Best subagents skills, page 6

Profile and debug Hermes sessions from their JSONL transcripts.

tamdogood/builder-essential-skills

This skill should be used when the user asks to "create a team", "create agent team", "蜂群", "swarm", "团队协作", "parallel agents", "spawn teammates", "多 agent 协作", "组建团队", or executes "/swarm".

apple-ouyang/book-to-skill

A skill your agent uses when a complex, long-running task risks polluting one conversation — research, implementation, review, planning, or learning that should be split into dependency-aware…

Jinghao67/conductor

How to write JavaScript workflow scripts for the workflow tool - fanning work out across many isolated subagents with agent(), parallel(), and pipeline(), then synthesizing one result.

PostHog/code

Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a…

cbrock84/headcount

A skill your agent uses for structured research on an unfamiliar or complex codebase before planning, reviewing, or editing.

bbartling/open-fdd

Launches many parallel cloud workers on slices of a task or on the same brief, waits for them all, and returns one aggregated report.

cursor/plugins

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

loulanyue/awesome-claude-notes

Automated Dynamic Application Security Testing (DAST) using Playwright MCP plus standard OS pentest tooling.

hardw00t/ai-security-arsenal

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

ethanhq/cc-fleet

A skill your agent uses when rules or instructions mention "adversarial-authoring", "adversarial authoring", "must use adversarial-authoring skill", "model council", "cross-model review", or…

intent-driven-dev/intent-driven-template

Breaks a research question into two to five facets and sends parallel document-specialist agents to search the web and documentation, then merges the results.

Yeachan-Heo/oh-my-claudecode

When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

antonbabenko/deliberation

Audit open dependabot PRs in this repo. An agent skill from garfiec/Librechat-Mobile.

garfiec/Librechat-Mobile

Deep code-only review of a pull request or candidate patch for correctness, safety and .NET MAUI conventions, judging the code before reading the PR description.

dotnet/efcore

Full website SEO audit with parallel subagent delegation. An agent skill from andrew-yangy/gru-ai.

andrew-yangy/gru-ai

Delegate work to sub-agents as visible Pier terminal panels.

runloom/pier

Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns

alirezarezvani/claude-code-skill-factory

Gets an independent critique of recent work and session direction from the adversarial-review subagent.

ropensci/ckanr

Coordinates specialist agents to create a Homebrew cask for a macOS app: pre-flight checks, download and inspection, a livecheck strategy and the remaining cask steps.

malob/nix-config

Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes.

vincentkoc/dotskills

Install or upgrade MegaLinter on a repository. An agent skill from nvuillam/github-dependents-info.

nvuillam/github-dependents-info

Push py4vasp changes to origin and open a PR. An agent skill from vasp-dev/py4vasp.

vasp-dev/py4vasp

A skill your agent uses when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough.

tech-leads-club/agent-skills

Deeply analyze any empirical economics PDF using the five-question framework (五问框架): research question, identification strategy, core estimand, robustness logic, and scholarly contribution.

brycewang-stanford/Auto-Empirical-Research-Skills

Orchestrate endgame verification for a GitHub milestone issue.

microsoft/copilot-for-eclipse

Jalankan "Kantor Agent" — kantor 3D (three.js) tanpa konfigurasi di http://127.0.0.1:8788/kerja yang menampilkan apa yang sedang dikerjakan Claude di project ini.

humaedihume/kantor-agent

Runs a multi-task implementation plan by sending each task to a fresh implementer subagent, reviewing it independently, then reviewing the whole branch.

HoangNguyen0403/agent-skills-standard

Code and plan review with multi-angle dispatch. An agent skill from KaimingWan/oh-my-kiro.

KaimingWan/oh-my-kiro

Builds a structural map of a large or unfamiliar codebase by dispatching sub-agents to summarize regions, keeping the main context small.

yologdev/yoyo-evolve

Multi-agent brainstorming and strategic thinking on any complex topic.

Aedelon/claude-code-blueprint

Complete reference for decision-lab (dlab). An agent skill from pymc-labs/decision-lab.

pymc-labs/decision-lab

Runs Gemini CLI once in headless JSON mode for repository analysis or coding work, keeping its approvals read-only unless you ask for changes.

CherryHQ/cherry-studio

Runs GitHub Copilot CLI non-interactively on a repository task and reads its JSONL output, denying tools by default so nothing changes unless you ask.

CherryHQ/cherry-studio

Sends a bounded task to MiniMax Code with mcode exec, passing the smart permission mode for analysis and never the full one.

CherryHQ/cherry-studio

Runs the local OpenClaw main agent once with a JSON message and judges success from the returned payload, not only from the exit code.

CherryHQ/cherry-studio

Runs OpenCode once with opencode run and reads its JSON event stream, leaving its default denial of permission prompts in place for analysis.

CherryHQ/cherry-studio

Runs the Pi agent in sessionless JSON mode and limits it to read-only tools for analysis, since Pi has no approval prompt of its own.

CherryHQ/cherry-studio

Runs the Qoder CN CLI statelessly with JSON output and accepts the result only when the is_error field says the task succeeded.

CherryHQ/cherry-studio

Runs Qwen Code headlessly with JSON output for repository work, using restricted approvals and bounded turn limits, and never the --yolo flag.

CherryHQ/cherry-studio

Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- Code Mode (collapse many tool calls into one sandboxed Python execution), a filesystem and shell…

pydantic/skills

Route Harness Starter Kit workflows. An agent skill from harnessworks/harness-starter-kit.

harnessworks/harness-starter-kit

Local preview of the strands-agents/devtools /strands review agent.

strands-agents/harness-sdk

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test…

Dimillian/Skills

Writes plain-English integration test specs with verifiable steps and expectations, then runs each one through a subagent that reports pass or fail with logs.

av/mi

Pre-PR code review gate. An agent skill from ByteDance-Seed/VeOmni.

ByteDance-Seed/VeOmni

Has a separate agent review a code change without editing it, checking behavior, security, regressions, complexity, tests and docs before merge.

owainlewis/blueprint

Protocol that evo optimization subagents follow when dispatched from /optimize.

evo-hq/evo