Best subagents skills, page 11

Review uncommitted or PR diffs in the personal-assistant Obsidian plugin with project-specific risk lanes, second-layer future-risk checks, severity discipline, subagent review routing, and…

edonyzpc/personal-assistant

Drives the entire local inner loop in one invocation, as a conductor over the skills that own each role.

FHIR/fhir-codegen

Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes.

Dimillian/Skills

Spawns a team of coordinated agents on a shared task list, with optional agent types, a team size from one to twenty and a Ralph retry loop.

Yeachan-Heo/oh-my-claudecode

Rewrite Spectre subagent definitions into compact, contract-driven agents with clear routing, least-privilege tools, output schemas, and an auditable rewrite trail.

joenandez/spectre

This skill should be used when decomposing a spec into a multi-agent implementation plan with dependency ordering, parallelism decisions, contract testing, and verification strategy.

jacob-dietle/context-os

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

garrytan/gbrain

检查、报告、修复 Skills 间链接内容不同步，以及 Skills↔Docs 内容链接不同步。逐文件检查，最大化并发 subagent。Use when: skill 同步、skill 断链、skill 引用、skill 过时、skill audit、skills 一致性、skill 检查、skill↔docs。

ncatbot/NcatBot

Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history into a choices ledger, changes no code, and never blocks an unsupervised run.

dzhng/skills

Patterns for running multi-agent swarms on research, development and testing work, with four topologies and a four-phase research swarm built on claude-flow MCP tools.

ruvnet/agentic-flow

A skill your agent uses when decomposing a hardened spec into tracker issues: cutting tracer-bullet vertical slices through every layer, ordering structural work first with blocking edges…

DanMcInerney/architect-loop

This skill should be used when the user wants to file their tax return electronically via the 確定申告書等作成コーナー (NTA Tax Return Preparation Corner) using Claude in Chrome, Antigravity Browser Sub-Agent…

kazukinagata/shinkoku

Multi-agent workflow orchestration. An agent skill from KonghaYao/peri.

KonghaYao/peri

CRITICAL skill for executing multiple Task tool calls in a SINGLE message for true parallelism.

CloudAI-X/opencode-workflow

agystack's agentic engineering framework and rigor mode. Runs poteto-mode playbooks, isolated subagents, and cloud swarms. Use for /agystack…

jtaroreh/agystack

Multi-angle codebase exploration spawning 3-5 parallel agents for code structure, data flow, architecture patterns, and health assessment.

yonatangross/orchestkit

Decides, once a task is finished, whether the outcome deserves a loopany record and routes it to the right artifact kind through a quality gate.

superdesigndev/loopany

When GitHub Actions fails, fetch failing job logs and assign each failing job to a separate subagent that fixes its slice of the problem in parallel.

spencerpauly/awesome-cursor-skills

INTERNAL sub-agent for blind 7-dim rubric scoring. **NOT a user-facing skill — do NOT invoke from main conversation.** Called via Task tool by…

XBuilderLAB/cheat-on-content

Reviews the scripts' user-facing terminal output by running it past subagent reviewers role-playing a first-time user, then reports severity-ranked findings.

antoinecellerier/speaker-tuning-to-easyeffects

Run work through subagents instead of the main thread. An agent skill from tola-rs/tola-ssg.

tola-rs/tola-ssg

Connects an MCP client to the Forgetful memory server over stdio or HTTP, then confirms the link works with discovery and round-trip calls.

ScottRBK/forgetful

Field-test a skill by running it cold in parallel agent sessions, then turn what they hit into edits.

will-ness-ai/skills

Review the current change set from an opposing harness-engineering perspective.

harnessworks/harness-starter-kit

Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything.

hanzili/hanzi-browse

Takes an agreed task from intent to working code: splits it into units, implements the smallest correct change, verifies as it goes and reports what is left.

Yeachan-Heo/oh-my-claudecode

Optimize token usage and context management. An agent skill from rohitg00/pro-workflow.

rohitg00/pro-workflow

Vibe Coding 流水线的实现阶段(流水线终点,顺序 idea → interaction → architecture → design → prototype → implement)。当 interaction.md、architecture.md、design.md、prototypes/ 已就绪,用户说"开始实现""写代码""把设计落地""进入开发""implement /…

idiotLeoLYJ/Daliu-Awesome-Skills

A skill your agent uses when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt…

NeoLabHQ/context-engineering-kit

Delegate work from one AG2 beta Agent to another. An agent skill from ag2ai/build-with-ag2.

ag2ai/build-with-ag2

Drive OpenAI's Codex CLI (codex exec) as a non-interactive coding sub-agent from inside Claude Code.

kortix-ai/suna

For CLI agents WITHOUT subagent support (e.g., Codex CLI). An agent skill from pchalasani/claude-code-tools.

pchalasani/claude-code-tools

Decompose large tasks across parallel agents — use for migrations, multi-file refactors, or batch work

nyldn/claude-octopus

Investigates what went wrong in a superpowers session by reading its transcript, reports findings with path and line citations, and can draft a GitHub issue or redacted bundle.

jnMetaCode/superpowers-zh

Checks every subagent prompt before spawning, swapping pasted files and context for paths and short summaries and trimming the brief, to avoid multiplied token cost.

LichAmnesia/lich-skills

Patterns for parallel subagent execution using the Agent tool (formerly Task).

CloudAI-X/claude-workflow-v2

Phase 3 of the loop pipeline for lago-front. An agent skill from getlago/lago-front.

getlago/lago-front

Optimize a vague subagent brief into a structured Agent task brief carrying falsifier, invariant, source-citation rule, and concrete-noun anchors.

Cranot/roam-code

One-shot profile analysis for seq-db — turns pprof profiles (and optional metrics/report) into a ranked list of concrete, profile-grounded optimization opportunities for the code.

ozontech/seq-db

Workflow orchestration for complex coding tasks. An agent skill from brianlovin/agent-config.

brianlovin/agent-config

当用户修正了 AI 行为、提出改进意见、或 Skill 执行后需要记录效能评估时，由 feedback-observer sub-agent 调用。

riowang88/tvbox-source-aggregator

Orchestrates modular PyTorch profiler trace analysis with TraceLens: generates perf reports, prepares category data, runs system-level and compute-kernel subagents in parallel, validates outputs…

amd/skills

End-to-end playbook for working a GitHub issue (or bug-fix PR) on nubjs/nub: triage → acknowledge an external report with an "Investigating" comment → reproduce it yourself → SIZE it → fix it at…

nubjs/nub

Pattern GSD (Get Shit Done) - découper en tâches atomiques avec contextes subagent frais pour combattre le context rot.

TheBeardedBearSAS/claude-craft

Coordinate bounded subagent work for analysis, coding, review, simulation, research, and handoff tasks.

cyfung1031/userscript-supports

Research patterns, ecosystem tools, and best practices before writing a design.

Smana/cloud-native-ref

Leads a small team of Qwen Code teammates: read-only investigators work in parallel, then one writer pinned to a git worktree makes the changes.

QwenLM/qwen-code

Orchestrates JUCE plugin implementation through stages 1-3 (Foundation, DSP, GUI) using subagent delegation with automatic validation after each stage.

glittercowboy/plugin-freedom-system