Results for “fix-loop”

review-all を実行し、指摘内容をコードに反映、bun run c / bun run lint / bun test で自己検証し、CONVERGED/NOT_CONVERGED の収束判定付き完了レポートを /tmp/arima-review-fix-result.md に出力する。レビュー→修正→検証→レポートを一気通貫で行うスキル。スコープ引数は /review-all と同じ（wt / PR #N / vs:<branch> / range / ファイル列挙）。review-fix-loop からの自動呼び出し（mode=non-interactive）にも対応。Use when user says 'レビューして直して', 'review and fix', '自動修正', 'レビュー反映', or when invoked by review-fix-loop.

The English summary is being prepared. Showing the original description.

/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'.

The English summary is being prepared. Showing the original description.

Drive repeated debugging cycles with the required diagnose skill: establish evidence for a cause, choose one focused fix, and rerun the original validation. Reassess after each change until no credible fix remains or further progress requires user input.

• Repeating bug fixes and verification until validation is clean
• Checking performance changes against original measurements
• Investigating regressions after each fix

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.

The English summary is being prepared. Showing the original description.

Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing assertion) and the user wants the agent to converge to "green" on its own. Framework-agnostic — wraps Aider's `--auto-lint`/`--auto-test`, an OpenHands SWE-Bench loop, a manual LangGraph cycle, or Claude Code's bash tool just the same.

The English summary is being prepared. Showing the original description.

QA validation and fix loop workflow — validates implementation completeness then iterates fix cycles until all acceptance criteria pass and quality gates clear

The English summary is being prepared. Showing the original description.

项目待办管理器（两种模式）。【收集模式】接收任意混合输入 → 解析追加到「项目待办.md」文档，不立即执行；【处理模式】读取文档 → 前置决策收集 → 按优先级逐条路由执行 → 更新状态 → 批次报告。触发词：【收集】「有几个问题先记到待办」「加到项目待办」「先存到待办文档」「记录这些待办」；【处理】「处理项目待办」「按待办文档逐条修复」「开始处理待办文档」。⚠️ 触发词必须含「待办」关键词才激活，避免与 issue-tracker / bug-fix-loop 混淆。

The English summary is being prepared. Showing the original description.

Bug修复循环协调者。测试完成后，读取技术问题追踪台，按P0→P1→P2顺序协调修复，每修复一个触发针对性回归测试，循环直至P0+P1全清，输出可上线结论。所有信息通过文档传递，不依赖对话历史。触发词：「全自动修复循环」「按Bug清单修复」「修复所有问题」「循环修复到上线」「开始bug修复循环」。

The English summary is being prepared. Showing the original description.

[Code Quality] Use when a workflow step or the user asks for a focused code-change review: staged, unstaged, branch diff or simple pull request. --fix-loop fixes and re-reviews. Complex pull request: workflow-review-changes; rationale: why-review.

The English summary is being prepared. Showing the original description.

[Code Quality] Review an exact pending commit when the commit skill selects lightweight review or the user requests it. --fix-loop repairs and re-reviews; no Git publication authority.

The English summary is being prepared. Showing the original description.

[Testing] Use when initializing, writing, reviewing or verifying performance/load/soak/capacity tests. --mode=verify --fix-loop (or --mode=green) diagnoses, fixes and remeasures with performance-review. Static bottleneck audits use performance-review.

The English summary is being prepared. Showing the original description.

[Workflow] Use when reviewing a pull request or changes that are complex, risky or cross-module and need specialist reviewers: reviews, applies validated fixes, re-reviews. Defaults to --fix-loop; --review-only reports. Simple PR: changes-review.

The English summary is being prepared. Showing the original description.

[Code Quality] Use when a workflow step or the user asks for rationale evaluation or critical judgment of a decision, claim or statement: necessity, options, trade-offs. --validate-findings checks findings; --fix-loop fixes. Diffs: changes-review.

The English summary is being prepared. Showing the original description.

[Planning] Use when a workflow step or the user asks for implementation planning. --mode=review supports review-only or --fix-loop; validate interviews, execute implements. --mode=ci plans CI fixes; --mode=cro plans conversion optimization.

The English summary is being prepared. Showing the original description.

[Testing] Use when a workflow step or the user asks for integration test generation, diagnosis or traceability checks. --mode=review checks test quality; --mode=verify runs tests, with optional --fix-loop.

The English summary is being prepared. Showing the original description.

[Testing] Use when a workflow step or the user asks for E2E test selection, generation or updates. --mode=verify runs tests; --fix-loop repairs failures; --visual-review={true|false}.

The English summary is being prepared. Showing the original description.