Best subagents skills, page 12

Local claude-code documentation reference (latest). An agent skill from olorehq/olore.

olorehq/olore

Triages open GitHub issues and pull requests with the gh CLI, optionally merging ready PRs, closing resolved issues with evidence and assigning local priority and size estimates.

trailofbits/skills

Strategic Codex model selection for .NET development workflows.

Resgrid/Core

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

How and when to delegate work to subagents via the subagent tool (Explore, Plan, General).

PostHog/code

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

affaan-m/ECC

To build an AI harness: run, observe, validate, automate repeated work faster — CLI/MCP actions, devcontainers, skills, subagents, hooks, pipelines, automations.

griddynamics/rosetta

Software development delivery SOP for an Orchestrator agent.

kid0317/crewai_mas_demo

Design and write deterministic multi-agent workflow scripts (.js files in .claude/workflows/) for Claude Code's Workflow tool.

alirezarezvani/claude-skills

Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

CorridorTech/PoseCap

Safe-use reference for the optional Aside browser agent (the aside command-line tool and its MCP server), which works inside the operator's own logged-in browser.

modu-ai/moai-adk

Suede Labs agent-team orchestrator: split complex work into coordinated lanes with explicit file ownership, WIP collision detection, quality gates, escalation thresholds, rollback plans, and…

JasonColapietro/suede-creator-skills

A skill your agent uses when executing a pre-registered analysis plan with mostly independent steps in the current session

K-Dense-AI/science-superpowers

Splits substantial coding or repository-review work between a Sol commander that decides and verifies and a separate Luna Max worker that implements, with an auditable run log.

majiayu000/spellbook

Analyze an open-source project from What/Why perspective (not how-it's-implemented).

team-attention/hoyeon

Explore a large codebase in parallel by launching multiple explore subagents that each investigate a different area simultaneously.

spencerpauly/awesome-cursor-skills

Builds with and operates Pi, the minimal terminal coding harness.

K-Dense-AI/scientific-agent-skills

Quality gate. An agent skill from macro-inc/macro.

macro-inc/macro

Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file.

eric-tramel/moraine

Launch both thermo-nuclear review subagents in parallel, then synthesize their findings.

cursor/plugins

Orchestrates group discussions between installed BMAD agents, enabling natural multi-agent conversations where each agent is a real subagent with independent thinking.

delorenj/mcp-server-trello

Orchestrate English→Japanese translation of po/ja.po — classify, delegate translation/review to subagents, iterate until clean

natsukium/dotfiles

Creates Cursor-specific AI subagents with isolated context for complex multi-step workflows.

tech-leads-club/agent-skills

Guide for creating AI subagents with isolated context for complex multi-step workflows.

tech-leads-club/agent-skills

Feature auto-development — clarify requirements, generate spec, dispatch dev sub-agent to implement and merge into current branch

ZhangShenao/harness9

Expert guidance for creating, building, and using Claude Code subagents and the Task tool.

glittercowboy/taches-cc-resources

Orchestrate a multi-repo, multi-mission Spec Kitty program end-to-end: run specify → plan → tasks → implement → review → merge → mission-review → post-merge fixes across several repositories in a…

spec-kitty/spec-kitty

Multi-source research synthesis — aggregate and compare 3+ sources or any source 5KB using sub-agent dispatch and SharedState

yologdev/yoyo-evolve

Delegate work to builtin or custom subagents with single-agent, parallel, forked-context, and intercom-coordinated runs.

bastani-inc/atomic

Review changed Touch'N'Stars code with three parallel agents, one each for functionality, UI and maintainability, against this project's own rules (NINA/PINS dual mode, polling contract…

Touch-N-Stars/Touch-N-Stars

A skill your agent uses when creating specialized subagents for Claude Code plugins or the Task tool - covers description writing for auto-delegation, tool selection, prompt structure, and testing…

ed3dai/ed3d-plugins

60-Second Property Snapshot — quick assessment without subagents for fast property evaluation with signal, key factors, and CTA for full analysis

zubair-trabzada/ai-realestate-claude

Timeboxed ideation on a topic using propose-and-critique subagent pairs.

av/mi

eve framework guidance for durable AI agents and agent-powered applications.

vercel/vercel-plugin

Before handing work to parallel agents: generate the brief with pnpm brief:new (port, owned files, scratch, checks, landing) and add the task, decisions and acceptance.

wlsdks/ontology-atlas

Guides work across Cloud, local, and other available computers, including teleporting conversations, running remote subagents, and transferring files.

letta-ai/letta-code

Distill a book into a coherent set of executable skills. An agent skill from HHU3637kr/skills.

HHU3637kr/skills

A skill your agent uses when starting a new round (substrate-touching / fix-round / admin) to generate a complete handoff doc from scope + prior-round context.

Arch1eSUN/Arcgentic

基于功能设计文档(由 product-feature-tech-design 产出或等价输入)、源码目录、以及测试所依赖的环境信息(例如 PostgreSQL 插件开发需要的 PG 源码/实例、第三方依赖),编排「开发者 ↔ 评审者 ↔ 测试者」三方隔离的实施循环,直至评审通过、且所有测试(新增 + 已有)通过。三方互不可见,测试者绝对不能看到开发者写的代码。完成后输出 markdown…

digoal/blog

Decompose Claude Code work into parallel subagent-friendly streams when the environment permits delegation.

AlexAI-MCP/hermes-CCC

Create a plan for the specified task.

CodelyTV/agent-harness

Dynamic multi-agent workflows — plan first, then orchestrate parallel agents with adversarial verification via the local odw daemon.

sickn33/agentic-awesome-skills

A skill your agent uses when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost…

GanyuanRan/Aegis

A skill your agent uses when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

GanyuanRan/Aegis

A skill your agent uses when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline.

GanyuanRan/Aegis

Strategic Claude model selection for .NET development workflows.

Resgrid/Core

求是方法论的入口与总原则。在每次新的顶层会话开始时加载一次，用「实事求是」约束全部判断，并只在明确适用时把任务路由到对应的方法论 skill；被派遣执行单一具体任务的子 agent 直接跳过。

HughYau/qiushi-skill

A skill your agent uses when a pr-council-review (PR or branch mode) result needs independent corroboration from a different model family before trusting a GREEN verdict — high-stakes…

ffroliva/gflow-cli