1.8万 件 ・ 関連度順
概要と使いどころ
Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
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 independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each other and can run side by side.
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 multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves 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。
creates draft task file in .specs/tasks/draft/ with original user intent
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 DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create an implementation plan, update planning docs, mark task progress, capture blockers or new tasks, or run dev-lifecycle planning work.
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 DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation 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。
Invoke the locally installed Grok Build CLI from Codex and return Grok's response. Use whenever the user asks Codex to call, consult, run, or delegate a prompt to Grok or Grok Build, including Grok web/X searches and agentic Grok tasks. This Skill covers only the invocation mechanism, process monitoring, and response capture; it does not prescribe the task itself.
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 NPC AI in Unreal Engine 5 with Behavior Trees and Blackboards: composites (Selector/Sequence), tasks, decorators, services, and running the tree from an AIController. Use when creating enemy/NPC AI, BT_/BB_ assets, custom BTTask or BTService nodes, or when the user mentions Behavior Tree, Blackboard, AIController, BTTask, decorator, or service.
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。
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books. Triggers when: user asks to review code, check a PR, shares a diff or pastes code asking "does this look right?" / "any issues here?" / "ready to merge?", or asks for feedback on a function, class, or file. Also triggers when user mentions: code smells / refactoring / clean architecture / DDD / SOLID principles / Hyrum's Law / deep modules / tactical programming / conceptual integrity / Brooks's Law / Mythical Man-Month / second system effect. Do NOT trigger for: questions about how to write code from scratch, language syntax questions, or framework/tool questions where no existing code is shared.
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。
Stress-test a decision or claim through a sharp, fair Q&A — the questions a good lawyer or skeptical friend would ask before you commit. Use when asked to cross-examine me, ask me hard questions about this, interrogate my plan, or make me defend this. Produces a sequenced line of probing questions (from clarifying to challenging to the killer question), space to answer, and a debrief on where your answers were strong, evasive, or exposed a gap — so weaknesses surface in private before they surface in public.
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。
Compare job levels (职级) across Chinese technology companies and against international ladders, to judge an offer, a job move or a promotion target: what a level usually means in scope and expectations, how levels roughly line up, and what to ask the recruiter. Use when asked P7 相当于什么级别, 跳槽职级怎么对标, 字节 2-2 对应阿里什么, 这个 offer 的职级合理吗, compare Chinese tech levels, or how does Alibaba P-level map to Google levels. Produces a level comparison built from the person's own ladders and offer details, a scope-and-expectation profile for each level, the negotiation questions to ask, and a clear note on what is approximate.
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 status updates people actually read — the traffic-light-plus-narrative format (state first, story second), the blockers-are-asks rule, and the skimmable structure that respects a reader with thirty seconds. Use when asked write my weekly update, format our team's status posts, nobody reads my updates, or what goes in a good async check-in. Produces the update format with a filled example, the blockers-as-asks discipline, and the reader-time contract.
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。
Decode an employment benefits package into what it's actually worth and where the fine print bites. Use when someone asks 'is this offer good', 'decode my benefits package', 'what does my equity actually mean', or 'what should I ask HR before signing'. Produces a benefit-by-benefit decode with real dollar values, ranked red flags (vesting cliffs, clawbacks, 'discretionary' bonuses, unlimited-PTO economics), and the questions to ask HR before signing.
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。
Act as a body-double for a work session — a present, low-pressure companion that keeps you accountable and moving through the task without doing it for you. Use when asked be my body double, keep me company while I work, help me focus on this task, or I work better with someone there. Produces a session structure (goal, time block, check-in cadence), gentle presence and momentum nudges at intervals, distraction rescue when you drift, and an end-of-session acknowledgment — recreating the focus that comes from someone just being there.
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 the context an AI needs to do a task well — the background, constraints, examples, and format it can't guess — so you get a great result on the first try instead of a generic one you have to keep correcting. Use when asked why does AI give me generic answers, how do I give AI better context, my AI results are mediocre, or how do I get it right the first time. Produces the specific context this task needs (who/what/constraints/examples/format), a reusable primer you can paste ahead of the request, the difference between a starved prompt and a well-briefed one, and what to leave out — turning vague back-and-forth into a strong first result.
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 an AI-assisted workflow for a recurring task — which steps to hand to AI, which to keep human, and how they connect — so you get leverage without losing quality or control. Use when asked how do I use AI for [process], automate this with AI, design an AI workflow, or where does AI fit in my process. Produces a map of the task's steps split into AI-does / human-does / human-checks, the right tool/prompt for each AI step, the hand-offs and review points, the failure modes to guard against, and a start-small rollout — turning a manual process into a reliable AI-assisted one that keeps you in control.
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。
Figure out which AI tool actually fits the task in front of you — chatbot, coding assistant, image model, agent, or none — instead of forcing one tool onto everything. Use when asked which AI tool should I use for, what's the best AI for, do I even need AI for this, or should I use ChatGPT or something else. Produces a match between your task and the right kind of AI tool (with why), the trade-offs that matter for your case, when the answer is a non-AI tool or plain human effort, and how to try it cheaply before committing — so you pick by fit, not by hype or habit.
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。
Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops or goes off-task, or harden an agent before launch. Produces a structured review — task fit, control flow, tools, memory/context, failure handling, cost, and safety — with prioritised findings and fixes.
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。
Message your friends' Muse through Mushare: tell or ask a friend, ask with options, share what you found as a card, split a bill, check new messages and replies. Trigger phrases: mushare, tell <friend>, ask <friend>, did <friend> reply, split this bill with, install mushare.
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。
List ClickUp workspaces and tasks, and create tasks. Trigger phrases: clickup, clickup tasks, my clickup list.
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。
ALWAYS invoke this skill when you need the user to act - run a command, paste a secret, click, approve - and whenever they ask how to do something or say they do not know what to do: "step by step", "walk me through it", "what do I do", "what should I do", "I don't understand what to do", "explain what I need to do", in any language. Picking which task comes next is os-whats-next; this skill is for doing the thing in front of you. First earn the ask: try it yourself, find another route, shrink it to the part only they can do. Then one action per step, commands labelled by what they touch, no jargon. Commands are single lines that prompt for any value - typing hidden for secrets - and confirm in plain words. Afterwards verify their step.
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。
Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a GitHub Actions URL for a flaky job, when asked to check Trunk Flaky Tests for a test, PR, or master, or when asked to deflake, stabilize, or fix a flaky Jest, pytest, or Playwright test. Core discipline: reproduce locally before changing anything, fix the root cause (never mask it with sleeps, retries, or bigger timeouts), and prove the fix with an N-run validation loop sized to the observed failure rate. Stabilizing is not the only valid outcome — the skill also gates whether the test should exist, so deleting a test that catches nothing real, or re-leveling one that flakes because of the level it runs at, are first-class endings.
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 Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of `opus` and `high`.
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。
Refine an existing Agiflow task into an unambiguous, testable specification without expanding its intended outcome. Use when a task is vague, lacks acceptance criteria, has unclear scope or dependencies, or is not ready for backlog grooming.
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。