Best subagents skills, page 4

A skill your agent uses when creating new Claude Code skills from scratch, editing existing skills to improve their descriptions or structure, or converting Claude Code sub-agents to skills.

metaskills/skill-builder

Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation.

kubefleet-dev/kubefleet

Audit a finished design document for hard-to-read or hard-to-understand paragraphs, then harden the house-style rules so future design docs avoid them.

JetBrains/youtrackdb

Multi-agent SlangPy code review using predefined specialist sub-agents.

shader-slang/slangpy

Use Claude Code as an independent claude -p subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude.

dzhng/skills

COSTLY: Spawns a separate sub-agent CLI session. An agent skill from Wide-Moat/open-computer-use.

Wide-Moat/open-computer-use

Delegate work to subagents or create custom pi-crew agents. An agent skill from melihmucuk/pi-crew.

melihmucuk/pi-crew

Run a document coherence, link integrity, and git repository status audit across repository markdown files using a dedicated subagent.

GoogleChrome/modern-web-guidance-src

Monitor GitHub pull requests through a subagent-based loop that watches CI checks, review comments, PR comments, review state, merge conflicts, and branch freshness.

elastic/terraform-provider-elasticstack

A skill your agent uses when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting.

chmonitor/chmonitor

Runs a goal as a project in which the agent coordinates separate agent threads, judging when to split the work, and interviews you first when nothing can be verified.

asgeirtj/system_prompts_leaks

通过 reasoningeffort、Magic String、组合推理题和离线日期题快速检测当前 API 是否为真实 Claude 模型，并在需要时升级到身份、工具、元数据与嵌套层级的深度审查。用于怀疑模型真假、来源异常、被第三方包装，或需要输出模型真实性检测报告时。

rt22766/claude-skill-model-fingerprint

Splits a large goal into a tree of parallel Cursor cloud agents, with planners, workers and verifiers coordinated by a script and reporting through structured handoffs.

cursor/plugins

All-in-one project configuration and health management. An agent skill from jezweb/claude-skills.

jezweb/claude-skills

Run comprehensive agent-native architecture review with scored principles.

deepklarity/harness-kit

Plans and launches Claude Code agent teams with distinct roles, right-sized tasks and detailed spawn prompts, and says when subagents or worktrees fit better.

lexler/skill-factory

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model.

google/adk-python

Hands a self-contained coding task to Codex, Claude Code, OpenCode or Pi as a non-interactive background process, using OpenSquilla's exec_command and process tools.

TokenRhythm/opensquilla

Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

ruvnet/ruflo

Take a branch from "code exists (or is about to)" to "ready for Ben's final review" — multi-axis subagent review with verified findings, fixes, ci:check, checkpoint commits, and an updated PR.

VladSez/easy-invoice-pdf

Publish an agent session as a readable trace page in Grain, with the story, key moments, every request and step on a timeline, subagents, and the pull requests it opened.

greenfield-inc/Pane

A skill your agent uses when creating or reviewing a Skill package for this Career Agent, including its SKILL.md, progressive disclosure, tool workflow, MCP coordination, subagent boundaries…

low-hands/MyCareer

Execute plans via delegatetask subagents (2-stage review). An agent skill from mateaix/mateclaw.

mateaix/mateclaw

Dispatches the comment-sicko subagent to hunt gratuitous comments in a PR/diff, triages its raw findings, and posts a polite, professional writeup.

Comfy-Org/ComfyUI_frontend

Verify local CI passes before pushing or opening a PR. An agent skill from pulp-platform/snitch_cluster.

pulp-platform/snitch_cluster

Delegates repository analysis or implementation to the Codex CLI in a single non-interactive run, with a read-only sandbox by default.

CherryHQ/cherry-studio

Orchestrate complex Codex coding work for the Pro profile with GPT-6 Astra at medium reasoning as planner/integrator, Luna subagents for exploration, implementation, testing, and research, and an…

donvito/codex-astra-luna-orchestrator

Graph engineering for parallel task execution: convert a task, PRD, SPEC, or issue set into a dependency graph (DAG), layer it into supersteps, then implement each independent node concurrently with…

smallnest/goal-workflow

多轮对抗式稿件打磨技能。通过"批评→改写→综合→盲评"循环，像学术同行评审一样反复打磨稿件直到收敛。所有中间产物（批评、改写、综合、评分）保存为独立文件，完整记录进化过程。当用户说"对抗打磨""反复打磨""深度打磨""多轮润色""盲评打磨""打磨到收敛""帮我把这篇稿子磨一磨""pressure polish""adversarial…

JimLiu/Illustrated-Agent-Skills

Use Hermes Vault as the canonical credential broker for Hermes and persistent sub-agents.

asimons81/hermes-vault

Improve Kandev's AI harness from session learnings or explicit requests.

kdlbs/kandev

Multi-perspective code review for a branch before merging. An agent skill from microsoft/bocpy.

microsoft/bocpy

Cross-runtime playbook for multi-agent collaboration, agent teams, swarm orchestration, parallel task distribution, capability discovery, and quality gates on Claude Code, Codex, OpenClaw, and Cursor.

KimYx0207/Kim_Service

Continue a multi-phase engineering spec from its progress table.

karanhudia/borg-ui

Delegates code generation, editing and explanation tasks to the OpenAI Codex CLI, with commands for interactive, auto-edit, question-only and model-specific runs.

taracodlabs/aiden

Turns course slides, homework files, class code and earlier solutions into concise student-style Markdown answers, with optional subagents for solving and review.

vect-G/lecture-to-hw

Runs one read-only reviewer subagent per configured model against a diff to challenge a change, then synthesizes a single verdict without applying any fixes.

cursor/plugins

Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.

mylukin/agent-foreman

Autonomous performance-optimization loop for seq-db driven by seqbazooka.

ozontech/seq-db

Main-session orchestrator for arcgentic rounds. An agent skill from Arch1eSUN/Arcgentic.

Arch1eSUN/Arcgentic

Drive your own Claude Code session from Basecamp. An agent skill from basecamp/basecamp-cli.

basecamp/basecamp-cli

Generates a security status report based on docs/threats.json by spinning up sub-agents for each threat to compute a quality score.

agent-substrate/substrate

Build batteries-included agents with planning, context management, subagent delegation, and sandboxed execution.

langchain-ai/docs

Runs Phase 4 review/publish/verify for a cli-web- CLI: implementation review by 3 parallel agents, the tiered quality checklist (Tier 1 critical fail-fast, then comprehensive), pip install + smoke…

ItamarZand88/CLI-Anything-WEB

Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

sickn33/agentic-awesome-skills

A skill your agent uses to evaluate architecture, design proposals, refactors, module boundaries, dependency direction, data flow, concurrency model, and maintainability tradeoffs across any codebase.

bbartling/open-fdd

Deep EVM smart contract security audit system. An agent skill from austintgriffith/ethskills.

austintgriffith/ethskills

Three-axis review of the branch diff — Standards (this repo's documented standards + public API surface), Spec (the originating Linear issue / PR), and Correctness (runtime bugs + the SDK threat…

getsentry/sentry-dart