670 件 ・ 関連度順
概要と使いどころ
Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously. Use when onboarding onto a new project, understanding architecture, or investigating a cross-cutting concern.
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 four parallel read-only subagents that each review the same diff from a different lens — security, performance, correctness, and readability — then merge findings into one report. Use before merging large or risky PRs.
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。
ABSOLUTE MUST to debug and inspect LLM/AI agent traces using PostHog's MCP tools. Use when the user pastes a trace or session URL (e.g. /ai-observability/traces/<id> or /ai-observability/sessions/<id>), asks to debug a trace, figure out what went wrong, check if an agent used a tool correctly, verify context/files were surfaced, inspect subagent behavior, investigate LLM decisions, or analyze token usage and costs. Also use when raw SQL/HogQL against `events.properties.$ai_input` / `$ai_output_choices` returns empty — message content lives only on the dedicated `posthog.ai_events` table.
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。
Launch multiple explore subagents in parallel to investigate architecture, data models, auth, APIs, and deployment. Synthesize into an onboarding document.
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 group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking. Use when user requests party mode, wants multiple agent perspectives, group discussion, roundtable, or multi-agent conversation about their project.
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。
Automated CLI-based parallel agent execution — spawn subagents via Gemini CLI, coordinate through MCP Memory, monitor progress, and run verification
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。
Create Claude Code slash commands and OpenCode command files that delegate to subagents. Use when creating new commands or refactoring existing ones to follow the delegation 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。
Use when independent bounded tasks benefit from delegation during implementation
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。
Re-analyze an existing GitHub Issue using its current title and body, refresh the implementation plan against the latest code state, and update the Issue in place. Use when the user provides an Issue number (numeric, `#`-prefixed, or Issue URL) and wants to regenerate the code analysis via the explore-agent subagent. For reflecting comment-driven updates, use update-issue. For creating a brand-new Issue from a natural-language task description, use create-issue.
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。
Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.
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 Claude markdown subagent files to Codex CLI TOML format. Parses YAML frontmatter and body, applies model/permission/tool mappings, and outputs to agents/codex/<name>.toml.
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。
Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.
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 user wants to execute an existing pwdev-feat action plan — 'executar o plano user-crud', 'exec latest', 'rodar o plano', 'retomar a execução'. Dispatches the executor (subagent when the runtime has one, inline otherwise) in IMPLEMENT or REPORT mode, handles NEEDS_ADVICE with the advisor, and supports --resume. Do NOT use to create plans (feat-feature, feat-backend, feat-frontend, feat-test, feat-review) or for tasks without a plan (feat-quick).
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。
Introduce the cross-section read interface boundary (I<Section>ServiceRead) for one section's service per memory/architecture/section-read-write-split.md. Audits the surface, evaluates which methods belong on the read interface, sets up the workspace, dispatches a subagent that introduces the interface and migrates non-section callers, opens a PR. Use when the user says 'read split for X', 'split <Section>Service', 'add I<Section>ServiceRead boundary', 'apply the section-read-write-split rule to <Section>', or any variation of carving the cross-section read surface out of a section's full service interface. Reference implementation is Teams (PR 678). Operates on one section per invocation.
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, critique, set, create, activate, or run durable Codex goals for persistent or long-running objectives. Use when the user says "set a goal", "start a goal", "activate goal mode", "persistent goal", "long-running objective", "goal tree", or asks for a goal with verifiers, durable state, approval gates, completion proof, bounded delegation, or parent/child subagent goals.
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 a Go design spec before implementation begins - dispatch a subagent that checks a design doc for completeness, consistency, and idiomatic Go (simplicity, small consumer-defined interfaces, explicit wrapped errors, context propagation) plus Cobra/Viper conventions where applicable. Use when a user has a Go spec to review, asks "is this spec ready?", or is about to implement from a written design. Distilled from spf13/go-skills and adapted to this repo's conventions.
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。
Route user requests to the right skill, decompose complex work into parallel subagents, and manage project phase transitions. Load when the user asks "what should I do next", "which skill should I use", "orchestrate this", "run the full workflow", "split this into parallel tasks", or when a complex request spans multiple skills. Also triggers on "coordinate agents", "parallel execution", "task decomposition", "agent workflow", "what phase am I in", or when the user gives a broad instruction that requires multiple skills in sequence. This is the project's brain — it decides what runs, when, and whether to parallelise.
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。
Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health check.
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。
Pre-commitment attack on a plan by an agent that did not write it. Use when presenting a feature-deep-dive plan, assigning vision-to-fleet briefs, moving a register to build mode, ratifying a scope list, or coding a new contract or table. NOT for built work or DONE reports (use subagent-dispatch).
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。
Working playbook preloaded into the reviewer helper; the coach updates its Lessons after each round. Use only when acting as reviewer or coaching it. NOT for writing a verifier brief (use subagent-dispatch).
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。
The recipe for production-grade AI Matrx platform agents built through the AI Dream MCP. Use when asked to create, build, configure, improve, rename, or re-instruct a platform agent, or when a deliverable or kind needs an agent to emit it. NOT for Claude Code subagents or .claude/agents files.
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。
サブエージェントを活用した並列実行・調査委譲・コンテキスト管理の戦略。複雑な問題への対処、調査・探索タスク、複数の選択肢の比較検討、大規模なリファクタリングなどでこのスキルを参照する。「調べて」「比較して」「並列で」「複数のアプローチを試して」といったリクエストや、メインのコンテキストが肥大化しそうな場面で使う。
Pattern for progressively refining context retrieval to solve the subagent context problem
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。
Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.
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。