Agent skills directory

Execution skill for delegated tasks. Use this skill when you are a subagent that has been delegated a task by the tech l...

Run a one-shot or flat parallel batch of provider LLM subagents (headless `cc-fleet subagent`) that return a result. Use...

Protocol that evo optimization subagents follow when dispatched from /optimize. Auto-loaded by spawned subagents via the...

Activate when you are a delegated subagent (not the orchestrator). Establishes subagent protocol with terse returns, det...

Spawn and manage autonomous background agents for parallel work

Design, review and improve Claude Code sub-agents: generates .claude/agents definitions with YAML frontmatter, checks ex...

Create subagent definitions for Claude Code and OpenCode that delegate to skills. Use when creating new subagents or ref...

Patterns for launching and managing parallel subagents efficiently.

Auto-injects subagent delegation best practices when agents, subagents, Task tool, or parallel execution is mentioned.

Guide creation of Claude Code Subagents with task scope definition, tool selection, system prompt design, and delegation...

Create and configure custom subagents in Claude Code. Use when user asks to create a new subagent, needs specialized AI...

This skill should be used when the user asks to "configure a subagent", "create a custom agent", "set up agent tools", "...

Use before dispatching a subagent with `isolation:"worktree"`, or while another subagent is in flight, to avoid three di...

Global contract for all specialist subagents. Enforces role boundaries, scope discipline, and DONE/BLOCKED status signal...

Coordinate all subagents in the Physical AI & Humanoid Robotics textbook project. Assign tasks, validate outputs, and tr...

Multi-perspective review council for pre-execution prompt sharpening and post-execution project code audit (compatible w...

创建具有自定义系统提示和工具配置的专业化 Claude Code 子代理。当用户要求创建新的子代理、自定义代理、专业助手，或为 Claude Code 配置特定任务的 AI 工作流时使用。

Design bounded sequential lenses of codenavi-agent with a single deliverable, explicit evidence packet, minimal tools an...

Create new Claude Code custom agents (subagents). Use when: (1) User wants to create a new custom agent, (2) User says '...

Guide for creating effective subagents (custom agents). Use when users want to create a new subagent that can be dispatc...

Use before running a subagent edit wave on D:/Monarch, or after parallel-agent edits to a Kotlin/Android repo: KSP fails...

Decomposes complex work into bounded subagent tasks, decides whether delegation is worthwhile, routes each task to an ap...

Use when executing a multi-task plan where each task is independent, or when the user wants parallel or isolated task ex...

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for ea...

Use when executing implementation plans in current session. Dispatches fresh subagent per task with two-stage review. Sp...

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

Delegating work down to subagents: briefs, report statuses, independent review. Use when writing an implementer or verif...

Execute a multi-task plan by dispatching one fresh subagent per task, auditing each result against an adversarial review...

Execute implementation plans with structured subagent dispatch and two-stage review (spec compliance, then code quality)...

Execute implementation plan by dispatching fresh subagent per task. Each task gets: Implementer → Spec Review → Quality...

Use when executing a pre-registered analysis plan with mostly independent steps in the current session

Use fresh agents for focused subtasks to avoid context pollution

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent per tas...

Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage r...

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

Dispatch parallel subagents for independent Godot tasks — use when a plan has tasks with no shared files or sequential d...

The implementation engine. Routed to by /sprint (full plan, autonomous) and by executing-plans (scoped batch, checkpoint...

subagent-driven-development — Execute plans via delegate_task subagents (2-stage review).

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues th...

Use when executing implementation plans with independent tasks — dispatches fresh subagents per task with two-stage revi...

This skill should be used when coordinating "multiple specialized agents", "complex workflow orchestration", "autonomous...

Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans...

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, the...

Use when executing implementation plans with independent tasks in the current session. Dispatches fresh subagent for eac...

Use when executing a written implementation plan with independent tasks in the current session where delegation beats in...

Execute plans task-by-task with two-stage review.

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

subagent-driven-development

当在当前会话中执行包含独立任务的实现计划时使用

Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks

(ePost) Use when a plan has 3+ independent tasks, phases have non-overlapping file ownership, or user says "parallel imp...

Use for complex multi-task work. One fresh subagent per task + two-stage review.

Execute plans via delegate_task subagents (2-stage review).

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for ea...

Fresh-subagent-per-task execution with two-stage review gates.

Two-stage review process - spec compliance then code quality

Use when decomposing complex work. Dispatch fresh subagent per task, review between tasks. Flow: Load plan → Dispatch ta...

Executes an approved implementation plan through fresh implementer and reviewer agents for each task, with explicit hand...

Use when executing an implementation plan whose tasks are mostly independent, in the current session, with a fresh subag...

Execute implementation plans by dispatching a fresh subagent per task with two-stage review (spec compliance then code q...

Execute an implementation plan through bounded implementer and independent reviewer agents with disjoint write ownership...

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for ea...

Use parallel subagents for large-scale paper screening and deep dive analysis

Design and maintain Claude Code subagents: the delegation decision, the frontmatter that governs a run, and the system p...

Empirically evaluate and optimise a Claude Code sub-agent via a blinded head-to-head against the production baseline, th...

Execute implementation plans using subagents. Three modes: single task, batch (sequential), parallel. Two-stage review f...

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-co...

Create specialized Claude Code agents on-the-fly. Guides through agent definition file creation with proper frontmatter,...

Skills群に対応するサブエージェント（.claude/agents/*.md）を設計・生成する。「サブエージェント作成」「並列処理エージェント」「専門エージェント」を依頼されたときに使用する。

Generates custom Claude Code subagents with specialized expertise. Activates when user wants to create a subagent, speci...

Task-isolated worker for codebase exploration, test generation, and repetitive mechanical refactoring

Maintain an existing generated subagent package when its sources, converters, runtime behaviour, or requirements change...

Subagent（{{AGENT_CONFIG_DIR}}/agents/*.md）の作成・更新・削除を対話で行い、フロントマター仕様と品質を維持したまま反映する。Subagent作成、agent追加、subagent updateを依頼さ...

Specialized AI assistants for task-specific workflows with separate context. Learn when to delegate, configure tools, an...

Use when designing or debugging the Master Orchestrator's routing logic, intent detection, escalation rules, or handoffs...

Use when asked to plan, decide, or execute subagent orchestration: subagents, delegated agents, parallel workers, review...

Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and re...

Use when a task spans 3+ files or components; You want multiple agents working at the same time

Manages the lifecycle, configuration, and synchronization of specialized sub-agents (Planner, Implementer, Reviewer, etc...

Coordinate quota-aware parallel subagents for large, multi-file Antigravity tasks.

Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS),...

Use when dispatching development work to one or more subagents and deciding how to shape each dispatch. Triggers: "use s...

Patterns for when and how to use Claude Code subagents via the Agent tool. Use when the user needs to delegate research,...

Run a cold-start implementer, reviewer, and fixer subagent chain for one issue, gated by CI, ending in a staging PR. Use...

Produce a comprehensive prompt that hands off the current session's work to a fresh session for sub-agent-orchestrated e...

Apply instruction-engineering to all subagent prompts. Use BEFORE invoking the Task tool, spawning agents, or dispatchin...

Template for structured sub-agent invocation using 4-part prompting (GOAL/CONSTRAINTS/CONTEXT/OUTPUT) and F# pipeline no...

Merges agent or review outputs into one deduplicated, evidence-linked, severity-ranked actionable report.

Runs swarm_search, swarm_run, or run_judge_panel via the synthet-agent-swarm MCP server. Use for a read-only external re...

Structure a multi-round Leader / Developer / Code-Reviewer review of a document or code change. Use when planning how ma...

Generate and validate project-scoped Codex subagents for explicit read-heavy exploration, review, security, docs researc...

Decide which work is safe to delegate to worker agents. Use before delegating tasks that may require user interaction, a...

Decide whether a piece of work should go to a subagent or stay in the main agent loop. Use before spawning subagents, wh...

Use when the user asks why their Claude Code quota or usage limit runs out so fast, which subagents cost the most, or wa...

Orchestrate complex tasks by delegating work to parallel subagent teams, preserving the main context window and preventi...

TDD-style testing methodology for skills using fresh subagent instances to prevent priming bias and validate skill effec...