「subagents」の検索結果

Runs a multi-step procedure as a Python DAG, so ordering, branching and retries are enforced by the runner rather than described in prose a model can generate past. Use for "run these steps in order and retry the flaky one until the check passes", "build a pipeline that fetches, validates, then skips the upload when nothing changed", "make sure these steps cannot be skipped", "resume from where it broke instead of redoing the expensive early stages", "run these independent calls at once and merge the results", or any procedure of 3+ steps with branches, input contracts, or side effects that must not block the critical path. Primitives are depends_on, when=, validate=, retry_until=, detached= and journal_path=. Not for a single sequential call, for steps needing reasoning between them that no predicate captures, or for async and distributed work. To audit whether one verification check can actually go red, use gating. To fan work out across many subagents, use a dynamic workflow.

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-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness. Spawns parallel subagents for comprehensive analysis. Produces per-post scores and a prioritized action queue. Use when user says "audit blog", "blog audit", "site audit", "blog health", "audit all posts", "check all blogs".

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, update, or audit AGENTS.md (default) or CLAUDE.md agent instructions: set up, prune, add a rule, or merge CLAUDE.md or .cursorrules into one file Claude Code, Codex, and Cursor all read. Don't use for READMEs, skills, or subagents.

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 王建硕 wants to evaluate whether a change to VoiceDrop's 挖矿 system prompt is actually better than the live version — runs the local eval harness (golden fixtures × champion-vs-candidate, same input), dispatches blind pairwise judge subagents, aggregates a win-rate verdict, and on approval promotes the candidate into agent/src/prompts/mine.js. Triggers — "评估 prompt"、"挖矿 prompt 改好了吗"、"eval prompt"、"比一比两版 prompt"、"/wjs-evaling-voicedrop-prompts".

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 tasks to specialized subagents for parallel or sequential execution.

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。

Orchestrate a multi-model code review: spawn 3 review subagents, merge findings. In PR mode, posts GitHub PR comments with reactions. In local mode, outputs findings directly. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

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。

Comprehensive code review using parallel specialized subagents. If a PR URL is provided, fetches PR details and can post comments. If no PR is provided, reviews the diff between the current branch and its base branch plus any uncommitted changes. CRITICAL: this skill is costly, don't use it unless user explicitly requested to use it.

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。

Team-theory primitives for cooperative agents: what each subagent sees, when to communicate, aggregation, Shapley credit, coalition topology. Use when organizing subagents.

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。

Chooses subagent, team, workflow, or debate and launches it on Claude Code or Codex. Use when delegating, running agent review boards, or installing shared 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。

Orchestrating multi-session parallel execution via Claude Code Agent Teams API and Codex CLI Subagents — launch, manage, coordinate concurrent tasks. Use when parallel work is needed.

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 a trivial task inline — no subagents, no planning overhead

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。

Independent review loop run before delivery in code work. An independent reviewer (Codex, or fresh Codex-style subagents) reads the whole PR against the approved outcome; the lead fixes in-scope functional findings and re-reviews until none remain. Its differentiator is independence and exhaustiveness — a reviewer that fails differently from the authors, run to clean — distinct from the recursive-refinement ladder. Invoked by the team lead from the unified pre-ship gate (code-mode and /swarm:refine) after the ship steps.

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。

Comprehensive Rust code review that fans out across detected technology areas, running them in parallel when the agent supports subagents and sequentially otherwise. Use for pre-push or pre-PR review of .rs 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。

Comprehensive Remix v2 code review with per-area review skills, run in parallel where the agent supports subagents and sequentially otherwise. Detects Remix v2 in package.json, loads relevant review skills, runs verification protocol.

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。

Comprehensive React/TypeScript frontend code review with per-area review skills, run in parallel where the agent supports subagents and sequentially otherwise.

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。

Implements agents using Deep Agents. Use when building agents with create_deep_agent, configuring backends, defining subagents, adding middleware, or setting up human-in-the-loop workflows.

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。

Reviews Deep Agents code for bugs, anti-patterns, and improvements. Use when reviewing code that uses create_deep_agent, backends, subagents, middleware, or human-in-the-loop patterns. Catches common configuration and usage mistakes.

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。

Detects common LLM coding agent artifacts across four categories (tests, dead code, abstraction, style) over the project or changed files — using parallel subagents when the agent supports them, otherwise four sequential passes. Scans files changed since main by default; use --all for full-project scan. Triggers on LLM cruft cleanup, agent-generated code review, dead code sweeps, test-quality passes, or when the user asks to scan the whole repo.

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 as the follow-up to brainstorm-beagle when a spec has an Open Questions section (or quietly carries latent gaps) that need closing before planning or implementation can begin. Triggers on: "resolve the open questions", "close the gaps in this spec", "research the open items", "finalize my spec", "make this spec implementation-ready", "answer the TBDs". Also triggers whenever the user points at a brainstorm-beagle spec and asks for research, proposals, or answers to unresolved items. Orchestrates parallel research subagents when available (falls back to inline sequential research otherwise), proposes answers one at a time for user approval, then rewrites the spec in place so it arrives at planning with no known gaps. Does NOT write code, design implementation, or create plans — it only produces a complete spec.

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 you need a bite-sized, TDD-driven implementation plan but do NOT have a brainstorm-beagle spec to plan against. quick-plan reconstructs intent from the current conversation, fans out domain-expert exploration subagents across the codebase, and synthesizes the same plan format write-plan produces — without requiring `.beagle/concepts/<slug>/spec.md`. Triggers on: "quick plan", "plan this out", "plan what we just discussed", "turn this into an implementation plan", "plan this without a spec", "I don't have a spec, just plan it", "write-plan but no spec". Make sure to use this skill whenever the user wants an implementation or TDD plan and there is no spec to plan against — even if they just say "plan it" after discussing a feature. Writes to `.beagle/plans/<slug>/plan.md`. If a finalized spec already exists at `.beagle/concepts/<slug>/spec.md`, prefer write-plan. Does NOT brainstorm specs, write code, or execute the plan — produces the plan document (and an optional handoff prompt) only.

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。

60-Second Financial Snapshot — fast assessment of financial health based on six core inputs (income, expenses, savings, debt, age, retirement goal). No subagents. Produces a compact terminal scorecard with savings rate, DTI ratio, emergency fund coverage, retirement on-track status, and top 3 priority actions in under 40 lines.

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 design artifact (spec, plan, PR packet) with fresh, memoryless subagents. Invoke when the user asks — "goldfish this", "fresh eyes", "tear this apart" — or after suggesting it for a spec that has grown load-bearing and the user agrees.

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。

Guide for creating Claude Code plugin hooks — language selection heuristic (Node.js default, match project runtime when obvious), hooks.json configuration, event selection, prompt-based vs command hooks, ${CLAUDE_PLUGIN_ROOT} paths, stdio suppression, timeout sizing, and testing. Use when adding hooks to a plugin, creating PreToolUse/PostToolUse/Stop/SubagentStop/SessionStart/UserPromptSubmit hooks, or wiring hook scripts to hooks.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。

Use when writing delegation instructions to subagents, authoring CLAUDE.md files, rules, skills, or agent definitions, or auditing existing AI-facing content for bloat. Activates on "write a rule for", "add to CLAUDE.md", "create an agent", "update memory", or any request to author AI-facing instruction content. Removes discoverable data, explained-away knowledge, invented constraints, and stale cached facts.

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。