「when」の検索結果

Create, revise, or evaluate repository Agent Skills when the user asks to write a SKILL.md, improve triggers or information hierarchy, restructure references/scripts/assets, or diagnose skill predictability; do not use for product code, AGENTS.md initialization, general prompt editing, or automatic repository-wide cleanup.

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 one bounded adversarial pass when the user explicitly requests a report-style stress test or ROSE identifies a concrete material loophole in an existing strategy, spec, plan, review, or claim; do not trigger for an interactive grill/frontier interview or merely before write-back, implementation, reconciliation, or completion.

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。

Generate or materially revise a repository-local test plan, QA plan, acceptance matrix, or regression checklist on explicit request or when one concrete testability gap blocks formal DEFINE; do not trigger for ordinary implementation, test execution, TDD, review, or completion claims.

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。

Build a backend service or an end-to-end frontend/backend integration when service/API/data boundaries are the primary deliverable; do not trigger for pure UI, contract design only, security review, test workflow, or every feature touching both folders.

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 regression scouting routing. Use when agents, prompts, skills, model/tool routing, harness fixtures, or generated-output expectations change and need regression scenarios; do not use for ordinary product-code regressions.

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。

Perform direct, bounded browser inspection through the `browser.qa` capability when the user requests runtime UI evidence or one browser-specific claim needs DOM/accessibility/console/network/visual verification; do not trigger for every UI change, backend work, delegated QA, or durable E2E artifact routing.

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。

Conduct one bounded evidence-grounded code review when the user explicitly requests review or ROSE names a concrete unresolved correctness/quality risk; do not trigger automatically after implementation, before every merge, for every bug fix/refactor, or as a completion gate.

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。

Code-review quality gate and test-enhancement rubric. Use when ROSE needs sharper review output contracts, severity and risk prioritization, evidence anchors, negative review cases, fixture or golden-output drift guidance, or a Chinese review report profile; do not use as a duplicate code-review agent or final PASS 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。

Configure or diagnose project context, rules files, context packs, or documented context degradation when explicitly requested; do not trigger automatically at session start, task switching, ordinary repository exploration, implementation, or completion.

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。

Coverage review and verification sufficiency routing. Use when test coverage, uncovered paths, coverage reports, or verification adequacy need a read-only QA review; do not use for writing tests or running browser/E2E artifacts.

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。

Optional focused post-implementation review routing. Use only when the user requests review or the changed surface has a clear specialist evidence need that direct diff inspection and the smallest relevant check cannot cover. Never creates an automatic review swarm.

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。

Create or update source-grounded documentation when the user explicitly asks for docs/ADR/onboarding material, a public contract change requires docs, or an accepted hard-to-reverse decision meets the ADR gate; do not trigger for every feature, architecture discussion, implementation, review, or SHIP request.

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。

Generate, edit, inspect, or verify editable PowerPoint/PPTX decks when a .pptx file is the deliverable; use for template-preserving edits and from-scratch slide production, but not for HTML/SVG mockups, PDF-only reports, or presentation advice that needs no PPTX artifact.

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。

E2E artifact handling routing. Use when traces, videos, screenshots, reports, or failure bundles need controlled repository-local placement; do not use for simple unit tests or production-mutating E2E flows.

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。

Build or modify production UI components, layouts, client state, responsive behavior, accessibility, or UX inside an app when that frontend surface is the primary deliverable; do not trigger for rich campaign/media pages, backend integration, every user-facing text change, delegated browser QA, or review alone.

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。

Break a clear scope or accepted specification into ordered tasks/packages when the user explicitly asks for a plan, estimate, dependency order, or task breakdown; do not trigger for ordinary implementation, every multi-step task, speculative parallelism, review, or completion.

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。

Produce or apply an approved report-first proposal for workflow, ROSE, skill, command, subagent, memory, install, or harness-doc changes; use after harness-issue-triage localizes a harness problem or when the user explicitly requests harness maintenance, and do not edit core harness files without explicit human approval.

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。

Optimize a measured performance problem when the user names a latency/load/Core Web Vitals/resource target or current profiling evidence identifies a bottleneck; do not trigger from generic implementation, review, or an unsupported suspicion that code may be slow.

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。

Performs read-only GitHub issue or PR triage with evidence links. Use when analyzing public or repository GitHub issues/PRs without mutating labels, comments, branches, reviews, merges, or issue state.

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。

Prefer a fresh matching specialist for a clear bounded non-trivial package when current capabilities and permissions permit it; use direct ROSE work only for accepted direct-work exceptions or a concrete block.

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。

Create, edit, fix, or explain Mermaid diagrams for relationships, decision branches, interactions, lifecycles, and data models; also use when the parent selects a diagram to materially clarify an explanation. Do not trigger for simple status, one fact, short lists, quantitative charts, or marketing slides.

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。

Research one bounded mature-project/prior-art question when the user explicitly asks how established projects handle it or ROSE names a decision-shaping prior-art gap; do not trigger automatically for IDEATE, DEFINE, BUILD, implementation, local review, or every design choice.

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。

Implement an accepted change in bounded dependency-ordered increments when the user requests implementation and the scope benefits from multiple coherent slices; do not trigger merely because work touches multiple files, changes behavior, or is over an arbitrary line count.

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。

Diagnose user-reported AILI/ROSE harness or workflow behavior problems without editing files; use when the user says a command, skill trigger, subagent packet, memory flow, installer, docs, or agent prompt behavior is wrong and wants to know where the issue lives and how to fix it. Do not use for normal product-code bugs; return any approved modification need to ROSE.

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。