Best subagents skills, page 17

Orchestrate multi-repo, multi-mission Spec Kitty programs across dependencies, parallel agents, review gates, merge, and post-merge closeout.

spec-kitty/spec-kitty

Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change, reading any source the task names outside this repo.

tobihagemann/turbo

ANALYSIS SKILL — Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work.

jonathan-vella/apex

A skill your agent uses when about to claim completion: 'done', 'fix complete', 'tests pass', 'build succeeded', 'shipped', 'no regressions', 'ready to merge', 'ready to ship'.

FerroxLabs/ijfw

Implement a technical design by decomposing it into dependency-ordered vertical slices, executing each with TDD red-green, reviewing each via an isolated sub-agent, and persisting progress to a…

open-octo/octo-agent

Run adversarial review on a PM artifact via the pm-critic sub-agent.

product-on-purpose/pm-skills

Multi-agent stock trading signal analysis framework with two-round debate mechanism.

LeoYeAI/openclaw-master-skills

Spawn and manage autonomous background agents for parallel work

vellum-ai/vellum-assistant

Generate /aidd-fix delegation prompts for a list of tasks and optionally dispatch them to sub-agents in dependency order.

paralleldrive/aidd

Run a sequential pipeline of tasks defined in a markdown file: parse the list, then delegate each step to an isolated subagent via the Task tool.

paralleldrive/aidd

Notion-as-source-of-truth dispatch board for running your work like an AI agency.

jeremylongshore/tons-of-skills-marketplace

Codex workflow mastery for .NET developers. An agent skill from Resgrid/Core.

Resgrid/Core

Reviews an architecture-bearing development plan against strict Sesori architectural rules.

sesori-ai/sesori_apps_monorepo

Orchestrate the complete implementation lifecycle from requirements to deployment

shinpr/claude-code-workflows

Summon shadow clones: genjutsu's full-scale pipeline for a whole website or web app, from scratch or as a full redesign.

AThevon/genjutsu

A skill your agent uses when the user asks to create, build, generate, scaffold, or plan a new workflow.

growthxai/output

迭代执行流水线开发计划阶段。基于 spec.md 调用 /speckit.plan 以测试驱动开发模式构建 开发计划、技术调研与数据模型，并在同一 subagent 内就地做文档级合规自检，产出 plan-report.md。

TencentBlueKing/bk-bcs

迭代执行流水线任务生成阶段。基于 plan.md / research.md 调用 /speckit.tasks 生成全量任务， 随后调用 /speckit.analyze 验证产物合规。两段命令通过两次 subagent 隔离执行。

TencentBlueKing/bk-bcs

Bridges Claude Code and Codex sessions when native tools can't reach the target.

daymade/claude-code-skills

Multi-path parallel product analysis with cross-model test-time compute scaling.

daymade/claude-code-skills

Compare two sessions side-by-side using Agent Monitor data — per-model token usage (input/output/cacheread/cachewrite + compaction baselines), pricing engine cost breakdowns, workflow intelligence…

hoangsonww/Claude-Code-Agent-Monitor

Debug a specific session by inspecting its full event chain (PreToolUse, PostToolUse, Stop, SubagentStop, Compaction, APIError, TurnDuration, Notification events), agent hierarchy (recursive…

hoangsonww/Claude-Code-Agent-Monitor

Summarize a sprint's worth of Claude Code activity — sessions grouped by project (cwd), per-model cost breakdown, token efficiency (cache hit rate, compaction baselines), subagent effectiveness from…

hoangsonww/Claude-Code-Agent-Monitor

Analyze workflow patterns using the Agent Monitor's workflow intelligence API — orchestration DAGs, tool flow transitions, subagent effectiveness, model delegation patterns, error propagation by…

hoangsonww/Claude-Code-Agent-Monitor

Parallel multi-AI cross-validation research workflow (大版本). An agent skill from majiayu000/spellbook.

majiayu000/spellbook

Create file-based sub-agents as Markdown files following the OpenHands SDK format.

OpenHands/extensions

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality.

OpenHands/extensions

Review changed code for reuse, quality, and efficiency using a team of persistent named reviewers.

NikiforovAll/claude-code-rules

Understand the components, mechanics, and constraints of context in agent systems.

NeoLabHQ/context-engineering-kit

Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects.

claesbackman/AI-research-feedback

規模に応じた計画、承認、実装、検証、エスカレーションのフローでサブエージェントを調整。サブエージェントへの作業振り分け、承認済み作業計画の実行、自律実行の再開時に使用。

shinpr/ai-coding-project-boilerplate

Fan out a batch of autopilot-queued issues to parallel background worktree subagents — each runs /autopilot at the build model from its 'model:' label — with a gating review at Opus 5 or above and…

joshukraine/dotfiles

Triggers the QA Test Runner subagent to reproduce failures and interpret logs.

GoogleCloudPlatform/magic-modules

Checks sync status and invokes the subagent to align repositories if needed.

GoogleCloudPlatform/magic-modules

Draft a new Claude Code subagent at .claude/agents/<name.md, using the official subagents format.

CorridorTech/PoseCap

View and configure settings for coding agents (Claude Code, Codex CLI, OpenCode, Devin CLI/Desktop, and others).

CodeAlive-AI/ai-driven-development

A skill your agent uses when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task, reviews once per phase, loads phases just-in-time…

ed3dai/ed3d-plugins

Diagnose and plan fixes for errors/bugs with Codex-first multi-agent collaboration (Codex + Opus 4.6 + Agent Teams).

DeL-TaiseiOzaki/claude-code-orchestra

The agent's configuration surfaces: Settings › Agent pages (Instructions, Memory, Skills, Files, Sub-agents) and the full-page AgentTabsPage (resources, Snapshots, Agent integrations, Automations…

BuilderIO/agent-native

Unified Agent Teams orchestrator for Diverga v12.0.0. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

brycewang-stanford/Auto-Empirical-Research-Skills

Conducts comprehensive research across this Shopsys project using parallel specialized subagents, then writes a self-contained research document.

shopsys/shopsys

Searches multiple web sources, synthesizes findings, and produces cited research reports using delegated subagents.

brycewang-stanford/Auto-Empirical-Research-Skills

Convene an AI executive board of directors (CEO, CFO, COO, CLO, CISO sub-agent personas) to vet a business idea, product concept, new service offering, M&A target, or operational initiative — and…

davepoon/buildwithclaude

Quality-first per-stage model routing AND a pre-flight cost gate for Claude Code dynamic workflows.

davepoon/buildwithclaude

Propose and, after approval, configure a personalized team of Codex subagent roles based on the user's profile, goals, and working style.

kbanc85/claudia

Call nodetool.agents from a code action: hand a self-contained task to a sub-agent, fan several out in parallel, or start background sub-agents and collect their results later.

nodetool-ai/nodetool

Call nodetool.memory, nodetool.shared or nodetool.threads from a code action: save and recall durable notes and resources across conversations, pass results between steps and sub-agents in one run…

nodetool-ai/nodetool

Use a sub-agent (like generalist) to perform repetitive code transformations across multiple files in a single turn.

r3bl-org/r3bl-open-core