789 件 ・ 関連度順
概要と使いどころ
Plan and document handoffs, parent lane contracts, and parallel batch contracts between specialized AI agents (foreman, workers, reviewers). Use for multi-agent workflows, subagents, original goal preservation, native gates, claim ceilings, terminal states, baton passes, or guild-style agent coordination.
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 reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show
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 auditing or fixing prose that reads like a leaked reasoning transcript — dead design-session citations such as (decision N), audit item codes, or §N of uncommitted drafts; change narration such as "used to", "no longer", "this cut"; stack or review vantage ("a later PR in this stack", "rejected in review"); reviewer-addressed justifications; control-flow narration; or hedged planning residue in comments, JSDoc, docs, or Agent Notes.
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。
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships. Use when output must clear two independent adversarial reviewers before it ships.
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, design, write, revise, translate, and review empirical or technical research papers through an evidence-bounded dialectical workflow. Use when Codex must develop a research question, integrate reference papers with a user's ideas, build phenomenon-mechanism-conditions reasoning, design methods or experiments, restructure or edit a manuscript, translate Chinese academic text into restrained English, answer reviewers, or run multi-round peer-review convergence without fabricating evidence.
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。
Propose a UI change for human sign-off before building it. The default path deploys a rough live staging preview (with NUXT_PUBLIC_CROUTON_REVIEW=true) so the reviewer pins comments on the real running page. Use --static for the offline HTML/CSS mockup fallback (no deploy available, or speed over fidelity). Invoke for any task that adds/changes a .vue component, a layout, a page, or a theme.
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。
Record a WebM demo video of a UI flow with shot-scraper video — a YAML storyboard drives the browser (click, type, scroll, wait) with an animated cursor overlay, so a reviewer can watch the feature instead of driving it. Use to attach motion evidence to a UI sign-off (#307), to turn an issue's "How to test" steps into a watchable clip, or when asked to "record a demo", "make a video of this flow", "show me it working".
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, revise, and validate publication-ready academic paper figures and tables. Use for LaTeX tables, related-work comparison tables, result tables, notation/dataset/taxonomy tables, precise source-data-driven experiment plots from CSV/JSON/logs, generated conceptual figures such as system overviews/pipelines/architectures/threat models, captions, artifact specs, source-data traceability, and paper-ready PDF/SVG/PNG/LaTeX exports. Do not use for prose-only paper writing, self-review, reviewer response, rebuttal drafting, or external literature-management workflows.
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 every Convex audit (authz, reviewer, advisor, insights) into one scored, deduped readiness report with an ordered fix plan — Lighthouse for your backend.
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 every Convex audit (authz, reviewer, advisor, insights) into one scored, deduped readiness report with an ordered fix plan — Lighthouse for your backend.
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 code review that breaks the self-review monoculture.
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。
Simulates academic peer review, evaluating papers across Originality, Methodology, Results, and Writing to provide Major/Minor Revision recommendations with actionable feedback. Triggers when a user asks to "review my paper," "simulate peer review," or "give my paper a peer review.
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。
Integration review after stable code. Audit tier for high-risk surfaces; planning tier for optional low-risk review. Produces a review note and fix list — no implementation.
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。
Offensive/hostile QA auditor. Generalist reviewer specialized in the WordPress universe. Assumes everything is wrong until proven otherwise. Audit-tier only — produces severity-ranked findings, never implements.
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 reviewing vendor estimates for software development projects. Use this skill when you need to evaluate whether a vendor's cost estimate, timeline, and approach are reasonable and whether the project is likely to succeed. This skill helps identify gaps, risks, overestimates, underestimates, and unfavorable contract terms. It generates comprehensive Markdown review reports with actionable recommendations to optimize costs while ensuring project success.
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。
Web サーバ（nginx/apache、Linux 中心）の Phase 1 設定セキュリティレビュー。 target_profile.yaml で対象を確定し、MANIFEST.txt + manifest_attestation.txt で証跡 integrity を検証。 SSH 直接または証跡受領モードで 9 観点 (OS/リソース/ログ/ネットワーク/サービス/認証/監視/バックアップ/証明書) を read-only 走査。6 階層ガード (allowed/conditional/conditional_sensitive/ask-first/exceptional_sensitive_read/forbidden)、 3 軸補助 (Exploitability/Blast Radius/Service Criticality) の重大度判定、 observation_status による未確認の独立管理、evidence_dir/raw_evidence_store 分離、自己レビュー必須。 Windows/IIS は v1 hard fail。 Use when: Web サーバの設定セキュリティレビュー、Phase 1 監査、nginx/apache 構成監査、 EOL ランタイム調査、ログローテーション不備調査、ドキュメントルート漏えい調査。
Use this skill when you need to review presentation materials from an audience perspective to improve their quality and effectiveness. Evaluates content clarity, visual design, logical flow, engagement factors, and Marp technical compatibility. Triggers include "review my presentation", "check my slides", "presentation feedback", or when a user has completed a draft presentation and wants comprehensive quality review.
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 meeting minutes documents for completeness, action item clarity, decision documentation, and consistency with source materials like hearing sheets. Use when validating meeting minutes quality or preparing minutes for distribution.
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。
設計文書、分析レポート、報告書などを批判的な視点で徹底レビューするスキル。 6つの異なる立場（開発者、PM、顧客、QA、セキュリティ、運用）のペルソナを持つサブエージェントが並列でレビューを実行し、 「本当にそうか？」「根拠は何か？」「テストできるか？」「運用できるか？」という視点で 曖昧さ、根拠不足、論理飛躍、テスト不能、セキュリティリスク、運用懸念を検出する。 Use when reviewing design documents, analysis reports, incident reports, or any document requiring rigorous validation of claims and evidence.
Professional contract review skill for business agreements including NDAs, MSAs, SLAs, SOWs, and software license agreements. Provides systematic clause-by-clause analysis, risk assessment with quantified scoring, red flag detection, and negotiation guidance. Use this skill when reviewing vendor contracts, partnership agreements, service agreements, or any business contract requiring risk evaluation and negotiation preparation. Triggers include "review this contract", "analyze this NDA", "check this agreement for risks", "prepare for contract negotiation", or when evaluating terms and conditions.
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 this skill for critical code review that focuses on whether the code actually works correctly and achieves the expected results - not just whether it matches a design document. This skill assumes designs can be wrong, finds bugs the design didn't anticipate, and verifies end-to-end correctness. Triggers include "critical code review", "deep code review", "verify this implementation works", "find bugs in this code", or reviewing implementation against requirements. NOTE - Security review is OUT OF SCOPE; use a dedicated security review skill for that purpose.
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。
OpenAI Codex CLIを使用してドキュメントやコードのレビューを依頼するスキル。GPT-5.5モデルをxhigh推論モードで呼び出し、深い分析によるレビューを実行。レビュー結果を指定フォルダに出力し、その内容を確認・分析する機能を提供。コードレビュー、ドキュメントレビュー、設計書レビュー、テスト計画レビューなど、専門的なレビューが必要な場面で使用。
4人の異なる専門家ペルソナ（20年ベテランエンジニア、TDDエキスパート、Clean Codeエキスパート、バグハンター）で ソースコードを批判的にレビューするスキル。設計判断、テスト容易性、可読性、バグ検出の観点から コードの問題を検出し、改善提案を行う。Python/JavaScriptに対しては追加のチェックポイントを適用。 バグハンターは状態遷移、例外パス、依存関係、非同期競合に特化し、本番環境での問題を事前に検出する。 Use when reviewing source code from multiple expert perspectives to find design flaws, testability issues, code quality problems, and runtime bugs. Triggers: "critical code review", "multi-persona code review", "expert code review", "code quality assessment", "find bugs".
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.
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。