Best subagents skills, page 20

How to scope, brief and choose sub-agents when delegating work with the Agent tool - named vs forked agents, file ownership boundaries, model selection, and when a fork is the wrong choice.

sammcj/agentic-coding

Read-only local workspace scout subagent for Pi. An agent skill from CoWork-OS/CoWork-OS.

CoWork-OS/CoWork-OS

Launch a subagent to critically and exhaustively audit a task plan markdown file.

r3bl-org/r3bl-open-core

当主 Agent 面临多步骤复杂任务并正在判断要不要 / 怎样把子任务外包给内置子代理（browser / doc-editor / data-analyst / extractor / canvas-designer / coder 等）时触发。不用于：单步问答 / 读取 / 简单副作用（主 Agent 直接做）、已经明确要用 Agent 且知道 subagenttype 的场景。

OpenLoaf/OpenLoaf

Required for visualized output. An agent skill from OpenLoaf/OpenLoaf.

OpenLoaf/OpenLoaf

Post-implementation documentation-sync detector. An agent skill from ayoubben18/ab-method.

ayoubben18/ab-method

Coordinator and retrospective workflow-state protocol. An agent skill from sandgardenhq/sgai.

sandgardenhq/sgai

Shared delegation contract for SGAI agents that invoke Task subagents.

sandgardenhq/sgai

Shared return contract for SGAI Task subagents. An agent skill from sandgardenhq/sgai.

sandgardenhq/sgai

TDD for process documentation - test with subagents before writing, iterate until bulletproof.

sandgardenhq/sgai

A skill your agent uses when a bug, failing test, or unexpected behaviour needs investigation, especially across sessions or context resets.

coco-research/coco

Subagent for figma-from-code Phase 0b. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 2.5. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 2. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 1. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Subagent for figma-from-code Phase 5. An agent skill from bitovi/ai-enablement-prompts.

bitovi/ai-enablement-prompts

Mint isolated git worktrees for parallel agent work, track ownership in a cross-agent registry, and land finished branches back onto a target with a queued rebase, test gate, and atomic fast-forward…

iii-hq/workers

A skill your agent uses when executing a larger plan in Cursor with parallel or delegated work, while keeping tasks narrowly scoped and reviewed between steps.

6BNBN/FlowPilot

Quick-invoke QA testing for a web app URL. An agent skill from SpecterOps/skills.

SpecterOps/skills

Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to…

majiayu000/claude-skill-registry

Build autonomous AI agents with Claude Agent SDK. An agent skill from majiayu000/claude-skill-registry.

majiayu000/claude-skill-registry

Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result integration that catches contradictions.

mohitagw15856/pm-claude-skills

Java/Maven single-module deep documentation generator. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

智能任务分发与子代理协调中枢。当用户提交任何任务时，执行需求分析、任务拆解、分发策略制定，分发给合适的 subagent 执行，监控进度并阶段汇报，最终汇总结果。失败时自动兜底处理。适用于：（1）用户直接下达的任务（2）cron/heartbeat 触发的任务（3）任何需要多步骤处理的工作。

LeoYeAI/openclaw-master-skills

Persistent task queue system. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Investigate Elixir/Phoenix bugs root-cause first. An agent skill from oliver-kriska/claude-elixir-phoenix.

oliver-kriska/claude-elixir-phoenix

Run fix/refactor work with parallel subagents split into non-overlapping file batches; agents never build or test — the coordinator verifies once at the end.

LunCoSim/lunco-sim

Ultra-compressed communication mode. An agent skill from hashgraph-online/awesome-codex-plugins.

hashgraph-online/awesome-codex-plugins

Front door for running the clean-room unattended loop as a Claude Code dynamic WORKFLOW using in-session subagents, so it never spends claude -p API tokens.

hashgraph-online/awesome-codex-plugins

A skill your agent uses when a plan has parallel tasks and the harness supports dispatching subagents.

hashgraph-online/awesome-codex-plugins

Handle failures during spec2cloud execution. An agent skill from EmeaAppGbb/spec2cloud.

EmeaAppGbb/spec2cloud

Launch multiple explore subagents in parallel to investigate architecture, data models, auth, APIs, and deployment.

spencerpauly/awesome-cursor-skills

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.

spencerpauly/awesome-cursor-skills

When multiple tests fail, assign each failing test file to a separate subagent that fixes it independently in parallel.

spencerpauly/awesome-cursor-skills

Generate an agent across the host AI tools a project uses. An agent skill from ai-driven-dev/framework.

ai-driven-dev/framework

Planning agent for task breakdown and implementation planning.

EliasOulkadi/shokunin

Extract insights from external documents (research papers, books, articles).

Abilityai/cornelius

Fast knowledge base retrieval - single FAISS search + graph connections, no subagents or LLM orchestration

Abilityai/cornelius

Run an existing task autonomously to completion — each remaining mission in a subagent with tdd, tracker updated per mission, a commit after every green mission.

ayoubben18/ab-method

Dispatch multiple subagents in parallel on independent tasks.

danielvm-git/bigpowers

Autonomously ship a feature end-to-end with zero human intervention: plan it, implement it, review it with a team of subagents, boot the full stack, drive it in a real browser like a user…

theexperiencecompany/gaia

Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger.

yonatangross/orchestkit

Run parallel or isolated subagents for independent subtasks (research, parallel analysis, one-shot transforms) to avoid bloating the main context.

av/mi

Answer "how does X work", "where is X defined", or "trace through Y" questions about a codebase using parallel subagent searches with cited summaries.

av/mi

A robust methodology for LLM-based requirements gathering and high-fidelity artifact generation.

GoogleCloudPlatform/cxas-scrapi