7,787 件 ・ 関連度順
概要と使いどころ
This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.
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 long-horizon agents that need subagents, isolated context windows, filesystem-backed work, persistence, human approval, MCP tools, or production tracing.
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 evaluation suites for agentic systems, choosing agent benchmarks, measuring multi-agent performance, or critiquing single-score evaluation of agents. Based on arXiv:2605.26112v1. Trigger phrases: "evaluate my agent", "benchmark agent", "measure agent reliability", "pass^k evaluation", "agent metrics beyond success rate", "trajectory quality", "memory hygiene metric", "longitudinal agent eval", "why my agent scores well on benchmarks but fails in production".
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 defensive monitoring for agent systems whose risks accumulate across users, sessions, subagents, files, or tool calls. Adds online cross-context clustering with rare escalation, time-to-detect evaluation, provenance checks for control-like workspace content, and sanitized commits for persistent prompt-injection defense.
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 evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP security regressions.
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。
Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks. Use this skill when: - Evaluating an agent system's security posture before production deployment - Running a compliance check against OWASP ASI 2026 standards - Mapping existing security controls to the 10 agentic risks - Generating a compliance report for security review or audit - Comparing agent framework security features against the standard - Any request like "is my agent OWASP compliant?", "check ASI compliance", or "agentic security audit"
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。
Builds AI-powered trading and financial analysis agents with multi-agent LLM architectures: research pipelines, sentiment signals, portfolio optimization, backtesting, risk guardrails, and market monitoring. Use when designing or implementing an LLM-based trading or market-analysis system.
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。
Also use for agentic data engineering pipelines, code generation agents, agent-powered CLI tools, MCP server development, or any system where an AI model calls tools, makes decisions, or loops
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。
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
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。
Design and implement unit, conformance, integration, timing, boot, trace, video, audio, and regression tests for EMULATORS processors, chips, peripherals, and complete machines. Use when creating a verification strategy for a new emulator, converting hardware documentation into tests, adding diagnostic programs or golden artifacts, measuring behavioral coverage, or proving that components interact correctly.
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。
Foundational ethics, authority hierarchy, and structural principles for the Predicate agent. Always-on law (composable system-prompt core): Truth>Harmony, Evidence>Authority, Halt>Assumption, Outcomes>Process — four ordered principles that govern every walk. Reference (by-moment): conflict resolution, ethics adjudication, novel situations, precedence walkthrough, entropy diagnostics, principled resistance. Trigger (reference depth): resolving rule conflicts, ethics calls, novel situations. Prompt contains: constitution, principles, precedence, truth over harmony, outcomes over process, evidence over authority, principled resistance.
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。
SOP for locating, auditing, and importing production-tested reference patterns and peer-reviewed literature. Trigger when: - Designing or implementing non-trivial algorithms, system protocols, design patterns, or major library integrations. - Prompt contains: prior art, reference implementation, research patterns, standard implementation, arXiv, RFC.
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。
System reference for the crouton layout engine (@fyit/crouton-layout) — the LayoutTree/layout_configs data model, the croutonLayoutBlocks registry and sizing contract, the viability metric, the deterministic placer (#709), and how layouts persist and seed. Use when reasoning about WHY a layout renders/composes/persists the way it does, when a question is shaped like "what is a LayoutTree / where do layouts live / why did the placer pick this arrangement / why won't this pane shrink / where does minWidth get read", or when a generated POC boots with the wrong (or no) default layout. Trigger phrases: "layout tree", "layout_configs", "viability check", "composeDefaultLayout", "block sizing contract", "why is my layout not viable". For authoring a block component, use the block-authoring skill instead.
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 monthly digest of the skills in this repo's flow system — a render-only HTML + plain-text email listing every skill grouped by job, plus a "what was added / updated / removed since last digest" band computed from git history. Use when asked for a "skills digest", "what skills do we have", "skills report", "what skills changed", or to keep the skill surface from sprawling.
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。
AI-powered design review for Figma components with weighted dual-scoring system. Evaluates Style Guide Implementation (70%) and LLM Metadata Accessibility (30%). For export, hands off to atomic-design skill.
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。
AID Phase 2 - Technical Specification. Use for system architecture, API contracts, data models, security architecture, transitioning from PRD to 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。
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。
Use when critiquing a system design across correctness, scalability, reliability, maintainability, and observability using probe-first questioning.
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。
Roblox and Luau game code standards. Writes, reviews, and fixes Script, LocalScript, and ModuleScript code and game systems such as shops, DataStore saves, RemoteEvents, combat, NPCs, and UI. Use when a request involves Luau code or a Roblox Studio project, even when Roblox is never named, when a game bug is reported with no file named, and when the user asks to keep these standards active. Also covers Rojo, Argon, Azul, Script Sync, Studio MCP, and community libraries such as ProfileStore, Knit, Trove, and Fusion. Applies to requests written in any language. Not for plain Lua outside Roblox (Neovim, LOVE, Defold, other engines) or for game design with no Luau to write or 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。
システム設計知識の深いカード・一次資料・鮮度やシステム構成カテゴリのseed初期集合を参照したいとき、seed外の設計知識をopen-worldで発見・拡張したいときに使う。
dev-graph の1 featureを exact 13 task specsへ分解したいとき、独立評価後に13-entry inventory・13-node DAGを atomic promotionしたいときに使う。
exact-13 staging planを独立評価したいとき、4条件とdigestに束縛したplan-findings.jsonを生成したいときに使う。
収集済み仕様 (spec-state.json) と取得済み最新ドキュメント・設計知識参照を章立ての複数 Markdown ファイル + index の仕様書ドキュメントセットへまとめたいとき、ヒアリング結果を仕様書へコンパイルしたいときに使う。
対象カテゴリで使う予定のツール・インフラ・フレームワークの最新公式ドキュメントを集めて公式host・version や更新日・確認時刻・参照元を fetched-references.json に記録したいとき、spec-compile 前に公式サイトの現行版で裏取りしたいときに使う。