset.', zh: '批量评分候选,并在返回最高价值子集前应用收敛规则。', ja: '候補をバッチ採点し、収束ルールを適用してから価値の高い部分集合を返します。' } }),
p({ id: 'docjev', name: 'DocJEV', owner: 'jerryjliu', category: 'search-data', repo: 'jerryjliu/docjev', sha: '7e6b48d3f7eec8db7b582e7276f2778c0d12ca3d', path: 'src/jev_docs/engines/jev.py', starsAtCapture: 201, language: 'Python', license: 'Apache-2.0', summary: { en: 'A document classifier and splitter with a dedicated JEV engine.', zh: '带专用 JEV Engine 的文档分类与切分工具。', ja: '専用 JEV エンジンを備えた文書分類・分割ツール。' }, decision: { en: 'Classifies documents and split boundaries from bounded schemas, with cache and alternate-engine support.', zh: '根据有限 Schema 判断文档类别与切分边界,并支持缓存及备用引擎。', ja: '限定 Schema から文書カテゴリと分割境界を判断し、キャッシュと代替エンジンにも対応します。' } }),
p({ id: 'laya-node-runtime', name: 'Laya Node Runtime', owner: 'receptron', category: 'open-models', repo: 'receptron/laya', sha: '6478649e723122ca24bbf5fb69ed1010023c9750', path: 'src/laya.ts', starsAtCapture: 195, language: 'TypeScript', license: 'MIT', summary: { en: 'A Node.js and TypeScript runtime for the open Laya JEV-compatible decision model.', zh: '面向开放 Laya JEV 兼容决策模型的 Node.js / TypeScript Runtime。', ja: 'オープンな Laya JEV 互換判断モデル向け Node.js / TypeScript Runtime。' }, decision: { en: 'Runs the ONNX model locally and returns typed decision probabilities without a hosted JEV call.', zh: '在本地运行 ONNX 模型并返回类型化决策概率,无需调用托管 JEV。', ja: 'ONNX モデルをローカル実行し、ホスト型 JEV を呼ばずに型付き判断確率を返します。' } }),
p({ id: 'arc-cua-typesafe', name: 'Arc CUA · TypeSafe Policy', owner: 'shhivv', category: 'browser-computer-use', repo: 'shhivv/arc-cua', sha: '6d47ce6c906d7d8586d3553e277c1c3611c4f6af', path: 'src/arc_cua/policies/typesafe.py', starsAtCapture: 127, language: 'Python', license: 'MIT', summary: { en: 'A fast computer-use action layer with a TypeSafe policy implementation.', zh: '带 TypeSafe Policy 实现的高速 Computer Use 动作层。', ja: 'TypeSafe Policy 実装を備えた高速 Computer Use アクション層。' }, decision: { en: 'Selects the next allowed UI action from observed state while the local harness owns execution.', zh: '根据观察状态选择下一步允许的 UI 动作,执行仍由本地 Harness 负责。', ja: '観測状態から次の許可済み UI 操作を選び、実行はローカル Harness が担います。' } }),
p({ id: 'llm2jev', name: 'LLM2Jev', owner: 'Yinsongxu', category: 'open-models', repo: 'Yinsongxu/LLM2Jev', sha: '6fbbf74fc604f92fc9b0b67f0989157bb2908229', path: 'src/llm2jev/inference/binary.py', starsAtCapture: 125, language: 'Python', license: 'Apache-2.0', summary: { en: 'An adapter that turns local language models into JEV-compatible structured decision engines.', zh: '把本地语言模型转成 JEV 兼容结构化决策引擎的适配器。', ja: 'ローカル言語モデルを JEV 互換の構造化判断エンジンへ変換するアダプタ。' }, decision: { en: 'Uses prefill-only binary inference to produce Choice, Score, and Noul probabilities.', zh: '通过仅预填充的二元推理生成 Choice、Score 与 Noul 概率。', ja: 'prefill のみの二値推論で Choice・Score・Noul の確率を生成します。' } }),
p({ id: 'jev-dsh-decision', name: 'JEV DSH Decision', owner: 'Devin-AXIS', category: 'agent-workflows', repo: 'Devin-AXIS/jev-dsh-decision', sha: 'adc88caa9bf174d367e79a5f254c7936bcef088e', path: 'service/jev.mjs', starsAtCapture: 78, language: 'JavaScript', license: 'NOASSERTION', summary: { en: 'A structured JEV decision plugin for DeepSeek Harness and compatible coding-agent hosts.', zh: '面向 DeepSeek Harness 及兼容编码 Agent Host 的结构化 JEV 决策插件。', ja: 'DeepSeek Harness と互換コーディング Agent ホスト向けの構造化 JEV 判断プラグイン。' }, decision: { en: 'Packages bounded questions as a service and returns typed results to the host harness.', zh: '把有限问题封装为服务,并向 Host Harness 返回类型化结果。', ja: '限定質問をサービス化し、ホスト Harness へ型付き結果を返します。' } }),
p({ id: 'siliconlab-openjev', name: 'OpenJev', owner: 'SiliconLabAI', category: 'open-models', repo: 'SiliconLabAI/OpenJev', sha: 'a08e969c37b2e4a37f95b3426f983bd94303590c', path: 'README.md', starsAtCapture: 67, language: 'TypeScript', license: 'MIT', summary: { en: 'An open-source JEV-compatible implementation for typed decision requests.', zh: '面向类型化决策请求的开源 JEV 兼容实现。', ja: '型付き判断リクエスト向けのオープンソース JEV 互換実装。' }, decision: { en: 'Accepts bounded question schemas and returns structured answers through a compatible interface.', zh: '接受有限问题 Schema,并通过兼容接口返回结构化答案。', ja: '限定質問 Schema を受け取り、互換インターフェースで構造化回答を返します。' } }),
p({ id: 'abdelstark-awesome-typesafe-jev', name: 'Awesome TypeSafe JEV', owner: 'AbdelStark', category: 'developer-tools', repo: 'AbdelStark/awesome-typesafe-jev', sha: '9384099af36cd439b7f0bd4311560ac02eeabe7c', path: 'README.md', starsAtCapture: 431, language: 'HTML', license: 'MIT', summary: { en: 'A source-backed field guide to TypeSafe JEV projects, SDKs, demos, and evaluations.', zh: '带源码依据的 TypeSafe JEV 项目、SDK、演示与评测指南。', ja: 'TypeSafe JEV のプロジェクト・SDK・デモ・評価を根拠付きでまとめたガイド。' }, decision: { en: 'Organizes ecosystem resources by how they implement or apply typed, confidence-aware decisions.', zh: '按类型化、置信度感知决策的实现与应用方式组织生态资源。', ja: '型付き・信頼度付き判断の実装方法と用途別にエコシステム資料を整理します。' } }),
p({ id: 'heyjunpenn-awesome-jev', name: 'Awesome JEV (HeyJunPenn)', owner: 'heyjunpenn', category: 'developer-tools', repo: 'heyjunpenn/awesome-jev', sha: 'eabb8446bdadd6744adce2e30871ef0691cf34e5', path: 'README.md', starsAtCapture: 148, language: 'Astro', license: 'MIT', summary: { en: 'A multilingual, community-maintained catalogue of open-source JEV projects.', zh: '社区维护的多语言 JEV 开源项目目录。', ja: 'コミュニティ運営の多言語 JEV オープンソース・カタログ。' }, decision: { en: 'Indexes implementations and integrations while retaining repository-level provenance for discovery.', zh: '索引实现与集成,并保留仓库级来源信息用于发现。', ja: '実装・連携を索引化し、発見用にリポジトリ単位の出典を保持します。' } }),
];
const byRepo = new Map(catalogue.projects.map((project) => [project.repoUrl.toLowerCase(), project]));
for (const project of additions) byRepo.set(project.repoUrl.toLowerCase(), project);
catalogue.projects = [...byRepo.values()].sort(
(a, b) => b.starsAtCapture - a.starsAtCapture || a.name.localeCompare(b.name),
);
catalogue.capturedAt = '2026-09-22';
catalogue.source.batch = '2026-09-22-star50-cross-search-and-source-review';
catalogue.source.policy = 'Project-level deduplication. Public JEV-related GitHub repositories at or above 50 stars are included only after fixed-commit source review. Discovery includes GitHub repository search, GitHub code search, current competitor catalogues, and direct source inspection. Runtime behavior is not independently verified.';
await writeFile(catalogueFile, `${JSON.stringify(catalogue, null, 2)}\n`);
console.log(`Added or refreshed ${additions.length} projects; catalogue now has ${catalogue.projects.length}.`);
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |