「subagent」の検索結果

Catalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories (theatrics, overwrought register, corrective antithesis, dramatic short sentences), fix subagents repair only what a catalog names, mechanical lint + frequency analysis bracket the run, and a regression gate (lint delta, word count, cold meaning check) decides whether the result ships. Use when the user says "deslop this draft", "catalog deslop", "strip the AI patterns from this file", or as the final stage of the article-factory and mosaic-writing skills. For writing or redrafting prose from scratch, use the prose skill instead - this skill only repairs an existing draft in place.

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。

Delegate implementation work to a dedicated implementer subagent, then review its diff, send it back to iterate, gate on the full test suite, and ship it as a PR. Use this whenever the user wants a separate model to write code, mentions handing off / delegating implementation, asks to work through a plan or spec unit-by-unit with a subagent doing the coding, or wants a review-and-merge loop wrapped around delegated output — and also when resuming such a loop ("keep going", "next unit", "继续下一个"). It encodes constraints that are expensive to rediscover: the implementer self-reports success, must not run the full test suite by default, must not touch git, and its report is a claim rather than evidence. Cursor port of implementation-loop. This loop expects an approved plan or an equivalently precise spec; settle an unsolved high-level goal into a plan first, using the cursor-engineering-mode skill (it ships in this same plugin).

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。

Coordinates staged or parallel jobs across live-verified coding-agent runtimes (Claude Code, Codex, Cursor, and other installed CLIs) and in-session toolkit subagents. Routes each job by capability and risk tier, isolates parallel writers in git worktrees, captures redacted output, resumes interrupted runs, and blocks completion until an independent arbiter verifies the results. Use when work should be split across multiple runtimes or subagents, run as staged or parallel jobs, and reviewed before handoff. NOT for a single-agent task or the in-session 7-phase flow (use mk:cook / mk:workflow-orchestrator).

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。

Turns a plan phase into a PhaseSpec v1 and dispatches it to a specialist subagent via the Agent tool. Subagent reads files itself, returns a structured result, the result is logged into progress.md. Markdown is the shared state; no in-memory shared store across agents.

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。

Coordinate complex engineering work across bounded subagents while protecting the main context, preventing edit conflicts, and measuring whether delegation was worthwhile. Use when the user asks to delegate, parallelize, orchestrate, use subagents, fan out a review, or handle a large task with independent workstreams; do not use for small, tightly coupled, or inherently sequential 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。

Execute plans via delegate_task subagents (2-stage 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。

Subagent that scans CopilotKit + AG-UI releases shipped in (and just after) the report window, diffs the git tags to extract what each release actually fixed, and returns a fix-map the weekly-report writer cross-checks against open issues. Catches issues that are quietly already-fixed in a shipped release, and is the authoritative source for the "current release vX.Y.Z" version claims. Invoked by weekly-report (spawned in parallel with the Discord/GitHub pulls); runs as a general-purpose subagent so the orchestrator's context stays small.

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。

Subagent for GitHub author enterprise enrichment. Runs gh api users/<login> for each unique handle and classifies enterprise vs indie. Invoked by weekly-report or enterprise skills; runs as Explore subagent so the orchestrator's context stays small.

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。

Subagent flow for deep-reading GitHub issues + their linked/closing PRs to the bottom. Captures CURRENT state, maintainer status updates, reporter repro, blocking reviewer concerns, hidden second bugs, cross-repo duplicates. Invoked by weekly-report orchestrator; runs as a general-purpose subagent so the orchestrator's context stays small.

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 spawning a task()/agent()/workpool() subagent with an outputSchema, to reduce yield-tool retry failures by stating the exact result envelope and required fields in the task prompt.

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 orchestrating implementer/judge subagents — form gate + nine modes (do-and-judge ±two-stage, steps/parallel/worktrees, competitively, debate, live-app-judge, adversarial-council).

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。

frontmatterを記述するとき、subagent/hooksを配線するときに読む。

Use when an approved plan has independent tasks ready for delegated execution with fresh subagents and two-stage 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。

Use for the subagent-as-a-tool pattern.

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。

Baut und prüft neue Agentenrollen im ellmos-Ökosystem: native Claude-Code- Subagenten (dauerhafte Rollendefinition) und Companion-Worker (SendMessage- wiederverwendete Instanz für eine Ticket-/Aufgabenserie). Formalisiert das bislang unformalisierte eigene Wissen aus dem laufenden Bau von Agentenrollen (ati-agent, bueroassistent, versicherungs-agent u. a.) zu einem wiederverwendbaren Scaffold-plus-Verify-Ablauf. Nutze diesen Skill, wenn eine neue Rolle entstehen soll ("neue Agentenrolle bauen", "Subagent anlegen", "Companion-Worker starten") oder eine bestehende gegen die Haus-Konventionen geprüft werden soll ("ist dieser Agent richtig aufgesetzt?").

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。

RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes

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。

Expert en workflow Claude Code (commands, skills, subagents, CLAUDE.md, best practices)

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。

Configure and synchronize multi-harness subagents (Claude Code, Google Antigravity, OpenCode, ChatGPT Codex CLI) with optional per-harness model overrides and single source of truth in .aos/pipeline.json.

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。

Execute plans via delegate_task subagents (2-stage 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。

プロジェクト（特にこのテンプレートから始める新規プロジェクト）にClaude Code用の.claude/環境を対話形式で段階的にセットアップする。settings.jsonの権限・hooks設定、必要に応じたカスタムskill・command・subagentの雛形作成、CLAUDE.mdのビルド/実行/テストコマンド欄の穴埋めを行う。「セットアップして」「環境構築して」「init」「このプロジェクトでClaude Codeを使えるようにして」「開発を始めたいので準備して」といった依頼で積極的に使うこと。エンジニアが常駐しない・少ない組織で「事故らないようにしたい」「危険な操作を防ぎたい」「lint/testやセキュリティレビューが誰もチェックしないまま放置されるのを防ぎたい」といった要望がある場合も、権限・hook・レビュー体制を通じた安全網の構築としてこのスキルが対応する。既存の/initスキルはCLAUDE.mdのコードベースドキュメント生成に特化しているが、権限設定やskill/command/agentの追加が絡む場合は必ずこちらを使う。

Sous-agent spécialisé dans les appels API REST/GraphQL avec retry, auth et transformation de données. Se déclenche avec "sous-agent API", "API caller agent", "agent qui appelle une API", "REST agent", "HTTP agent", "API integration subagent", "external API agent".

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。

OpenAI Codex (CLI / IDE / cloud) の公式リファレンス。 codex CLI, codex exec, AGENTS.md, rules, subagents, prompting, approvals, sandbox, permission profiles, auto-review, config.toml, profiles, MCP 設定, 環境変数, GitHub Action, Codex SDK, Agents SDK 連携, cloud 委譲, administration, roles, provisioning, analytics API, compliance API, Codex Security 脆弱性スキャン, deep scan, triage, findings, SARIF export, threat model, security hardening, cloud / local / worktree 環境, git worktrees, Record & Replay, GitHub / Linear / Slack 連携。

Claude Agent SDK (code.claude.com/docs/en/agent-sdk) の TypeScript / Python リファレンス。 query(), ClaudeAgentOptions / Options, custom tools (in-process MCP), createSdkMcpServer, hooks, permissions (canUseTool), subagents, sessions (resume / fork), streaming, structured outputs, slash commands, tool search, hosting / observability。

Claude Code (code.claude.com) の拡張機能リファレンス。 Agent Skills (SKILL.md), slash commands, output styles, subagents, agent teams, agent view, workflows, routines, scheduled tasks, hooks (PreToolUse / PostToolUse), plugins, plugin marketplace, MCP 設定 (.mcp.json / claude mcp add), managed MCP, channels (--channels / claude/channel push events, webhook / telegram / discord / imessage), tools-reference, advisor, ultrareview。