「review loop」の検索結果

Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.

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。

the UGC fix-loop toolkit — surgically re-render a bad window/beat of a single-take UGC master (stitch_replacement.py, pure FFmpeg) and GPT cross-model review a Seedance prompt before render (vet_seedance_prompt.py, routed through the openai-proxy). Fetch it into a one-shot UGC recipe so both scripts resolve on any machine and the vet call bills the Ads agent.

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。

End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.

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。

Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.

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。

Run fable-mode execution discipline on Claude Sonnet. When invoked by slash command or by name, spawns a Sonnet subagent that follows the staged loop — stage plan, parallel delegation, a failable verification check at each stage, and a skeptical self-review before delivery; a wording-only request runs the loop inline on the current model. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on Sonnet.

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。

Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.

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 SQL and ORM queries for correctness, safety, and performance before they ship.

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。

Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.

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 running, reviewing or changing coco's self-evolution cycle: the 30-day loop that observes how skills are actually used, proposes evidence-backed edits to them as one branch and one pull request, and lands nothing without the owner's merge. Also use when asked why a skill changed, what the loop would propose next, or how to reject a proposal so it is not raised again.

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, implement, optimize, and review SIMD code in .NET. USE FOR: vectorizing scalar loops with TensorPrimitives, Vector64/128/256/512, or platform hardware intrinsics; reviewing existing SIMD code, including the generic Vector type, for contract equivalence, tail handling, memory safety, portability, fallbacks, and measured performance. DO NOT USE FOR: performance work unrelated to SIMD or vectorization.

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。

Close out a change without the deep review loop: stage, simplify code and docs, run the project's checks, smoke test, update the changelog, self-improve, and ship. Use when the user asks to "quick finalize", "quickly finalize", "finalize quickly", "light finalize", "wrap this up quickly", "close this out without the full review", or "ship this without the deep pass".

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。

Adversarial review and fix loop for code, specs, plans, and migration manifests.

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。

Route substantial coding or repository-review work through a two-stage Sol commander/verifier and separate Luna Max CLI worker. Use when the user explicitly asks Sol to direct or supervise Luna, explicitly requests this router, needs an isolated auditable Luna-owned implementation with a Sol review loop, or asks to diagnose or measure the router itself. Do not use merely because a task involves coding, verification, progress reporting, or token saving. For small or straightforward tasks, keep work in Sol unless the user explicitly requests Luna; router configuration, usage, and efficiency questions should use read-only inspection without launching a worker.

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。

Full enhancement pipeline for an existing Lattice skill — rewrites a molecule or atom to modern-capable-model grade: restores degraded grammar, deduplicates, hardens gates and branching to one-unambiguous-action precision, verifies zero behavioral loss against a pre-capture diff, then runs the combined QA gate (skill-review, skill-tighten, skill-validate) and an independent fresh-context verifier, fixing everything found. Consumer-first: optimized for first-time open-source users on fresh repos with minimal .lattice/ setup, running capable models. Use when the user says 'enhance this skill', 'upgrade this molecule', 'modernize this skill', 'optimize this skill', 'make this skill production grade', 'full enhancement', 'polish this molecule like design-blueprint', or names a molecule/atom to overhaul. For gap-finding only use skill-review; for conventions only use skill-validate — this skill runs the whole loop end to end.

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。

This skill should be used when the user says "/council", "council", "deliberate", "multi-perspective decision", "트레이드오프 분석", "위원회 소집", "여러 관점으로 검토", or wants deep multi-perspective deliberation with tradeoff mapping. Combines tribunal (structured adversarial review), agent-council (external LLM opinions), dev-scan (community sentiment), and step-back (meta-level review) into a unified decision-making committee. Uses Agent Teams for real peer-to-peer debate with iterative step-back moderation loop.

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。

You are an expert in Cline, the autonomous AI coding agent for VS Code that can read files, write code, run terminal commands, and use the browser — with human-in-the-loop approval at each step. You help developers use Cline for complex multi-file refactoring, feature implementation, debugging, and codebase exploration where the AI plans and executes while the developer reviews and approves.

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。

Make hand-painted watercolour-and-ink cartoon videos (MP4) with code — p5.js + p5.brush rendered frame by frame in headless Chrome, encoded with ffmpeg — starring Clawd or any character. Use when the user asks to make an animation, animated short, cartoon, music video, lyric video, animated GIF/loop or "a video of Clawd…", or mentions the PDoomVideo / ClaudeAnimationBase approach. Covers storyboarding, the engine API, the render-and-look review loop, music/lyric sync and splitting long videos across subagents.

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。

Closes a large backlog of findings (a gap analysis, an audit, or 10+ bugs) in prioritized waves. Loops through triage, dependency analysis, parallel fix streams, a test gate, and re-audit until the target is met. Use after a gap analysis, audit, or review produces 10+ findings, or to burn down a large bug or tech-debt backlog.

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。

Suede-affiliated recurring marketing workflow design for cadence, inputs, decision rules, checkpoints, failure states, and measurable outputs. Use when the user wants repeatable ad-fatigue, content-refresh, churn-watch, ranking-drop, or weekly-review loops. NOT FOR: one-off tactic ideation (use suede-marketing-ideas), experiment design (use suede-ab-testing), or creating a live automation without explicit scheduling authority.

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 optimizing, auditing, or preparing to ship web animations or rendering performance work: frame loops, scroll/viewport reveals, mount/unmount transitions, canvas/WebGL lifecycles, reduced motion, lazy rendering, and deferred off-screen work. Use for jank, per-frame allocations, forced reflows, render loops, animations that do not pause off-screen, content-visibility, requestIdleCallback, analyzing Chrome DevTools performance traces for animation or rendering issues, or choosing between browser-driven CSS/WAAPI, minimal JS, phase, and Motion/GSAP. Use when the user explicitly asks about phase APIs or behavior. Do not use during exploratory animation ideation, prototyping, visual iteration, or trying variants, even when the code already imports phase; wait until the user asks for performance guidance, an audit, production implementation, ship-readiness review, or about phase itself.

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。

Audit an implementation against its plan with a hostile peer agent, debate findings to consensus, and drive fix waves until the auditor runs dry. Use when a done-claim needs verification the implementer cannot game ("hostile review", "adversarial audit", "is this PR faithful", "find the escape hatches") — the loop that beats the laziness bias with its own game theory.

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。

Engineering design cycle covering requirements elicitation, specifications writing, constraint identification, iterative prototyping, and design communication. Spans the full loop from problem definition through ideation, analysis, prototyping, testing, and redesign. Includes morphological charts, TRIZ, Pugh matrices, design reviews, and the distinction between functional and non-functional requirements. Use when framing engineering problems, generating design alternatives, writing specifications, or running design reviews.

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。

ALIGN for paper figures — draw a method-overview figure as an executable p5.js program that replays its own construction in named stages, exports SVG, and improves through pixel-only independent Codex subagent review whose gate is 'explain the method back from the figure alone, and is it worth looking at'. The method sets the relationships the figure must show, the chosen visual identity sets how its marks look, a composition source lends arrangements; the method may be the source's own (意临) or yours in its arrangement (风格迁移). Not for one-shot raster image generation.

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。

ALIGN for paper figures — draw a method-overview figure as an executable p5.js program that replays its own construction in named stages, exports SVG, and improves through pixel-only cross-model review whose gate is 'explain the method back from the figure alone, and is it worth looking at'. The method sets the relationships the figure must show, the chosen visual identity sets how its marks look, a composition source lends arrangements; the method may be the source's own (意临) or yours in its arrangement (风格迁移). Not for one-shot raster image generation.

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。