Agent Workflows

Guide to building Node.js and TypeScript apps on the agent-squad package: orchestrator, agent types, classifier routing, storage, retrievers and MCP tools.

2FastLabs/agent-squad

Acts as a skeptical checker for changes an implementer sub-agent made, running the tests, confirming the diff scope and returning approve, reject or escalate to a human.

cobusgreyling/loop-engineering

Self-check your branch before creating a PR — catch dead code, prevent new model-specific Python examples, verify accuracy/perf claims, validate PR title format, and confirm merge readiness.

vllm-project/vllm-omni

A skill your agent uses when a Solo task or thread should become an interactive, reviewable, self-contained HTML artifact for progress/status, review/decision, or comparison/leaderboard work inside…

solo-agent/solo

Generate and operationalize improvement ideas for projects. An agent skill from DavidWells/markdown-magic.

DavidWells/markdown-magic

Create or update skills. An agent skill from HKUDS/OpenOPC.

HKUDS/OpenOPC

Teaches an MCP-connected agent when and how to call Memori's recall, summary, compaction, augmentation, feedback and quota tools to keep context across sessions.

MemoriLabs/Memori

Find and install relevant Omnibot skills. An agent skill from omnimind-ai/OmniBot.

omnimind-ai/OmniBot

Track daily activity logs and summaries for the user. An agent skill from memodb-io/Acontext.

memodb-io/Acontext

A skill your agent uses when implementing, resuming, reviewing, or verifying the DeepSeek++ Codex-style automation feature in this repository.

zhu1090093659/deepseek-pp

Identify documentation gaps and prioritize the docs backlog.

strands-agents/harness-sdk

Gives an agent a set of working rules for any development task: understand first, surface decisions, verify results, and load deeper reference files per scenario.

shareAI-lab/Kode-CLI

Saves a fact, decision or preference the user states into mem0 as written, labeled with a memory type such as decision, convention or user_preference.

mem0ai/mem0

Make every team AI native — TeamAI syncs a team's AI skills, rules, docs and env across AI coding tools. Use when the task operates on team-shared…

Tencent/teamai-cli

Quizzes you on Claude Code in a quick or deep mode, scores your level across 10 topics and recommends what to learn next, in Chinese.

lhfer/claude-howto-zh-cn

Answers questions about the Paseo app, such as setup, providers, connectivity, updates and logs, by checking the current public docs and working out which daemon is involved.

getpaseo/paseo

Turn recorded agent sessions (Beacon traces from Claude Code, Cursor, Codex, OpenCode, and other harnesses) into reviewed, reusable project memory.

Asymptote-Labs/agent-beacon

Shared memory that never forgets. An agent skill from ourmem/omem.

ourmem/omem

Shows how to build a Vibe plugin package in the Agent Plugins 1.0 format, with a plugin.json manifest and optional skills, MCP servers, hooks and other components.

mistralai/mistral-vibe

Shows how to write custom cognee tasks, chain them into pipelines, store custom DataPoints and run enrichment over the existing graph.

topoteretes/cognee

Deletes chosen memories from agentmemory only after showing the matches and getting an explicit yes, for privacy requests and cleanup of outdated notes.

rohitg00/agentmemory

Deep multi-agent code review run locally — a fleet of parallel finder agents reviews the diff from independent angles, then adversarial verifier agents reproduce each finding before it is reported.

dyad-sh/dyad

Has Leon's agent investigate, change and verify code in a repository with its file, search and shell tools, staying inside the scope the owner authorized.

leon-ai/leon

Search and call websites through Unbrowse's hosted API or remote MCP, reuse indexed site tools, read pages, and learn missing routes in its cloud browser.

unbrowse-ai/unbrowse

Understand Microsoft technologies by querying official documentation.

MicrosoftDocs/mcp

Introspect, explain, and improve Ralph Orchestrator using its published llms.txt doc map.

mikeyobrien/ralph-orchestrator

A skill your agent uses when adding, changing, or reviewing an LLM/MCP tool in Trilium (the defineTools definitions under packages/trilium-core/src/services/llm/tools/ —…

TriliumNext/Trilium

Find what is burning CPU in a live app container without restarting it: separate the JS thread from GC and libuv, open the V8 inspector in place with SIGUSR1, take a CPU profile over CDP, and…

activepieces/activepieces

The binding directive for ultrawork mode: evidence-first delivery, a light or heavy process tier, and constant use of memory during the work.

code-yeongyu/lazycodex

Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status…

JamesShi96/project-butler

agent-deck, the terminal session manager for AI coding agents.

asheshgoplani/agent-deck

Add or extend Redis commands in the Lettuce client API end-to-end — a new core command, a family of new commands, an extension to an existing command's options, or a module/area command…

redis/lettuce

Create new agent skills with proper structure, progressive disclosure, and bundled resources.

sanity-io/sanity

Create new agent skills following the Agent Skills specification.

deadlock-mod-manager/deadlock-mod-manager

A skill your agent uses when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically…

GanyuanRan/Aegis

Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.

addyosmani/agent-skills

Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI.

Haohao-end/openagent

Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.

jnMetaCode/superpowers-zh

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks.

dixiyao/FoT

Control a live local SketchForge editor through its MCP server.

Formsmith746/SketchForge-3D

Give an AI agent persistent, cross-session long-term memory through MindMemOS.

mindscale-noah/MindMemOS

Activate when the user types prose ..., opens a .prose.md file with kind: frontmatter, opens a .prose file, or asks for reusable multi-agent orchestration.

openprose/prose

【漫剧老李AIGC 全流程Skill · V6.9.8 轻量版 Multi-Agent】抖音与红果爆款短剧/漫剧工业化编剧与视听导演超级系统。全面支持 OpenClaw、WorkBuddy、豆包智能体/扣子(Coze)等多Agent平台，深度适配 Seedance 2.5/2.0（强制二选一，即梦为次选/历史兼容）＋ MiniMax H3 格式支线（七段式→H3…

lixiaoxiao9888-create/manju-laoli-skill

Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first…

evo-hq/evo

Store user preferences, learnings from tasks, and procedure outcomes.

vectorize-io/hindsight

Runs an unattended iterate-until-verified loop in which a user-set verify command, not the agent's own claim, decides when the task is finished.

tanweai/pua

Set up, resume, inspect, or pause a measured experiment loop in Claude Code or Codex.

drivelineresearch/autoresearch-claude-code

Use when users /learn, save, remember, or distill lessons.

tigerless-labs/autoharness