Expert guide for agent-native structured outputs, JSON Schema strict mode enforcement (OpenAI response_format, Gemini schema mode, Claude tool_use), MCP resource schemas, and…
当你在 Codex 下想写 / 调试 / 启动 cc-master 的 workflow 脚本、或想套用 Claude Code dynamic-workflow API 时用——这是 Codex adapter 的 unsupported stub。Triggers: 在 Codex 里提到 Workflow 工具、`agent()` /…
Describes the sub-agent pipeline: task-decomposer breaks a task into subtasks, task-worker implements them, work-reviewer checks the result; on issues feedback goes back to the…
当用户任务复杂、想让"一个专职角色"只干一件事（如挑计划漏洞/做研究/审稿），或问"怎么建 sub-agent"时调用。 提供子 Agent 设计模板：角色定义 + 单一职责 + 边界 + 与主 Agent 的交接。 不适用于：单一线性任务（一个 Agent 够）；或角色职责模糊。 触发信号: "建个子 agent" "sub-agent" "让一个 AI…
Manages parent/child agent relationships with task delegation and result aggregation. Supports sequential chains, parallel fans, conditional routing, retry logic, timeout…
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns.
Comprehensive guide to sub-agents in Claude Code: built-in agents (Explore, Plan, general-purpose), custom agent creation, configuration, and delegation patterns.
Pattern for progressively refining context retrieval in multi-agent workflows — avoids context-overflow failures when subagents cannot predict what context they need upfront.
Rosetta MUST skill. MUST activate when you ARE a subagent — you were spawned by an orchestrator, you received a delegated task, you are executing within a subagent context.
Запуск нескольких субагентов параллельно с автоматической сборкой результатов в единый отчёт. Используй для независимых задач которые можно выполнить одновременно.
Guide for creating AI subagents with isolated context for complex multi-step workflows. Use when users want to create a subagent, specialized agent, verifier, debugger, or…
Conception de systèmes de délégation parent-agent → sous-agents avec dispatch intelligent, suivi des tâches et agrégation des résultats.
Use when orchestrating multiple subagents with dependencies between them, running agents in parallel, or managing complex multi-agent workflows.
Use when executing implementation plans with independent tasks via subagent dispatch and two-stage review
Execute plans using fresh subagent per task with code review between tasks. Use for high-quality iterative implementation.
Dispatch fresh subagents per task with typed artifact handoff and two-stage review.
Execute a multi-task plan. Use when the user says "execute with subagents", or hands you an ordered multi-task plan to run.
Use when executing implementation plans with independent tasks in the current session — from TheFJK/UberDev
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent for each task with code review between tasks.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling f — from…
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Use when executing implementation plans with independent tasks in the current session — from bg-szy/TOP-SKILLS
Execute an implementation plan by dispatching Codex-backed implementer and reviewer agents while Claude keeps spec-compliance control. Codex-backed variant.
Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code review between tasks, enabling f — from…
Workflow for passing environment variables (like PATH) from the Orchestrator to subagents. Use when spawning subagents that need specific environment variables.
Executes a plan by dispatching one fresh subagent per STEP. The controller owns the todo and review; subagents own the edits. Keeps the main conversation light.
把子代理派发从"监督型治理"升级为"契约型治理"：探查/实现/验证角色分离、契约快照（含负空间）、三级有界读取、单写者文件所有权、行动门槛替代轮次门槛、结构化 BLOCKED、token/工具/轮次预算、结构化结果回收与 repair-contract…
Create specialized Claude Code agents on-the-fly. Guides through agent definition file creation with proper frontmatter, effective prompts, and tool scoping.
Delegate broad searches and independent subtasks to subagents to keep the main context clean. Use when a question requires sweeping many files or directories, when several…
Internal controller procedure for tracking, cleaning up, and recovering subagent sessions before workflows spawn additional subagents.
Translate a streaming subagent run into task progress, analytics, and notifications while keeping partial results and cleanup tidy.
Использовать для полного пайплайна: исследование AI-темы, написание новости, редактура, HTML-верстка, публикация в статический блог и проверка в браузере.
Fresh subagents per task with two-stage reviews. Trigger: When coordinating parallel agents for complex workflows.
Orchestrate subagent workflows for complex tasks that benefit from decomposition, role-based delegation, and parallel execution.
Monitor sub-agent health and progress via a pull-based bash daemon. Use when spawning sub-agents that need progress tracking, staleness detection, and automatic status reporting.
Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated execution.
Systematic methodology for constructing compact (<150 lines), expressive, Claude Code-integrated subagent prompts using lambda contracts and symbolic logic.
為 Codex 產生交付前 subagent 審查與驗證 prompt。用於功能已大致完成，需要先掃 repo、tests、docs、env 與 release 路徑，再依使用者語言輸出一份聚焦 correctness、安全、行為回歸、README / `.env.example` 同步與 e2e 驗證的 prompt。
Activate when you are a delegated subagent (not the orchestrator). Establishes subagent protocol with terse returns, details to history/, file ownership boundaries, and escalation…
Автоматический запуск и управление субагентами для параллельной обработки задач. Разбивает большие задачи на подзадачи, запускает субагенты параллельно, собирает результаты.
Build sessions_spawn command payloads from JSON profiles. Use when you want reusable subagent profiles (model/thinking/timeout/cleanup/agentId/label) and command-ready JSON…
Coordinate multiple agent sub-roles (architect, implementer, reviewer, tester) in parallel or sequential swarm mode, with clear handoff contracts and evidence recording.
Coordinate multiple subagents through dependency-aware waves, stage handoffs, monitoring, and verification loops. Use when the work is too large or too mixed for a single agent.
Review every Claude Code subagent file for the tools it can actually reach: agents with no tools line inherit every built-in and MCP tool, lookalike fields such as allowed-tools…
Use when the user explicitly asks for subagents, parallel agents, worker agents, independent code review, multi-agent codebase exploration, subagent-ready handoffs, or an approved…
File a structured issue against the designgrappler/agent-os public mirror. Use when the user says "file feedback", "report an Agent OS issue", "this Agent OS skill is broken", or…
Substitution Rabattvertrag Aut-idem: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen.
Split complex work into coordinated agent lanes with WIP checks, quality gates, rollback plans, and handoffs that prove what shipped.
Next-action selector for this pack: reads current repo, terminal, plan, or handoff state, scores 2-4 candidate moves against goal alignment, unblocking, evidence, urgency, and…
How to compress retrieved vector/RAG document chunks into 3-bullet atomic facts before injecting them into frontier LLM context, cutting RAG token bloat by 85%.
Weekly meta-review that orchestrates /weekly + /patterns + vault-hygiene + claude-md-drift + decision-retrospective in one flow.
Use when you need to apply tracked changes and comments to DOCX files programmatically, merge multi-agent edits with conflict resolution, or produce native Word revisions from AI…
Use when executing implementation plans with independent tasks in the current session — from steph-frtech/cdesign-expo
Use when executing implementation plans with independent tasks in the current session — from ranbot-ai/awesome-skills
Use Cc Haha as a local desktop workspace for Claude Code sessions, worktree launches, diff review, permission approvals, Computer Use, remote access, and scheduled agent tasks.