“subagent”的搜索结果

Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Review a GitHub pull request from multiple perspectives in parallel, output only findings, then let the user pick which to fix in the same session. Use when the user asks to review a PR by number, mentions "PRレビュー" / "PR review" with a number, or invokes `/pr-review <number>`. Fans out subagents for absolute-rules, stop-slop, security, architecture, code-quality, testing, and ai-antipattern.

中文简介正在准备中。当前显示原文说明。

Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).

中文简介正在准备中。当前显示原文说明。

Execute a phased implementation plan using subagents. Use when asked to execute, run, or carry out a plan — especially one created by make-plan.

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

Design and scaffold new skills, subagents, and MCP surfaces. Use when choosing which primitive to create. NOT for invoking existing agents, generic coding help, or deployment work.

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

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).

中文简介正在准备中。当前显示原文说明。

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.

中文简介正在准备中。当前显示原文说明。

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。

中文简介正在准备中。当前显示原文说明。

Runs a session's fan-out — splits a large request into tiered, recoverable units, dispatches and reconciles them against the repo. Trigger when work needs many agents or spans many repos or files (rebuild, re-architect, sweep, migrate, 'do all of this'); when subagents would launch with no model or effort set; for the plan table (units, models, tokens, meters) before launch; to resume a unit that died or hit a usage limit; when units would share a repo; or say dispatchwright (plan, dispatch, resume, audit, refresh). Tiers come from its own table (scoutwright flags it stale); pacing, pacewright's; hooks, rigwright's; schedules, agentwright's.

中文简介正在准备中。当前显示原文说明。

Paces a Claude subscription's usage — how fast to spend this week, what can still run at N% weekly, whether planned work fits before a reset. Reads the 5-hour, weekly, per-model and CI-minutes meters, sets a spend mode (normal, pace, turbo, overnight, work-day, owner-away, reset-eve) and re-cuts waves that don't fit. Also when something ate usage overnight, CI minutes run low, context runs high (compact or clear?), a new model needs a measured baseline, or which skill or subagent used tokens; or say pacewright (check, mode, fit, context, uba, baseline, spend, refresh). The plan table is dispatchwright's; the handoff, handoffwright's; one artifact's cost, skillwright's slim; the meter statusline, rigwright's; a scheduled check, agentwright's.

中文简介正在准备中。当前显示原文说明。

Pattern for progressively refining context retrieval to solve the subagent context problem

中文简介正在准备中。当前显示原文说明。

Use when executing implementation plans with independent tasks in the current session

中文简介正在准备中。当前显示原文说明。

Implement a whole spec by orchestrating subagents over its ticket graph; auto-detects the most recent task folder when no argument is given.

中文简介正在准备中。当前显示原文说明。

Builds production-ready applications with the Claude Agent SDK for Python, covering orchestrators with subagents, programmatic agent configuration, hooks, and permissions.

中文简介正在准备中。当前显示原文说明。

Identify all files a specific author contributed to on a branch vs its upstream, tracing code through renames. Use when asked who edited what, what code an author contributed, or to audit authorship before a merge. This skill should be run as a subagent — it performs many git operations and returns a concise table.

中文简介正在准备中。当前显示原文说明。