702 skills · sorted by relevance
Agentツール（subagent）と相談するスキル。 ユーザーが「subagentと相談して」「subagentに聞いて」「subagentにレビューしてもらって」と言った時に使用する。 現在の会話コンテキストに基づいてsubagentにプロンプトを送り、結果を要約して報告する。
The English summary is being prepared. Showing the original description.
Design specialized assistants that work with their own separate context. Define responsibilities, delegation conditions, working steps, and report formats for reusable subagents handling verification, debugging, security audits, or code reviews.
Claude Code の SubAgent（agents/*.md）を正しく定義するためのベストプラクティスガイド。 YAML frontmatter、ツール選択、3-Phase 構造、コンテキスト受け渡し、アンチパターンを網羅。 Use when: agents/*.md を書く、SubAgent 定義を改善する、エージェントの動作が想定外、 コンテキストが渡らない、ツール選択に迷う。 Triggers: "subagent", "agent definition", "agents/*.md", "エージェント定義", "サブエージェント", "3-Phase", "context passing", "コンテキスト渡し", "tool selection", "ツール選択", "subagent_type", "bypassPermissions"
The English summary is being prepared. Showing the original description.
Run a task iteratively over a user-specified duration by dispatching subagents. The orchestrator stays strictly linear and time-checked, but each iteration fans out MULTIPLE subagents in parallel over independent units (and those subagents may fan out further). Shared state — a compact progress digest and a growing environment cheatsheet — lives on disk and is passed to every subagent BY REFERENCE, killing the per-subagent rediscovery tax. Every subagent first reads an initialiser preamble that points it at that shared state and makes it write findings back, so the cheatsheet populates itself; role prompts are produced ONCE on the filesystem by a single scaffold command and dispatched by path, never re-typed per dispatch. Subagents persist their results to disk and return only a tiny status, so the orchestrator's context stays small and lasts. The orchestrator classifies the goal as FINITE or OPEN-ENDED: finite lists may finish early; open-ended goals use the full duration, never idle, never manufacture busywork. Use when the user gives a task and a duration and wants it ground out iteratively by subagents over that time.
The English summary is being prepared. Showing the original description.
Guide for defining and using Claude subagents effectively. Use when (1) creating new subagent types, (2) learning how to delegate work to specialized subagents, (3) improving subagent delegation prompts, (4) understanding subagent orchestration patterns, or (5) debugging ineffective subagent usage.
The English summary is being prepared. Showing the original description.
Create specialized assistants for Cursor that work with their own context, separate from the main conversation. Define responsibilities, instructions, output formats, model choices, and execution settings for reusable workflows such as verification, debugging, and documentation.
原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。 Trigger: 「subagent 委譲」「genshijin-crew 使用」「investigator/builder/reviewer 起動」「コンテキスト節約」「圧縮 agent 出力」。
The English summary is being prepared. Showing the original description.
subagentに作業を任せる指揮役の心得。報告の確かめ方、進み具合の持ち方、止まったsubagentの扱い、利用上限との付き合い方を定める。 作業の単位ごとにsubagentを起動し、長い作業を指揮する時に読み込む。
The English summary is being prepared. Showing the original description.
スキルの新規作成・更新を支援するガイド。AIの能力を拡張するスキルパッケージの設計・実装・配布までをカバーする。SkillとSubAgentのどちらが適切かを判断し、SubAgentが適切な場合は subagent-creator へ誘導する。「スキルを作成して」「これをスキル化して」「新しいスキルを作りたい」「スキルを更新して」などのリクエスト時に使用。
The English summary is being prepared. Showing the original description.
Helps decide whether to handle a task directly, create a subagent, or route it to an agent already familiar with the work. The choice depends on required background knowledge and whether plausible but incorrect results can be checked.
Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via their host's skill loader. The orchestrator may also invoke this skill to understand the brief shape its dispatched subagents expect + what they're required to emit -- useful when writing briefs or debugging a subagent's behavior.
The English summary is being prepared. Showing the original description.
Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.
The English summary is being prepared. Showing the original description.
SubAgent（エージェント定義ファイル）を対話形式で作成するためのガイド。SubAgentの設計・description設計・システムプロンプト作成・ファイル生成までの手順を提供する。Skillの方が適切な場合は判断して適切に誘導する。
The English summary is being prepared. Showing the original description.
Gather relevant code and background for subagents, agents assigned part of a larger task. Search broadly, assess each file, identify missing information, and refine the search for up to three cycles to assemble context for bug fixes or feature work.
公司金融实证研究的"漏斗式选题查找器"。互动开场先后询问 (1) 研究方向、(2) 候选标题数量 N， 再扫描全球文献（已出版英文学术期刊 + SSRN working paper + 全球高校 department seminar 1 年内日程），基于 Edmans (2024) "1000 Rejections" 红线生成 N 个候选标题，**通过并行 subagent（Agent 工具）批量生成计划书 + 查新；每个 subagent 必须强制调用 Skill 工具加载 econfin-proposal 与 novelty-check 两个预设 skill 完成各自模块**，**只有当 novelty score >= 9 时（即 JF/JFE/RFS 顶刊层次），subagent 才把 proposal + 查新报告合并的 md 写入 F:\Dropbox\CC\选题大全\<研究方向短名>\（以"简短选题名称-分数"命名，子文件夹名由 Step 0 从用户输入的研究方向派生）；< 9 分的选题在 subagent 内部直接丢弃，绝不写盘、绝不输出**。当用户说"找选题"、"帮我找选题"、"想做 X 方向"、 "empirical CF idea search"、"批量生成研究计划书"、"100 ideas"、"econfin-idea-finder" 时触发。
The English summary is being prepared. Showing the original description.
Create production-grade agent .md files aligned with the current Anthropic subagent contract. Also validates existing agents against the marketplace compliance rules. Use when building custom subagents, reviewing agent quality, or creating parallel agent architectures for orchestrator skills. Trigger with "/agent-creator", "create an agent", "build a subagent", or "validate my agent". Make sure to use this skill whenever creating agents/*.md files for plugins or standalone use.
The English summary is being prepared. Showing the original description.
Chooses how to launch subagents from Claude Code (the Agent tool, a Workflow script, or headless claude -p children) and runs a headless fan-out from one background command. Use for "fan this out to 50 agents", "run these tasks in parallel", "launch subagents for each file", "should I spawn agents or write a workflow", "batch this through Haiku", "run claude -p in parallel", "dispatch a task list without the launches eating my context", or before any launch of more than a handful of subagents, where the launching itself is the cost. Covers the parent-turn cost of each mechanism, concurrency ceilings, what context and tools each child gets, effort control, output contracts, a cost ledger, and resume after interruption.
The English summary is being prepared. Showing the original description.
xp-harness の skill / subagent / instruction が意図どおり振る舞えているか (発火するか・あるべき振る舞いができているか) を transcript で事実確認する手順。skill / subagent / instruction を改修した後に動作検証したいとき、または本番の実運用セッションを「あるべき振る舞い」に照らして分析したいとき、「検証したい」「発火するか確かめたい」「このセッションを分析したい」と言われたときに発火させる。核は発火・振る舞いができたかの事実確認で、本番セッションでは自走の良し悪し (止まり方・判断の質など) も見る。
The English summary is being prepared. Showing the original description.
Delegate routine work to subagents — boilerplate generation, data transformation, file analysis, documentation drafting. Use when splitting tasks into independent subtasks for parallel subagent execution.
The English summary is being prepared. Showing the original description.
Use when executing implementation plans with independent tasks in the current session — trigger phrases "execute the plan", "independent tasks", "parallel tasks", "subagents for the plan","split the plan into subagents". Dispatches a fresh subagent per task with two-stage review after each: spec compliance first, then code quality.
The English summary is being prepared. Showing the original description.
Ground rules for an effective subagent in a loop, workflow, or graph run. Stay in scope, escalate when stuck, return structured results. Use when acting as a subagent, writing subagent prompts, or reviewing delegated agent behavior.
The English summary is being prepared. Showing the original description.
大学業務文書 (広報原稿 / 研修教材 / 申請書 / 学生向け案内等) のドラフトを 読み取り、subagent dispatch で「AI 臭度」「業務文書適切性」「読者負荷」の 3 軸評価を返す。「この広報原稿、AI っぽくない？」「研修資料が硬すぎないか 気になる」「職員が書いたふうに仕上げたい」と問われた時に起動する。 mizchi-blog-style の評価ワークフローを大学業務文書向けに翻訳、職員 / 学生 / 学外読者の 3 ロールのいずれかで subagent がドラフトを読み、 冗長敬語 / 空虚強調 / 両論併記等を行番号付きで指摘する。反復改善は 呼び出し側判断、本 skill 自体はシングル実行。
The English summary is being prepared. Showing the original description.
Delegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verifier brief, dispatching a subagent to build, fix, or verify work you own, or a subagent reports DONE, blocked, or concerns. NOT for campaign-scale doctrine (use campaign-pattern).
The English summary is being prepared. Showing the original description.
Carry out an implementation plan by assigning each task to a fresh subagent, a separate agent with its own context. Review specification compliance first, then code quality, repeat fixes as needed, and finish with an integration review.