2,246 件 ・ 関連度順
概要と使いどころ
Run the full implement-review-fix loop using implementer and reviewer personas. Supports effort-based multi-reviewer scaling (1-5 reviewers) with automatic specialization selection. Includes memory-based feedback loop that learns from past review patterns. Loops until all reviewers find 0 issues of any severity.
日本語の概要は準備中です。原文の説明を表示しています。
Runs Charted Coding iterations in a loop — route via charted-continue, batch red or green work for an entire test file, commit, then repeat until the PR is complete. Infers design doc and PR number when omitted. Use when the user invokes charted loop, wants batch TDD for a PR test file, or asks to continue charted work with commits.
日本語の概要は準備中です。原文の説明を表示しています。
Design AI feedback loops for continuous improvement. TRIGGERS - Use when user needs help with ai-feedback-loop related tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Design agricultural cooperatives. TRIGGERS - Use when user needs help with agricultural-cooperative related tasks.
日本語の概要は準備中です。原文の説明を表示しています。
Interact with UI Toolkit (UXML/USS) runtime UI in PlayMode. Use INSTEAD OF uloop-simulate-mouse-ui / uloop-simulate-mouse-input whenever the target UI is UI Toolkit — those tools only reach uGUI and report 'no UI element hit' or silently do nothing on UI Toolkit panels.
日本語の概要は準備中です。原文の説明を表示しています。
/review-fix をループ実行し、CONVERGED になるまで自動修正を繰り返す。スコープ引数は /review-all と同じ（wt / PR #N / pr:N / vs:<branch> / git range / ファイル列挙、デフォルトは比較ブランチとの差分）。最大イテレーション数を数値で指定可能。Use when user says 'レビュー収束まで繰り返して', 'review-fix-loop', '自動修正ループ', or '収束するまでレビュー'.
Compares Hi-C contact maps between conditions across the right scale -- differential bin-pair contacts (multiHiCcompare, diffHic), differential A/B compartments (dcHiC), differential TAD boundaries (delta insulation), and differential loops (diffloop, DiffHiChIP) -- with distance-stratified between-sample normalization, replicate-aware NB-GLM FDR, HiCRep SCC reproducibility gating, and CNV correction for cancer/aneuploid samples. Use when comparing Hi-C between treatment and control, finding differential contacts/compartments/boundaries/loops, normalizing two maps of unequal depth, choosing a replicate-aware test, gating replicates with SCC, or correcting copy-number artifacts before a tumor-vs-normal comparison.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user hands over a GitHub issue to be delivered end to end — 'resolver a issue #42', 'loop na issue 42', 'deliver issue https://github.com/o/r/issues/42' — or when an Orca worker preamble dispatches `feat-loop #N`. Turns the issue into a plan, executes it, reviews the result and runs at most 2 fix cycles until APPROVED, then opens a pull request that closes the issue. Never merges. Do NOT use without an issue (feat-feature / feat-quick), to only plan (feat-feature), to only review (feat-review) or to execute an existing plan (feat-exec).
日本語の概要は準備中です。原文の説明を表示しています。
Sanguo RAG unresolved mention resolution loop. Use for: 三國 RAG, unresolved mentions, alias review, observed mentions, MCQ triage, manual roster seeds, false-positive exclusion, running run_resolution_loop.py, applying unresolved-triage answers, delegating 三國名詞查證 to a web-capable agent, or Pilot ETL chunk experiments with LangChain text splitters / LangGraph / LangFlow around 張飛長坂橋等小樣本流程。
日本語の概要は準備中です。原文の説明を表示しています。
Sanguo event review loop with LangGraph Studio visualization. Use for: 三國事件審核、generic event candidates、battle candidates、event review MCQ、accepted/rejected events、promote events、LangGraph Studio、human-in-the-loop、事件候選可視化、chunk -> extract -> validate -> review -> publish。
日本語の概要は準備中です。原文の説明を表示しています。
Apply Boyd's OODA loop to navigate fast-moving, uncertain, or competitive situations — Observe what is actually happening, Orient through mental models and context, Decide on the clearest path, Act quickly, then loop again. Load when the situation is changing faster than the current plan, when a competitive response is needed, when the user is stuck in analysis paralysis in a dynamic environment, when shipping under uncertainty, or when deep-thinking diagnoses a fast-moving / competitive frame. Triggers on "what should we do right now", "the situation is changing", "how do we respond to this", "competitive response", "we need to move fast", or "we're stuck deciding". Based on John Boyd's OODA loop — Observe, Orient, Decide, Act — adapted for product and business contexts (OODA Canvas 2026).
日本語の概要は準備中です。原文の説明を表示しています。
Design a self-improvement loop for a shipped product's AI agents — production traces feed evals, evals feed improvement proposals (prompts, playbooks, retrieval configs), and a human approval gate promotes changes with rollback. Technique-agnostic: chooses per project between ACE-style evolving playbooks, GEPA/MIPROv2 offline optimization, or simple eval-driven iteration via references/techniques.md. Load when the user asks to make my product's agents self-improving, learn from production traces, add a learning loop, evolve prompts or playbooks safely, promote agent improvements, or GEPA-style optimization. NOT harness-evolution (that improves the coding agent), NOT experimentation (product A/B tests), NOT agent-run-retro (dev-phase manual retros — this skill is the production-scale continuation).
日本語の概要は準備中です。原文の説明を表示しています。
Compares Hi-C contact maps between conditions across the right scale -- differential bin-pair contacts (multiHiCcompare, diffHic), differential A/B compartments (dcHiC), differential TAD boundaries (delta insulation), and differential loops (diffloop, DiffHiChIP) -- with distance-stratified between-sample normalization, replicate-aware NB-GLM FDR, HiCRep SCC reproducibility gating, and CNV correction for cancer/aneuploid samples. Use when comparing Hi-C between treatment and control, finding differential contacts/compartments/boundaries/loops, normalizing two maps of unequal depth, choosing a replicate-aware test, gating replicates with SCC, or correcting copy-number artifacts before a tumor-vs-normal comparison.
日本語の概要は準備中です。原文の説明を表示しています。
front-end-design-patterns を使い、指定されたフロントエンド範囲に対して サブエージェント調査（必要時は複数スコープに分割した独立 fresh audit） → メインセッション修正 → 必要時のみ性能計測 → simple-add → 再調査を NO_FINDINGS まで繰り返す、機能変更なしの内部リファクタリングループ。 Trigger: front-end-refactor-loop, front-end-design-patterns リファクタリングループ, フロントエンドリファクタリングループ, Reactリファクタリングループ, サブエージェントでフロントエンド調査, NO_FINDINGSまでリファクタ, 性能計測つきフロントエンドリファクタ
This skill should be used when the user wants to "test a claim against data", "validate an empirical hypothesis", "refine a model/theory with evidence", "characterize a pattern and verify it", "演繹と帰納で検証", "仮説をデータで検証して更新", "実例と反例で確かめる", "弁証法ループ", "主張を現物で裏取り", "傾向分析を検証して精緻化", or mentions iteratively updating a hypothesis by deriving predictions and testing them against a real corpus. NOTE: Use this for VALIDATING/REFINING an empirical claim or model against real data through a derive→test→update loop. Use strong-inference for debugging an UNKNOWN cause, and devils-advocate for adversarially stress-testing a DESIGN proposal.
make review / make review-close があるプロジェクトで、Codex の PR レビューと修正を最大5周回す。「レビューループ」「review-loop」「make review で回して」で発火。各レビューを対象 commit と対応付け、根拠を確認して修正し、完了後にクローズする。
Cooperative vibe coding across machines — real-time collaborative development with humans and AI agents. Covers current tools (Live Share, Code With Me, Zed, Cursor multiplayer, tmux), git-based async patterns, AI agent coordination, and the aspirational future of multi-human multi-agent development. Activate on: "pair programming", "vibe coding together", "collaborative coding", "mob programming", "remote pairing", "code together", "multiplayer coding", "Live Share", "Code With Me", "ensemble programming", "cooperative development". NOT for: building a real-time collaboration ENGINE (use real-time-collaboration-engine), git workflow mechanics (use git-best-practices), single-user AI coding assistance.
日本語の概要は準備中です。原文の説明を表示しています。
AIエージェントが失敗や同じ操作を繰り返す原因を、エラーと実行状況から整理します。小さな復旧操作を試し、結果と根拠を引き継げる報告にまとめるスキルです。
PyTorchのモデルや学習コードを作成・点検し、データ読み込み、実験の再現性、学習状態の保存、GPUメモリや処理速度の改善を支援するスキル。
AIエージェントの不調を、指示・記憶・ツール実行・画面表示など12の層から調べるスキル。コードやログを根拠に原因を整理し、重要度順の指摘と修正案をまとめます。
処理の高速化を、現状の計測、仮説ごとの変更案の比較、正しさの検証へ分解し、時間や費用の上限内で最も速い安全な案と再実行できる手順を残すスキル。
Claude Codeの記憶、定期実行、タスク待ち行列を組み合わせ、継続的な作業を設計するスキル。外部の実行環境や画面操作の連携設定も案内します。
目標画像と実装した3Dシーンのスクリーンショットを比較し、構図・照明・質感を段階的に改善します。見た目の再現度を採点し、描画速度も確認しながら修正を重ねるスキルです。
Iterate on a GitHub PR until latest-head checks are green or a precise blocker is named. Use when a PR still has failing or pending checks after review fixes, including after greploop.
日本語の概要は準備中です。原文の説明を表示しています。