1.5万 件 ・ 関連度順
概要と使いどころ
Use only when the user explicitly requests agy, Gemini through agy, Antigravity, or an external-model second opinion for review or research. Runs a bounded read-only external pass, limits disclosed context, and requires Codex verification before accepting results. 中文触发：明确要求 agy、通过 agy 调用 Gemini、Antigravity、外部模型复核或外部第二意见。
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 the user explicitly invokes the `if` skill or asks for a concise, laconic, no-fluff, or to-the-point answer. Do not trigger on the ordinary word or programming keyword `if`. Detailed, step-by-step, exhaustive, educational, or fixed-length requests activate only when they also include an explicit invocation or brevity 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。
Use when designing, implementing, reviewing, debugging, testing, profiling, or porting concurrent, parallel, distributed, high-performance, network dataplane, kernel-bypass, or real-time software, including locks, semaphores, monitors, MPI, CSP rendezvous, DPDK, VPP, eBPF, XDP, AF_XDP, SR-IOV, RSS, RoCEv2/RDMA, RMS/EDF, priority inversion, and environment selection from silicon to edge.
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 performing cybersecurity operations - offensive or defensive - including threat detection and hunting, SOC operations, incident response, digital forensics and DFIR, malware analysis and reverse engineering, threat intelligence, cloud/container/network/application/API security, identity-access and zero-trust, OT/ICS and endpoint security, vulnerability and supply-chain management, DevSecOps, cryptography, AI security, compliance and governance, and red-team or penetration testing under signed rules of engagement; routes to one of 800+ technique playbooks mapped to MITRE ATT&CK, D3FEND, and NIST CSF.
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 developing, reviewing, debugging, porting, or engineering Linux kernel device drivers, kernel modules, device tree bindings, bus clients, subsystem drivers, DMA/IRQ/memory paths, userspace interfaces, or hardware bring-up plans.
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 advising, planning, reviewing, reporting, operating, or improving CTO and technology leadership work across strategy, cybersecurity management, SME/COE, functional and technical requirements, framework selection, people, organization, delivery, risk, KPI, roadmap, budgeting, governance, audit, R&D, stakeholder communication, culture, politics, and sector-specific leadership.
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 designing, evaluating, documenting, modernizing, reviewing, refactoring, or implementing software architecture and code-level structure, including requirements, context, architecture style selection, microservices patterns, WebAssembly/WASI/Component Model, UMA portable capabilities, runtime contracts, capability graphs, governed MCP/agent orchestration, clean code, code smells, Rust crate/library API architecture, Cargo feature/MSRV/SemVer policy, unsafe/FFI/no_std/library testing, modularity, views, NFR tactics, IAM/auth, security patterns, cost estimation, architecture-as-code fitness functions, ADR/RFC work, and engineering execution plans.
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 designing, reviewing, implementing, or validating UI/UX and frontend experiences for web, mobile, responsive apps, design systems, Figma-to-code handoff, frontend stack/library selection, personas, UX mapping, information architecture, UI patterns, accessibility, interaction design, UX research, usability testing, theme/token application, or XR/spatial interfaces.
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。
指定されたPRを6観点（セキュリティ、ドキュメント乖離、可読性、ライブラリ選定、PR説明、既知脆弱性）でレビューし、人間向け・AI向けの2形式でPRにコメントする。初回レビューおよび修正後の再レビューに使用する。Do NOT use for レビューコメントへの修正適用（pr-comment-fixerを使用すること）。
Dockerfile / Containerfile / compose analysis plus optional Trivy / Grype / Syft composition when those binaries are present. Use when reviewing a Dockerfile PR, gating `docker build`, building an image SBOM, evaluating base-image risk, or auditing a registry image for CVEs.
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。
Terraform / OpenTofu / Nix / k8s manifest misconfiguration detection — open security groups, missing encryption, public S3/GCS, IAM wildcards, plaintext secrets, missing tags. Use when reviewing an IaC PR, gating `terraform apply` / `tofu apply`, auditing existing state for drift, or building a compliance report for cloud configuration.
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。
Static application security testing (SAST) for changed source files — Vulnetix's built-in rule set plus optional Semgrep augmentation when `.semgrep` config is present. Use when reviewing a PR for code-level vulnerabilities, scanning a feature branch before merge, gating CI on critical findings, or running rule-specific checks for a known weakness class.
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 the user wants to design, preview, or customize an Obsidian vault theme — including choosing styles, comparing color schemes, adjusting typography, or generating CSS snippets. Triggers on keywords like "Obsidian theme", "color scheme", "CSS snippet", "appearance".
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。
A six-year-old code reviewer who asks "why?" about everything. Catches over-engineering, confusing names, and unnecessary complexity. Output is a 1-2 line summary of the request as a whole: how is the file? Is the class nice? Is the function correct?
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。
A six-year-old code reviewer who asks "why?" about everything. Catches over-engineering, confusing names, and unnecessary complexity, then corrects the code according to the language spec, but through kids eyes, maintaining simplicity and readability.
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。
A six-year-old code reviewer who asks "why?" about everything. Catches over-engineering, confusing names, and unnecessary complexity. To invoke, say `6yo`.
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。
xp-harness 本体 (skill / agent / instruction / kanban 等) のレビューを進めているときに必ず発火させる skill。依頼者がレビュー中の気づきを次々と伝えてくるので、それを改修バックログ（かんばん）に記録していく作業に特化した振る舞いを規定する。「レビューしている」「気づきを記録」「かんばんに追加」「TODO に追加」「あとは…」「次は…」のような連続入力を受けたときに発火。1 つの気づきへの返答が終わってから次の気づきを受けるリズム。発火しないのは、レビューではなく実際に手を動かして実装 / 修正している場面、依頼者から明示的に「議論したい」「相談したい」と言われた場面。
価値提案（誰に/何のために/なぜ勝てる）をレビューし、曖昧さ・矛盾・証拠不足を洗い出して、メッセージとMVPを磨くために使う。
ego-browser (ego-lite) is a Chromium-based browser that gives AI agents a CLI-accessible Node.js runtime for driving a real browser. Use this skill whenever the user needs to interact with a website opening pages, filling forms, clicking buttons, taking screenshots, extracting page data, testing web apps, logging into sites, automating browser operations, or any other browser automation task. Triggers include requests to "open a website", "visit a URL", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "extract content from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also used for exploratory testing, dogfooding, QA, bug hunting, or reviewing app quality. Prefer ego-browser over any built-in browser automation, web fetch, or other web tools.
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。
Architecture design and governance protocol for system structure, boundaries, contracts, APIs, schemas, migrations, rewrites, and long-lived codebase health. Use when designing or reviewing architecture, planning structural refactors or migrations, governing tech debt, or containing rewrite risk. Keeps the load-bearing spine small, owned, checked, and deletable over time.
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 EU and UK medical-device software, built from six sources captured 2026-10-13: MDCG 2019-11 rev.1 (June 2025), MDCG 2020-6 (April 2020), MDCG 2020-13 (July 2020), MDCG 2020-7 (April 2020), MDCG 2020-8 (April 2020), and the MHRA software-applications guidance (2023-07-01) with its stand-alone software PDF. Use for SaMD qualification and classification, legacy-device clinical evidence, the clinical evaluation assessment report, the PMCF plan, and the PMCF evaluation report, under EU MDCG guidance or UK MHRA guidance. SCOPE LIMITS: EU MDR and UK MHRA device software only; no IEC 62304, ISO 13485, or ISO 14971 text; no MDR or IVDR regulation body text; MDCG guidance is not legally binding; MHRA guidance is UK-specific; synthesized notes, not legal advice. LICENCE: Per-document: European Commission reuse policy (Decision 2011/833/EU, CC BY 4.0, attribution and indication of changes) for the MDCG documents; Open Government Licence v3.0 for the MHRA guidance; reconstructed notes with attribution; official PDFs not redistributed.
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。
Arlo Belshee의 6단계 네이밍 프로세스와 Clean Code 네이밍 규칙을 적용해, 여러 파일에 흩어진 개별 이름 스멜(타입 반복·-er/-Utils·불용어·축약어 등)을 탐지하고 배치 교체하여 코드 가독성 향상. 단, 하나의 긴 메서드를 통째로 관통(grouping→extract→rename)하는 것은 /intent-revealing-names가 적합. /naming-process로 호출.
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。
지역 변수가 서로 얽혀 Extract Method가 불가능한 거대 메서드를 별도 클래스(Method Object)로 추출. "긴 메서드를 클래스로", "지역 변수 때문에 추출 불가", "method object", "/extract-method-object" 요청 시 사용. 단, 지역 변수 얽힘 없이 잘라낼 수 있는 긴 메서드는 /intent-revealing-names(grouping→extract)가 적합. /extract-method-object [commit-ref]로 호출.
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。
간결한 plan을 사용자와 합의한 뒤, feature(use case) 하나를 RGB(Red→Green→Blue) 사이클로 끝까지 자율 구현하는 오케스트레이터. 문제 정의·기능 분해·완료조건(programmer test) 합의까지는 사용자와 피드백을 주고받고(인터랙티브), 합의 후 구현은 그 feature의 모든 test에 대해 Red 전체→Green 전체→Blue 전체 3-phase로 피드백 없이 끝까지 진행하고, feature(use case) 전체를 phase마다 하나씩 최대 3개 커밋(reviewable-commits Why-body 포함)으로 남긴다(자율). superpowers의 장황한 spec/plan 대신 개발에 맞는 간결 포맷을 쓴다. "기능을 TDD로 끝까지 구현", "plan 합의하고 자율 구현", "feature 단위 RGB", "use case TDD로 짜줘", "/tdd-feature" 요청 시 반드시 사용. 후속 "이어서", "다음 feature", "재개", "다시 진행"도 처리. 단, 단일 test의 step-wise(매 단계 피드백) RGB는 /tdd-rgb, plan 문서만 작성하고 끝낼 때는 /tdd-plan이 적합.
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。