1.8万 件 ・ 関連度順
概要と使いどころ
Use when the plan_ref returned by add-new-feature is provided. Executes the SAM implementation loop — opens an attempt per ready task, dispatches each to a specialist agent in parallel, settles and judges what comes back, manages bookend tasks (T0 baseline capture and TN verification), and tracks concerns and contract violations per task. Drives task state through the work ledger via the SAM CLI.
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 several language models as independent coders on the same labeling or discovery task and reads their disagreement as data — panel assembly for model diversity, keeping votes independent, consensus rules, agreement statistics (Cohen's and Fleiss kappa, Krippendorff's alpha), the correlated-errors caveat that stops agreement being mistaken for validity, human validation beyond the panel, and reporting. Use when the user asks about a council, panel, ensemble, or jury of models, asks how to combine several models' labels, or asks what kappa or alpha to report for model coders. Single-model codebook and validation work goes to text-classification, per-item confidence to llm-calibration-logprobs.
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 raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my prompt", "how to write a prompt for", "help me prompt", "rewrite this prompt", or explicitly asks to enhance prompt quality. Also triggers on Chinese equivalents: "优化prompt", "改进prompt", "怎么写prompt", "帮我优化这个指令". DO NOT TRIGGER when: user wants the task executed directly, or says "just do it" / "直接做". DO NOT TRIGGER when user says "优化代码", "优化性能", "optimize performance", "optimize this code" — those are refactoring/performance tasks, not prompt optimization.
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。
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and generates summary reports. Never executes tasks directly. Triggers on keywords: orchestrate, manage agents, spawn agents, parallel tasks, coordinate agents, multi-agent, orc, delegate tasks
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 marketing agencies — including branding, content marketing, PPC/paid media, social media, email marketing, performance/demand-gen, video production, and full-service digital agencies. Triggers on requests like "shortlist three B2B branding agencies in California", "find a PPC shop with ecommerce experience", "we need a content marketing partner for a SaaS launch", or "pull contact info for these 12 agency domains", even when the need is described indirectly. Drives the ServiceGraph API (api.servicegraph.co) — a 100k+ US firm catalog filterable by industry, services, location, size, ratings, and third-party listings. Skip SEO-only asks (use find-seo-agency), web/software-development asks (use find-web-developer or find-software-developer), recruiting an in-house marketing hire, "write me a marketing plan" do-the-work asks, non-US firms, individual freelancers, marketing-software-product recommendations, and consumer/personal-brand asks.
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 or set unique task id <id>. Use when user requests to work on a certain task or wants to know what the current task is.
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。
Dissect the current or given task plan, treated as an epic, domain-wise and logically into cohesive parts and materialize each part as its own separate task plan. Use when the user calls to "dissect", "split", "break up", or "decompose" a large "task" or "plan".
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。
Iteratively edit and refine a named plan for a task through a conversational loop. Each round, the current plan is shown and the user is asked whether to keep refining, mark the plan as done, or proceed to the implementation or draft. Use when the user wants to plan a task purely through chat-driven refinement.
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。
Protocol for task synchronization, context handoff, and cross-session coordination using Claude Code task tools. Ensures agents properly update tasks with findings and enables seamless work continuation.
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 4 of 5 — implements tasks from TASKS-<N>-<slug>.md (with ARCH-<N>-<slug>.md as architecture-only context) using mode-appropriate verification (tdd, test-after, ui, checklist); pass 'auto' to run without stepping. Use only when the user asks to run Phase 4 or implement tasks from an ARCH doc — never trigger automatically from a coding 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。
AWS の構成図を draw.io の XML（.drawio）で描く。公式の AWS4 アイコンを使い、タイトルや凡例や番号バッジのような装飾を足さず、どのサービスがどこにあって何とつながっているかだけで読める図にする。AWS 構成図、アーキテクチャ図、インフラ構成図、ネットワーク構成図、VPC の図を描いてほしいとき、draw.io で AWS の図を作りたいとき、既存の構成図を直したいときは必ずこの Skill を使う。Use this whenever the user asks for an AWS architecture diagram, cloud infrastructure diagram, VPC diagram, or a draw.io file of AWS resources, even if they don't say "draw.io". Mermaid、PlantUML、Python の diagrams ライブラリなど、ほかの形式を指定されたときは使わない。Do not use it when the user explicitly asks for Mermaid, PlantUML, or the Python diagrams library.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
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。
This skill should be used when the user asks to "create a team", "spawn agents", "parallel execution", "delegate tasks to agents", "use a swarm", "team workflow", "split work across agents", "run tasks in parallel", or mentions wanting multiple agents to collaborate on a complex task.
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 meta-cognitive meditation for observing reasoning patterns, clearing context noise, and developing single-pointed task focus. Maps shamatha to task concentration, vipassana to reasoning pattern observation, and distraction handling to scope-creep and assumption management. Use when transitioning between unrelated tasks, when reasoning feels scattered or jumpy, before a task requiring deep sustained attention, after a difficult interaction that may color subsequent work, or when reasoning feels biased by assumptions rather than evidence.
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。
Track and execute implementation work using Mighty (mt) tasks, with progress comments, linked evidence, recorded decisions, and clean closeout. Use when asked to fix a bug, implement a feature/refactor, or “work through” changes in code while keeping Mighty tasks/specs/decisions updated.
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。
Optimize ChatGPT Voice in the Codex desktop app into an ear-first control plane for free-form task coordination and opt-in workflows. Apply spoken synthesis, routing-only coordination, owning-task role contracts, project placement, explicit authority, safe speech, current-state verification, honest recovery, and the optional Slopware Dev Stack: MSL, MSW, CODER Loop, and Timebox. Load named workflows only when invoked: Freeway for parallel lanes, Decision Walkthrough for read-only authority convergence, and Tutorial for teaching-first onboarding. Use when the user invokes the voice optimizer, coordinates Codex work through voice, assigns the current voice task as coordinator, runs Freeway, starts a decision walkthrough, learns voice orchestration, routes development through CODER, authorizes Timebox, or asks CVO to install or use Slopware companions.
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, test, run, lint, format, and manage dependencies for Haskell projects using the hx toolchain CLI. Use whenever working in a Haskell project that has an hx.toml (or when setting one up), or when the user asks to build/test/run/typecheck Haskell code, manage GHC/Cabal versions, or add/remove Hackage dependencies.
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。
Pitfalls, examples, and edge cases for workers executing a Surogates subagent task. Loaded automatically when the dispatcher spawns a session bound to a Task (Session.task_id is set).
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。
Walks you through pairing your phone with Cowork and sending your first remote task — so you can control your desktop from anywhere. For deploying tasks while commuting or in meetings, when setting up mobile-to-desktop control for the first time, or during a Cowork Max feature exploration session. Use when the user says "dispatch", "control cowork from phone", "remote task", "phone to desktop", "try dispatch", "can I use cowork from my phone", or "send cowork a task while I am away".
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。
Shows you how to use Cowork's parallel workers to run multiple tasks at the same time instead of one after another — dramatically cutting the time on batch work. For processing large batches of files or research tasks, when running multiple independent analyses simultaneously, or during a performance optimization session. Use when the user says "speed up", "parallel workers", "batch task", "process multiple files", "why is cowork so slow", "faster", "do several things at once", or "can cowork multitask".
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。
Teaches you how to delegate tasks to Cowork so clearly that you get exactly what you asked for — every time. Use when learning how to give better instructions, for improving your delegation technique, during early Cowork adoption when results feel off, when writing clearer task descriptions, or when the user says "how do I ask cowork to do things", "delegation tips", "better instructions", "cowork isn't doing what I want", "help me delegate", "my results are bad", "how do I give better prompts", "cowork keeps getting it wrong", "I don't know how to use this", or "how do I get good results".
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 AI agent tasks on a Volcengine (火山引擎) cloud phone via the Mobile Use Agent OpenAPI. Use when the user asks to drive, automate, operate, or test an Android app on a cloud phone for enterprise use cases (e.g. reply to WeCom customer messages, add leads in a CRM, clock in on DingTalk, check invoicing stats, query inventory in a supply-chain app, ship e-commerce orders, approve OA requests) or personal ones (open 小红书 and search, place an order, check nearby places on a map), or to check status, fetch result, cancel, or list a Mobile Use run. Requires one-time setup to store Volcengine AK/SK locally; ProductId and PodId can be saved as a default device during setup, the user prompt is provided per run. Supports optional GPS injection (GpsInfo) with user consent (auto-asked only for location-related tasks).
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。
This skill should be used when the user asks to "generate tasks", "create implementation plan", "break down feature", "write agent prompts", "decompose into tasks", "create work items", or when creating agent-ready task descriptions from PRD and SDD documents.
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。
Deprecated redirect skill that routes legacy 'content creator' requests to the correct specialist. Use when a user invokes 'content creator', asks to write a blog post, article, guide, or brand voice analysis (routes to content-production), or asks to plan content, build a topic cluster, or create a content calendar (routes to content-strategy). Does not handle requests directly identifies user intent and redirects to content-production for writing/SEO/brand-voice tasks or content-strategy for planning tasks.
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。