Best subagents skills, page 13

Core principle that the main agent is a coordinator, not an implementer.

tzachbon/smart-ralph

Launch OpenAI Codex CLI as a subagent (ChatGPT subscription auth, no API key).

davidondrej/skills

Use only when the user explicitly invokes grill-for-unknowns or asks for a map-vs-territory unknowns pass, blindspot discovery, unknown-known prototypes, or a subagent launch packet before…

Asymmetric-al/core

Has a fresh-context adversary attack a blog post, recommendation, analysis brief or piece of code before you ship it, using a profile suited to that kind of artifact.

oaustegard/claude-skills

A skill your agent uses to run an ambiguity sweep over a written spec.md and close every under-specified point before planning or design proceeds — so two engineers can't reasonably build different…

genkovich/sdd

WAVES — Workers · Aggregate · Verify · Extend — wave-based orchestration for Cursor.

RayFernando1337/rayfernando-skills

Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result.

instructa/agent-skills

Launch a deep, multi-faceted investigation of a topic using parallel sub-agents.

strands-agents/box

Map-reduce a finished archestra-bench run into a Tier-1/Tier-2 improvement report using Claude subagents (same analysis as the Rust analyzer, no API key).

archestra-ai/archestra

Run a design arena: a coordinator fans out N subagents (default 7) that each prototype one UI section through a different lens, switchable in-app via a temporary prototype selector, refined in rounds.

archestra-ai/archestra

Consults existing breadcrumb analysis docs before exploring the codebase.

deepklarity/harness-kit

Queue processing with fresh context per phase. An agent skill from agenticnotetaking/arscontexta.

agenticnotetaking/arscontexta

Manual memory flush: dump current session context to daily raw log via subagent.

kevin-hs-sohn/hipocampus

A skill your agent uses when user explicitly asks for an adversarial / multi-round dialectic between masters — 祖师辩论, 各执一词, 谁更对, debate, 应成 vs 顿悟, 顿渐之争.

xr843/Master-skill

代码评审。协调 5 个专项 reviewer subagent 对代码进行并行多维度审查。可由用户直接触发，也可由主 agent 加载后作为 Judge 执行。

davidYichengWei/agentic-engineering-framework

Triage PR review comments, resolve already-addressed threads, and delegate /aidd-fix prompts for remaining issues.

paralleldrive/aidd

当在当前会话中执行包含独立任务的实现计划时使用

jnMetaCode/superpowers-zh

Best practices for spinning up nub Rust builds so they are PERFORMANT and CLEAN THEMSELVES UP — the prevention side of the recurring orphaned-build problem on the maintainer's dev host.

nubjs/nub

Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration.

inbrainfun/inbrain

Draft a new Codex custom subagent at .codex/agents/<name.toml, using the official Codex subagents format.

alexandremendoncaalvaro/CorridorKey-Runtime

Iterative review loop with subagent reviewer. An agent skill from microsoft/bocpy.

microsoft/bocpy

Delegate the latest implementation diff to the code-reviewer sub-agent for a PASS/CONCERNS verdict against CLAUDE.md rules, then write the verdict to reports/<feature-review.md.

juliepy/AI-Engineer-from-scrach

Merge several feature branches (often from parallel agents) into one branch for a single PR, resolving the repo's usual conflicts and checking the result.

sean-brydon/berthd

Same as /vspawn, but opens a dedicated git worktree for the child session (equivalent to vspawn --worktree).

vlinx-io/VelaTerm

Review a diff for clarity and safe simplifications, then optionally apply low-risk fixes.

sickn33/agentic-awesome-skills

Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs…

TanStack/ai

Researches domain ecosystem for project initialization. An agent skill from allgpt-co/QuickVoice.

allgpt-co/QuickVoice

Design a module's interface using parallel sub-agents producing radically different designs ("design it twice").

evanklem/evanflow

A skill your agent uses when in Multitask/Multi-agent mode or when the user asks for the agent team workflow.

curvenote/curvenote

WAVES - Workers, Aggregate, Verify, Extend - wave-based orchestration for Codex.

RayFernando1337/rayfernando-skills

A skill your agent uses when coordinating a startup goal across CEO, CTO, product manager, engineering manager, founding engineer, and QA lead role subagents.

johnku2011/boilerplates-with-ai-skills

Orchestrate review, tests, commits, branch pushes, and pull-request creation with parallel agents.

sickn33/agentic-awesome-skills

Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results.

sickn33/agentic-awesome-skills

A skill your agent uses when a supervisor, swarm, graph, planner-worker system, or parallel agent workflow needs review for task boundaries, shared state, branch joins, retries, cancellation…

sickn33/agentic-awesome-skills

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

sickn33/agentic-awesome-skills

Factory-context integrate stage (end-of-run shipping) for one dedicated builder subagent dispatched by the orchestrator after the fix wave has merged, after a GREEN verdict, or after a recorded…

DanMcInerney/architect-loop

Agent Teams orchestration patterns for multi-agent SAFe workflows.

bybren-llc/safe-agentic-workflow

Safely integrates commits from parallel agent branches using sequential cherry-pick.

ash1794/vibe-engineering

Review a flutterrustbridge PR before treating it as ready, including subagent checks for correctness and test weakening.

fzyzcjy/flutter_rust_bridge

Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry…

alirezarezvani/claude-skills

Review and resolve PR comments from GitHub. An agent skill from IvanMurzak/Unity-MCP.

IvanMurzak/Unity-MCP

When you report a brain page to the user — created, edited, committed, or relayed from a subagent — a working link is part of the deliverable, in the SAME message.

garrytan/gbrain

A skill your agent uses when 已有书面实施计划、任务相对独立，且在本会话内通过子代理逐任务落实时。触发场景：执行实施计划、子代理开发、按计划实现、Task 派发实现、两阶段代码审查、plan execution。

ProgrammerAnthony/Expert-Coding-Harness

Discipline for the seam between two SDKs (or two sides of one contract) that the same hand writes.

gridaco/grida

Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the…

Green-PT/honey-for-devs

A skill your agent uses when analyzing a large corpus of text, code, or data that exceeds a single agent's effective context - orchestrates parallel Worker subagents, Critic review subagents, and a…

ed3dai/ed3d-plugins

Interactively clear a backlog of open amd/gaia PRs to zero (or to a short, justified human-review list) by fanning out one isolated subagent per PR.

amd/gaia

Build, review, and audit technical docs and agent instruction files.

vincentkoc/dotskills