2,923 件 ・ 関連度順
概要と使いどころ
Use when the diff adds or moves a credential, logs or returns data, builds a URL or argv with a token, generates a random value, encrypts, signs, hashes, configures TLS or writes a credential file
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 diff builds a query, a shell command or argv, a subprocess environment, a template, an XML parse, an eval or a deserialization from data that may be attacker-controlled - SQL/NoSQL, OS command, argument, env-var, template and code injection, XXE, unsafe deserialization
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 diff touches login, password storage, sessions, cookies, JWT verification, OAuth/OIDC or SAML flows, MFA and step-up, passkeys/WebAuthn, account linking and recovery, password reset, webhook signatures, API keys, mTLS identity or headers used to identify a caller
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 diff adds or changes an endpoint, resolver, RPC, job or query that takes an object id, a role check, a request binding or a tenant filter - BOLA/IDOR, function-level authorization, mass assignment and tenant scoping
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 diff changes a GitHub Actions workflow, a reusable action, a CI cache or artifact handoff, a Dockerfile or compose file, Terraform/HCL, Kubernetes manifests or Helm values, an environment overlay, a workload identity binding or a cloud OIDC trust policy - judged only where concretely exploitable
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 or analysing an A/B test, computing power or sample size, testing whether a difference is real, or writing any statistical claim — effect sizes with intervals, SRM checks, multiple comparisons and causal caveats
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 a diff or design adds or changes a DB migration, an endpoint or DTO, an event payload, or a shared type with consumers
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 a task is in code_review - how to read the diff, which findings block, and the verdict move
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 in code_review when the diff touches input handling, auth, queries, files, outbound requests, secrets, dependencies or LLM calls, and in analysis for any new endpoint or data flow
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。
Summarize the current Git working tree and create a straightforward non-interactive commit. Use when Codex is asked to quickly commit the current work, commit everything currently changed, prepare a concise commit message from the diff, or avoid extra confirmation and commit splitting unless there is a real safety issue.
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 a read-only, defect-first review of a specified code change and return every actionable finding. Use when another agent delegates review of uncommitted changes, a base-branch diff, a commit, or custom review instructions.
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。
Prepare for challenging conversations using Prepare-Listen-Empathize-Clarify-Solve framework.
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。
Phase E of a WinForms-to-Avalonia migration: verify behavioral parity against Phase A contracts, record intentional differences, validate supported environments and packaging, and make evidence-based legacy cutover decisions. Use only for an explicit migration when comparing the legacy and Avalonia implementations or when the orchestrator routes here. Do not delete legacy without the cutover checklist and explicit authorization.
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 code review using parallel specialized subagents. If a PR URL is provided, fetches PR details and can post comments. If no PR is provided, reviews the diff between the current branch and its base branch plus any uncommitted changes. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use 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。
Draft professional emails, feedback (SBI/BID), difficult conversations, meeting notes, and escalation templates. Covers tone matrix, cross-cultural communication, Slack/Teams async patterns, and structured notes from raw transcripts.
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。
Browser automation, web scraping, E2E testing, and visual regression with Playwright. Covers 30+ patterns: login flows, form testing, responsive design checks, broken link validation, API mocking, data extraction, PDF generation, accessibility audits (axe-core), performance budgets (Lighthouse), visual diffing, multi-browser testing (Chromium/Firefox/WebKit), mobile emulation, infinite scroll, shadow DOM, iframes, file downloads, auth state reuse, cookie consent handling, WebSocket monitoring, console error detection, HAR export, trace viewer, Docker CI, GitHub Actions, and parallel sharding. Use when user asks to test a website, take screenshots, check responsive design, automate a browser task, scrape data, validate forms, check broken links, test login, audit accessibility, or measure page performance. Do NOT use for unit testing, API-only testing, or static analysis. Requires Node.js 18+.
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 descriptive commit messages by analyzing git diffs. Use when the user asks for help writing commit messages or reviewing staged changes.
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 startups with Paul Graham mindset (pressure, founder-market fit, brutal validation), Dan Koe discipline (monetization, offer, distribution, sales), and Seth Godin principles (differentiation, narrative, smallest viable audience). Triggers on startup idea, business validation, MVP, first customers, revenue model, GTM, product-market fit, "I have an idea".
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 a short motion-graphics video ad — a 15s Facebook/Instagram/TikTok spot — as a rendered MP4. Researches the destination landing page so every on-screen claim matches it, pulls real product imagery off the live site, animates one paused GSAP timeline in a single HTML page, and renders it frame-accurately through Playwright and ffmpeg. Use this whenever the user wants a video ad, promo video, animated ad, "an ad for my product", Meta/TikTok/Reels creative in video form, a 9:16 or 1:1 cut of an existing spot, or a re-render of an earlier ad with a different hook, hero or CTA — including when they never say the words "motion graphics". Not for animating UI inside an app, not for static image ads, and not for long-form or voiceover-led video.
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。
Runs security audits on codebases — full scans, diff reviews, threat models, vulnerability triage, remediation guidance, and finding tracking. Activate when the user says "security scan", "audit this repo", "review this PR for security", "threat model", "triage vulnerabilities", "fix this vuln", or "track findings".
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。
Revenue-Centric Design (RCD) — evidence-backed principles for making a SaaS or startup product convert, retain, and monetize. Use when the user works on a landing page or CRO ("my page isn't converting"), onboarding/activation ("users sign up but don't stick"), churn/retention ("customers keep canceling"), pricing/monetization ("how should I price this"), checkout/forms ("dropdowns kill conversion", "annotated checkout"), dashboards/data viz ("cognitive load", "KPI shortlists"), positioning/ICP/go-to-market, feature scope, A/B-test rigor, or AI-era differentiation — or asks for the behavioral-science mechanism behind a design choice. Also use when another skill needs the principle or evidence behind a conversion/retention/pricing/checkout move. Never apply to gambling, betting, or casino products.
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。
Draft a Guardrails PR from its complete final diff and carry out authorized CI and review follow-up, including stacked PRs and takeovers.
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, expand, and cluster keywords for content strategy. Use when planning content topics, building keyword lists, expanding seed keywords, clustering by topic and intent, or mapping keywords to funnel stages. Triggers on "keyword research," "keyword expansion," "keyword clustering," "content topics," "what to write about," "topic ideation," "content planning," "6 circles method," "seed keywords," "keyword difficulty," "search volume," "intent mapping," "pillar content strategy," or "content calendar planning." For SEO optimization and auditing, see seo-and-aeo-strategy.
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。
Used to invoke the PXMeter tool for rigorous quality assessment of biomolecular structure prediction models (e.g., proteins, nucleic acids, small molecules). This skill covers single-sample CIF evaluations and large-scale dataset benchmarks, providing rich result parsing support. Trigger this skill when the user asks to "run PXMeter", "compare PDB/CIF evaluation results of different tools", "check benchmark scores", or asks "how accurate is the structure generated by the model".
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。