4,007 件 ・ 関連度順
概要と使いどころ
"Calculate text similarity using lexical and semantic methods for matching and deduplication. Use this skill when the user needs to find similar documents, detect near-duplicates, or measure semantic closeness between texts — even if they say 'how similar are these texts', 'find duplicates', or 'semantic matching'.".
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 SQL queries against psql, BigQuery, or MySQL from the terminal, including natural-language-to-SQL and schema exploration. Use when analyzing data, inspecting DB state, or debugging tables. Trigger on "query the database", "SQL", "show me data from", "explore table".
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。
Stack-specific security implementation guidance (backend, frontend, database, infrastructure, operations) with auto-detection from your changes. Use when implementing a feature securely or hardening code as you write it. Trigger on "how do I secure this", "security best practices", "is this secure", "harden this". For scanning existing code use /security-verify.
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 and maintain a rolling financial forecast using a 12–18 month horizon. Lock actuals, reforecast remaining periods, extend the planning window, and generate a waterfall bridge showing prior-to-new variance. Use monthly or quarterly when the organization follows a continuous planning cadence instead of annual budgets.
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。
Identify and exploit HTTP Request Smuggling (HTTP Desync) vulnerabilities caused by discrepancies in how front-end proxies (load balancers, CDNs) and back-end servers parse the Content-Length and Transfer-Encoding headers. Use this to bypass security controls, hijack user sessions, and poison web caches.
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。
How every delivered app ships and stays up — Cloudflare-first hosting, prod-only (no staging), the deploy→prod-verify loop, atomic deploy + rollback.
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 1 of the Gaia evidence verification pipeline. Use this skill whenever you need to gather, consolidate, or refresh raw evidence for named skills in the registry. Trigger phrases: "collect evidence", "populate the data lake", "gather sources", "run ev-collection", "Phase 1", "compile the evidence index", "refresh the unified lake", "aggregate skill evidence", "build the evidence database". Also invoke as the first step before running ev-star-verification, ev-adversarial-audit, or ev-link-validation — nothing downstream is meaningful without a fresh, compiled index. Covers GitHub repo links, stargazer signals, YouTube showcases, arXiv papers, peer reviews, benchmark results, blog/newsletter posts, and self-attestation 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。
Generate a prioritized review queue of registry skills and catalog items that need attention. Use this skill whenever someone asks: "what needs review?", "what's overdue for audit?", "where are the weak spots in the registry?", "what should I audit next?", "run a health check on the registry", "show me flagged skills", "find problems in the registry", "what skills need fixing?", or "triage the registry". This is the triage layer — it surfaces candidates ranked P0–P4 so that focused work (via /gaia-audit) targets the right things first. Run this before any audit pass. Also invoke proactively when a PR changes registry/named/ at scale, or before a release, to catch regressions early.
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。
Put one question to several models at once — you, OpenAI Codex, and a cheap third via OpenCode — and show all the answers side by side. No judging, no consensus: three opinions, the user picks. Use for "ask everyone", "what do the other models think", "second opinion", "multi ask", or any open question where one model's answer is not enough.
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 be taught an Anthropic product or feature - "teach me Claude Code", "learn Cowork", "academy lesson", "train me on MCP or the Claude API", "quiz me", "next lesson" - or asks for structured learning rather than a one-off answer. Covers Claude Code, Claude.ai, Cowork, Tag, Platform/API, and AI Fluency. Do NOT use for auditing how the user already works (use academy-review) or for mid-task help where the user just wants their task done.
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。
Analyzes position-independent code and shellcode by identifying GetPC/PEB-walk techniques, API-hash resolution loops, and relocation-free addressing so the payload can be disassembled at the right base. Activates for requests to analyze position-independent code, identify PIC techniques, or understand how shellcode resolves APIs without imports.
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 a moment of friction — a conflicting PR, a wedged runner, a mysterious red check, a repeated manual chore — into a durable, actionable report. Sizes up the scenario, captures the evidence, separates one-off from SYSTEMIC, proposes a fix, and routes it (fix now, or hand off). Reports are LIVING documents that the fixing agent updates with the outcome. Invoke whenever something feels like it shouldn't have been this hard, or when the same annoyance shows up twice.
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。
Architect persistent, searchable memory for agents — episodic, semantic, and procedural stores with retrieval, consolidation, and forgetting policies. Use when designing how an agent remembers across 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。
Build streaming AI user interfaces with AI SDK patterns — message rendering, tool-call displays, loading states, and optimistic updates. Use when creating chat UIs that stream model output and show agent activity.
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 needs the judgment of an Energy Engineer working on building and industrial energy efficiency — running an ASHRAE Level 1/2/3 energy audit, calculating envelope heat loss/gain with the degree-day method, comparing HVAC equipment on SEER/EER/IEER/COP rather than nameplate alone, designing an IPMVP measurement and verification (M&V) plan, or ranking energy conservation measures (ECMs) by savings-to-investment ratio for a capital plan. Distinct from a wind-energy-engineer or solar/PV engineer (own generation-asset design and yield) and from an electrical-engineer (owns utility-scale power delivery and protection) — this role owns the demand side: how much energy a building or process actually needs, and which retrofit reduces that number with numbers that hold up after the fact.
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 needs the judgment of a Construction Trades Supervisor (foreman) — allocating a crew's daily task assignments against a labor-unit budget, deciding whether today's scope requires a formally designated OSHA competent person, arbitrating a trade-sequencing conflict between crews needing the same physical space, tracking crew productivity variance before it shows up on the master schedule, or logging and acting on a near-miss.
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。
Explains complex code through clear narratives, visual diagrams, and step-by-step breakdowns. Use when user asks to explain code, understand algorithms, analyze design patterns, wants code walkthroughs, or mentions "explain this code", "how does this work", "code breakdown", or "understand this function".
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 SERP for a keyword using Ahrefs live data: ranking pages, DR scores, traffic estimates, and content angle analysis. Use when user says "SERP analysis", "who ranks for", "SERP breakdown", "competitors ranking for keyword", "serp overview", "what's ranking for", "show me the SERP for", or "SERP competition for".
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。
Get Ahrefs domain overview: Domain Rating, total backlinks, referring domains, organic keywords, estimated monthly traffic, and traffic value. Use when user says "Ahrefs overview", "domain rating", "DR score", "check backlinks", "how strong is this domain", "domain authority", or "check domain in Ahrefs".
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 branded vs non-branded traffic split using Google Search Console data. Shows what percentage of organic clicks come from brand name searches vs generic queries. Requires user to confirm brand terms before analysis. Use when user says "brand vs nonbrand", "branded traffic", "brand queries", "non-brand traffic", or "branded vs generic".
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。
Discover, search, and manage Spotify music, audiobooks, podcasts, and playlists, including deleting shows or episodes you created with Save to Spotify.
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。
Qualify a sales opportunity using the MEDDIC framework. Use when the user says "qualify this deal", "is this deal real", "MEDDIC qualification", "MEDDICC framework", "should I pursue this opportunity", "deal review", "how qualified is this prospect", "pipeline review prep", "forecast this deal", "sanity check on this opportunity", or wants to assess whether a sales opportunity is worth pursuing and at what pipeline stage.
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 a blameless postmortem after an incident. Use when the user says "postmortem", "post-incident review", "PIR", "what happened in that incident", "incident review", "blameless postmortem", "5 whys", "how do we prevent this again", or needs to document learnings from a production incident - even if they don't explicitly say "postmortem".
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。
Structure and run effective 1:1 meetings with direct reports using Camille Fournier's Manager's Path and Andy Grove's High Output Management frameworks. Use when a manager says "help me structure my 1:1s", "my 1:1s feel like status updates", "I don't know what to talk about in 1:1s", "my reports don't open up", "how do I make 1:1s useful", "what questions should I ask in 1:1s", or "I need a 1:1 template". Also trigger when someone mentions their 1:1s feel transactional, that they keep canceling them, or that they're not sure if their report is happy.
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。