4,960 件 ・ 関連度順
概要と使いどころ
Verify one falsifiable factual claim against evidence appropriate to the claim. Use when a concrete assertion about software, documentation, configuration, releases, or repository behavior must be classified as VERIFIED, REFUTED, or INCONCLUSIVE.
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 PLAN artifact from SAM Stage 2 needs contextualization against actual codebase state — grounds the design plan in reality by performing scope analysis (NEW/MODIFY/COMPLETE classification), conflict detection between plan assumptions and codebase patterns, and resource mapping to concrete file paths and integration points. Produces an updated ARTIFACT:PLAN registered via MCP with a Contextualization section appended.
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。
Executes SAM Stage 5 — opens an attempt on a single ARTIFACT:TASK, dispatches it to a fresh stateless agent session, runs quality gates, and records an ARTIFACT:EXECUTION with implementation results and verification output on the task. Use when Stage 4 Task Decomposition is complete and tasks are ready for execution, when re-executing a task after Stage 6 returns NEEDS_WORK, or when dispatching a task to a language-appropriate specialist agent via the development harness pipeline.
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 Chain of Verification (CoVe) prompt design — a 4-step pattern separating generation from independent factual verification. Use when designing prompts that require factual accuracy, reducing hallucinations, checking technical standards or APIs, or producing step-by-step procedures where subtle errors are costly.
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 extracting specific data points from large agent output transcripts, kaizen analysis reports, or JSONL session files — tool timings, query counts, error summaries, or any structured facts — without loading raw data into orchestrator context. Activates when the orchestrator needs targeted facts from large files and context pollution must be avoided.
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。
Fact-check manuscript claims against their cited sources in a per-source Markdown knowledge base. Use to audit claim support, overclaiming, direction, scope, and misattribution after source intake is complete.
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。
Codified expertise for production scheduling, job sequencing, line balancing, changeover optimization, and bottleneck resolution in discrete and batch manufacturing. Informed by production schedulers with 15+ years experience. Includes TOC/drum-buffer-rope, SMED, OEE analysis, disruption response frameworks, and ERP/MES interaction patterns. Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines.
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。
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
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。
Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when: (1) Backend/logic implementation, (2) Algorithm design and optimization, (3) Bug analysis and debugging, (4) API/database code generation, (5) Code quality review and refactoring. Triggers: "implement algorithm", "debug", "analyze code", "backend task", "API implementation", "optimize performance", "refactor", "generate prototype", "code review". IMPORTANT: Default sandbox="read-only" (analysis/review/patch generation); use sandbox="workspace-write" only when codex must run tests/builds to verify. Always request unified diff patches only. Supports multi-turn sessions via SESSION_ID.
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。
Classifies raw pilot request → structured JSON {task_type, class, artifact, budget_estimate, confidence, routing_tag, resolution_path, schema_version, result_type, expected_result_kind, result_kind_resolution, hypothesis_relation}. Keyword-fast (<200ms) or Haiku fallback (<60s). Does NOT create WP or call executor.
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。
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
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 whenever the user wants to find, shortlist, vet, or enrich US engineering firms — civil, structural, MEP, mechanical, electrical, geotechnical, transportation, environmental, and manufacturing. **For real-world engineering (buildings, infrastructure, manufacturing) — NOT software engineering.** Triggers on "find civil engineering firms in Florida for transportation", "shortlist three structural engineering firms with high-rise experience", "MEP consultancy for a hospital project", or "pull contact info for these 12 engineering firm domains", even when described indirectly (PE-stamped drawings, building-permit review). Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings. Defer software-dev / "engineering team" / SaaS-architecture asks to find-software-developer. Skip in-house engineering-manager hires, DIY questions, software-product comparisons (Revit, AutoCAD), non-US firms, individual freelancers.
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。
Import information from foreign sources into a set of artifact kinds (the target), generating or updating them to reflect the imported information. Use when the user wants to "import", "ingest", or "bring in" external sources like files, URLs, or pasted text into artifacts like SPEC, CODE, DOCS, TASK, INFR, or OTHR.
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, revises, restyles, and critiques deliberate, editable Feishu / Lark whiteboards from content, references, existing SVGs, or live boards. Use for whiteboards, infographics, diagrams, system maps, timelines, decision boards, posters, and visual explainers that need factual fidelity, strong hierarchy, intentional composition, and evidence-based review rather than a generic grid of equal cards. Routes creation, revision, and critique through separate playbooks; commits to a content-and-design contract before drawing; validates deterministic SVG defects; renders and inspects the actual artifact; and uses an independent final reviewer for material deliveries.
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 link into a papercut reel script. Researches a sourced facts list, writes the 75-95 word script on the 10-beat spine, a banner fact track, a staging table with one set per banner, and the humour pass. Use for "write the script", "research this repo for a reel".
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。
Inspect and manually purge the Soniox artifacts — transcriptions and uploaded audio files — that offline transcription leaves behind, on dev or prod. Use when offline transcription silently stops working, when Soniox answers 429 `limit_exceeded`, when `SonioxTranscriberTest.OfflineTranscribeWorks` and `CleanerDeletesEnqueuedArtifacts` fail together, or when the user says "sweep Soniox", "soniox/sonoix sweep", "sonoix swipe", "purge Soniox", "check Soniox files", or "is Soniox at the cap".
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。
Convert deep research output (Claude Research, ChatGPT Deep Research, Gemini, Codex — any long-form MD/Word/text) into a consulting-quality HTML report: pyramid structure, numbers promoted to KPIs/charts, comparisons turned into framework tables, citations preserved. Use when the user provides research/investigation results and says レポートにして/HTMLにまとめて/資料にして/きれいにして, mentions ディープリサーチの結果/調査結果/リサーチ結果, or asks to research a topic AND deliver a report. NEVER invents numbers or facts not present in the source (盛らない原則).
Design system that makes HTML output look like a professional consulting deliverable instead of default AI styling. Use WHENEVER generating any HTML document — report, analysis memo, proposal, research summary, dashboard, artifact — and when the user says 「HTMLで資料」「HTMLでまとめて」「レポートにして」「コンサル風に」「資料っぽく」「デザインがダサい」 or asks to restyle existing AI-generated HTML. Replaces boxes, borders, gradients, emoji and rainbow colors with whitespace-driven, typography-first, print-ready (A4) design.
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Linux credential artifacts, service tokens, SSH material, cloud and container secrets, socket-level trust, and host-to-host pivot chains. Use when the user asks to trace Linux auth artifacts, accepted token or key replay, socket or service-account trust edges, sudo or capability abuse, or explain lateral movement across Linux challenge nodes. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
日本語の概要は準備中です。原文の説明を表示しています。
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for LSASS-resident secrets, Windows logon sessions, Kerberos ticket caches, DPAPI-backed material, SSP artifacts, and replayable credential extraction. Use when the user asks to inspect LSASS memory, recover tickets or logon sessions, trace DPAPI or SSP material, distinguish which credential artifacts are replayable, or connect host-resident credential material to an accepted pivot or privilege edge. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.
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。
Self-learning SEO content pipeline: dashboard, multi-agent queue, token budgets, research → write → audit → publish. StoryBrand/Cialdini/JTBD-style frameworks; config-driven. Use for content factory, batch articles, or scaled publishing.
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。
Score deep research agents on benchmark tasks using factual verification, report-quality scoring, and process evaluation before model or workflow changes ship.
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。
Lets agents operate Google NotebookLM/Gemini Notebook through a Python API, CLI, skill, MCP server, or REST server to create notebooks, add sources, ask cited questions, generate artifacts, and download exports.
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 Bats-core when an agent needs to turn fragile shell scripts or command-line workflows into something it can verify repeatedly after edits. The agent writes focused Bash tests for success paths, failure paths, and output contracts, then runs them locally or in CI before a refactor, release, or incident fix goes out.
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。