「nes」の検索結果

設計判断・ライブラリ選定・アーキ判断・実装アプローチが 2 つ以上ありえる場面で必ず発火させる、「複数案＋メリデメ＋推奨」を提示する横断スキル。「どっちがいい？」「これでいい？」「方針を相談したい」と聞かれたとき、ライブラリ選定・ディレクトリ構成・API 設計・テスト戦略のように選択肢が複数ある相談を受けたとき、要件定義 / 設計 / 実装の中で「複数アプローチがありそう」と感じたときに必ず使う。一案だけポンと出さない。

調査・スパイクを「問いに答える」でなく「判断の危険を潰す」ために走り切る。何を決めるための調査かを計画として出して依頼者と合意し、裏付け一つで閉じず反証で開き、結論から読める形で報告するまでを担う。次の判断・見積もりが決められず調べる必要があるとき、使い捨ての実験で確かめたいときに使う。

作業をふりかえって改善案を引き出し、記録する。セッション内のすべてのストーリーが完了したとき、依頼者の終わり発話 (作業を区切る発話) を観測したとき、または依頼者が「ふりかえろう」「retrospective」と明示したときに発火。同セッション内で 1 度 skip された場合は再発火しない。

エンジニアとして手を動かす作業全般で必ず発火させる: コードを書く / テストを書く / リファクタ / バグ修正 / E2E spec 追加 / 既存仕様への小さな修正など、コードに触る作業すべて。「実装して」「テスト書いて」「リファクタして」「バグ直して」のような依頼を受けたとき、または基本設計が済んで実装フェーズに入るときに発火。基本作業は TDD（テスト先書き → 最小実装 → リファクタ → コミット）で進め、要件が大きければ適切な小ささに分割しつつサイクルを回す。発火しないのは要件定義 / 基本設計の対話中（まだ手を動かしていない時）だけ。

ユーザーストーリーを Independent / Valuable / Small / Testable で点検し、満たさないストーリーを分割または再定義するための skill。要件定義完成直後 (ユーザーストーリーを書き終えた直後) に必ず発火させる。基本設計中や実装中に「このストーリー大きすぎる」「他のストーリーに依存している」「ユーザー価値が見えない」「受け入れテストが書けない」と気付いたタイミングでも発火させる。Small は『ユーザー価値を保ったまま分割可能な最小単位』として価値ベースで判定する (技術的なサイクル数ではない)。Negotiable は意図的に落とし (要件 / 設計フェーズで固める方針)、Estimable は暗黙 (固める方針なら自動で満たされる)。

Analyze Codex provider rollout JSONL and ego-benchmark-harness run artifacts to identify slow or failed individual tasks, tool retries, token/cost anomalies, and differences in agent execution paths. Use when users ask to analyze a Codex session or rollout, explain why a Codex task was slow or failed, inspect a Codex provider execution trace, compare Codex runs, count function_call or tool output events, or investigate agent-home/.codex/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。

Compare standardized metrics across multiple ego-benchmark-harness runs by recalculating them from tasks.jsonl and session JSONL, never from HTML reports. Covers overall aggregates (success rate/average score), Odysseys per-rubric pass rates, duration distributions (avg/p50/p90/max), turns/tools/cost, error and exception counts, per-task success matrices, helper distributions, and the share of DOM operations. Use whenever users ask to compare data or metrics across runs, calculate aggregate/Odysseys/duration/turn/error/helper metrics, inspect differences among runs, or compare multiple rwb/real-world-bench runs. Use pi-session-analyzer instead for deep forensic analysis of why an individual task was slow or failed.

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。

Analyze pi (coding-agent) session JSONL and ego-benchmark-harness run artifacts to explain slow or failed individual tasks, compare execution-path differences between agents or browser tools, and count tool calls and error types. Use this skill whenever users ask to analyze a pi session, explain why a task was slow or failed, compare two runs, investigate an error, locate the session corresponding to tasks.jsonl, inspect an agent execution path, count tool calls, analyze a run ID, or perform any forensic or retrospective analysis of JSONL under ~/.pi/agent/sessions/ or agent-home/.pi/agent/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。

Signpost (not a knowledge pack) for maritime safety and class rules: SOLAS Consolidated Edition 2024 (IH110E) as the paywalled statutory core, ISM Code & Guidelines 2018 (ID117E), ISPS Code 2003 (K116E) and the 2021 guide (IB116E), and COLREGS 2026 (IC904E), with designation, edition, owner, status, and official URL only. Contains no source content. Free-path layers are US flag implementation (eCFR Title 46 and USCG circulars), the USCG Navigation Rules PDF, UK MCA notices under Open Government Licence v3.0, and class portals (DNV, ABS, Bureau Veritas). None of those layers is the IMO consolidated text. No in-repo pack covers these instruments.

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。

Reconstructed reference notes on US FAA approval guidance for airborne software and airborne electronic hardware, built from four public-domain sources (FAA Order 8110.49A, AC 20-115D, AC 20-152A, AC 00-69; documents dated 2017-07-21 to 2022-10-07, pinned 2026-10-12). Use for how FAA certification staff plan and conduct software reviews (certification liaison, desk versus on-site review, review planning agreements), how the level of FAA involvement (LOI) is picked and scored with the Appendix A worksheets, how software conformity inspection works (software part and installation conformity, ASE and ASI tasks, Form 8120-10), what AC 20-115D recognizes and how DO-178B processes and tool qualification transition to DO-178C/DO-330 (supplements, FLS, UMS, legacy software changes), and what AC 20-152A adds for airborne electronic hardware (simple versus complex custom devices, robustness and HDL code coverage, tool assessment, previously developed hardware, COTS IP, COTS devices, circuit board assemblies), and what AC 00-69 adds as best practices for change impact analysis, data and control coupling, and design-level error handling (best practices, not guidance and not a means of compliance). SCOPE LIMITS: FAA guidance only, and guidance is not regulation (ACs are acceptable means, not the only means); no RTCA DO-178C or DO-254, EUROCAE ED-12C or ED-80, supplement, or SAE ARP text, which are copyrighted and named only (see the avionics-signpost pack); no AC 00-72 (named, not packed); no DO-178C software-level objective tables; no EASA AMC 20-115D or AMC 20-152A content (use easa-rules); reflects the pinned source dates, not later FAA actions; synthesized reference notes, not legal advice and not a substitute for the source documents. LICENCE: Public Domain (US Government work, 17 U.S.C. 105).

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。

Choose the design and the numbers a research run can honestly claim — write the structured METHOD RECORD (databases, date of access, search string, criteria, screening counts) that r0 validates, pick the claim strength a design can actually carry, record a statistic as data rather than prose, route to the reporting guideline the design owes, and decide what to preregister. Use when a run's question, design, search or statistics have to be settled before the writing, or when a claim needs a strength or a number attached to it.

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。

Write acceptance criteria for a Jira story using Given/When/Then scenarios. Use this skill when the user asks to write AC, acceptance criteria, write scenarios, improve a story, add AC to a ticket, or mentions a Jira ticket and wants better requirements. Also triggers on "write better AC", "this story needs AC", "add scenarios to this ticket", or when reviewing a Jira story for completeness.

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。

Comprehensive, measurement-driven performance optimization for latency, throughput, memory/GC, and tail behavior. Use when the user asks to optimize/speed up, reduce latency (p95/p99), increase throughput/QPS, lower CPU/memory/allocations/GC pauses, profile hot paths, or run a benchmarked perf pass (including JSONL/query-heavy code). Requires before/after measurement on a runnable workload (or an explicit `UNMEASURED` plan) plus a correctness 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。

Mutation testing patterns for verifying test effectiveness. Use when analyzing branch code to find weak or missing tests.

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。

Mitigate incidental code complexity when control flow is tangled, nesting is deep, names are hard to parse, or reasoning requires cross-file hops. Use when a review stalls on readability, you need an analysis-first refactor plan before edits, or you want essential-vs-incidental verdicts, ranked simplification steps, a small structural sketch, and a TRACE assessment (analysis-only; no edits).

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 a Marty-Cagan-style opportunity assessment interview and produce a ~2-page Opportunity Brief in Confluence. Covers business objective, customer, problem, success metric, current alternatives, assumptions/risks, and what we don't know yet. Triggers on "opportunity brief", "opportunity assessment", "discovery brief", "who is this for", "why are we building this", "validate this idea", "product discovery", or any request to frame a feature before implementation. One question at a time. Records accepted research gaps as structured Confluence Decision pages with bidirectional links.

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。

Brutally honest AGENTS.md/CLAUDE.md review backed by real A/B test evidence. Not just opinions — actual proof that your rules are dead weight. Roasts instruction files for bloat, slop, and redundancy, then proves it by running evals. Use when user says "roast my agents.md", "roast my CLAUDE.md", "prove my rules are useless", "eval roast", or wants entertaining evidence-based feedback on their AI config files. Also triggers on "audit my instructions" or "are my rules helping".

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。

Turn 'should never happen' into 'cannot happen' by defining owned inductive invariants and enforcing them at parse/construct/API/DB/lock/txn boundaries with a verification signal. Use when prompts mention invariants, impossible states, validation sprawl, cache/index drift, idempotency/versioning, retries/duplicates/out-of-order events, race/linearization bugs, loop correctness, or hardening another workflow (for example /tw-fix) with invariant checks first.

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 comprehensive exploratory testing on a website using browser automation, covering user journeys, forms, errors, accessibility, responsiveness, performance, and security basics. Use when asked to QA a site, explore an app, find bugs, or produce a browser testing report.

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 protocol with optional pre-core git diff review and safety guardrails (unsoundness, invariants, footguns, incidental complexity). Use when prompts say "/tw-fix this PR", "fix current branch", "fix this diff", "repair CI red", or "apply a minimal patch", and when crash/corruption/invariant-break issues need correction with a validation signal. Stop only after self-review exhausts actionable changes, each full cycle reaches post-self-review rerun plus terminal diff-review closure, and two consecutive zero-edit full cycles are clean.

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。

Compile deep repository evidence into artifact-bound correctness doctrine — authority/law/proof maps, owned invariants, failure archaeology, and the strongest durable destination for each piece of knowledge, plus an optional minimal repository-specific skill portfolio. Use when the user wants both deep codebase understanding AND durable doctrine, knowledge routing, or repo-specific skill recommendations. Research discoverable facts before asking. Read-only. Not for quick onboarding, one isolated invariant, ordinary implementation, generic review, or direct skill creation.

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 review an external integration QA lab with official surface snapshots, coverage matrices, fixtures, opt-in live lanes, and safe credential handling.

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 functional Clawix UI wiring while respecting visual mutation boundaries, pattern contracts, protected surfaces, and debt baselines.

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。

Investigate latency, freezes, memory growth, hitches, dropped frames, or perceived slowness with reproduction and instrumentation before optimizing.

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。