Best agent workflow skills, page 173

Designs human-in-the-loop review points for DAG workflows. An agent skill from curiositech/some_claude_skills.

curiositech/some_claude_skills

Master coordinator that delegates to specialist skills, synthesizes outputs, AND creates new skills on-the-fly when needed.

curiositech/some_claude_skills

Validates that a DAG node's output matches its declared JSON schema before passing to downstream nodes.

curiositech/some_claude_skills

Creates Claude subagents equipped with curated skills for solving problems within DAG workflows.

curiositech/some_claude_skills

将当前对话压缩为交接文档（handoff document / session handoff brief），供下一个 agent 接续工作。手动调用 /handoff。

feiskyer/claude-code-settings

Persist and retrieve repository-specific knowledge using AGENTS.md files.

OpenHands/extensions

Weekly agentic idea hunt for the brand. An agent skill from real-simple-labs/parker-brain.

real-simple-labs/parker-brain

Parker's self-improvement governance for the brand — the disposing half of the living layer.

real-simple-labs/parker-brain

WordPress plugin architecture review for Codex. An agent skill from jorgerosal/wordpress-skills.

jorgerosal/wordpress-skills

READ this skill when implementing or configuring animation-style shaders (Toon/Cel Shaders) — including outlines, rim lighting, toon shading, MatCap, emission, dissolve, hatching, or any stylized…

aiskillstore/marketplace

Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects.

aiskillstore/marketplace

This skill should be used when parallelizing multi-issue sprints using git worktrees and parallel Claude agents.

aiskillstore/marketplace

DEPRECATED: This skill has been replaced by mcp-app-builder.

aiskillstore/marketplace

Context management specialist for multi-agent workflows and long-running tasks.

aiskillstore/marketplace

Operate a Famulor workspace through its hosted MCP server, including assistants, conversation history, campaigns, messaging, telephony, knowledge, dashboards, automations, billing, settings…

aiskillstore/marketplace

Comprehensive guide for building Model Context Protocol (MCP) servers with support for tools, resources, prompts, and authentication.

aiskillstore/marketplace

DEPRECATED: This skill has been replaced by mcp-app-builder.

aiskillstore/marketplace

Nx monorepo management skill for AI-native development. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

This skill should be used as the entry gate for build/create/implement requests.

aiskillstore/marketplace

QuantAll（全A解析）MCP —— 股市全市场向量化计算引擎，为 AI 提供本地 Python 计算环境. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Manage Raindrop.io bookmarks with AI assistance. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Help users create high-quality skills by discovering and incorporating proven methodologies from domain experts.

aiskillstore/marketplace

A skill your agent uses when user asks to "build a Solana dapp", "write an Anchor program", "create a token", "debug Solana errors", "set up wallet connection", "test my Solana program", "deploy to…

aiskillstore/marketplace

Sequential subagent execution with two-stage review gates for implementation plans.

aiskillstore/marketplace

Create specialized Claude Code agents on-the-fly. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Manage AI coding agents on a visual Kanban board. An agent skill from aiskillstore/marketplace.

aiskillstore/marketplace

Manage MCP servers - discover, analyze, execute tools/prompts/resources.

secondsky/claude-skills

Autonomous AI agent that modifies and iteratively improves a GPT language model training setup, running experiments within a 5-minute time budget to optimize validation bits-per-byte.

lamm-mit/scienceclaw

Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration

lamm-mit/scienceclaw

A skill your agent uses when an operator or stakeholder request is too vague or conflicting to convert directly into testable scope: ask a bounded question ladder, label assumptions DEFAULT or…

mtarcure/claude-vibe-squad

A skill your agent uses when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent…

mtarcure/claude-vibe-squad

Persistent long term memory for for continuity in ai sessions between providers and codegen tools.

sundial-org/awesome-openclaw-skills

The local task workspace, the build/test commands the hand-off gate runs, and the file and exploration tools.

makifbaysal/tasktrooper

A skill your agent uses when planning a delivery request as the only orchestration agent - one board-writing subtask, backlog first, one approval question, then move approved tasks to todo

makifbaysal/tasktrooper

A skill your agent uses when an analiz task arrives in done (approved) - turn the approved split into implementation tasks with repository, AC, derivedfrom and ordering arguments

makifbaysal/tasktrooper

Evidence rules for completion claims. An agent skill from makifbaysal/tasktrooper.

makifbaysal/tasktrooper

Marks project context as unconfigured until domain constraints, repository quality standards, phase, conventions, and external-resource access are recorded.

shinpr/ai-coding-project-boilerplate

Expert knowledge for Azure Connector Namespace development including configuration.

MicrosoftDocs/Agent-Skills

Verify your current Claude Code Hero quest level. An agent skill from kylesnowschwartz/claude-code-hero.

kylesnowschwartz/claude-code-hero

5-layer testing approach for agent validation including adversarial testing, security validation, and prompt injection resistance

nWave-ai/nWave

Structured divergent thinking techniques — HMW framing, SCAMPER, Crazy 8s mechanics, and option diversity guarantees.

nWave-ai/nWave

Event Modeling facilitation technique — brainstorm events, identify commands and views, define aggregate boundaries, write Given-When-Then specifications

nWave-ai/nWave

GPT Pro(웹 전용·API 없음 — 현 시점 최신 플래그십 모델의 Pro 추론)를 Codex CLI 안에서 활용한다.

fivetaku/gptaku-plugins-codex

AI-powered context management for OpenClaw sessions. An agent skill from aAAaqwq/AGI-Super-Team.

aAAaqwq/AGI-Super-Team

多 Agent 架构设计与智能 Spawn 系统。当需要设计多 Agent 系统、配置专业化 Agent、实现智能任务分发、或优化并发处理能力时使用此技能。

aAAaqwq/AGI-Super-Team

管理Claude Code的全局工具权限配置，自动将MCP命令或其他工具添加到allowedTools中，避免每次使用时都需要手动批准。工作流程：确认用户需要添加的命令 - 确认添加级别(默认全局~/.claude.json) - 执行添加 - 验证并提醒重启。

aAAaqwq/AGI-Super-Team

Audit or update Core's repository instruction system and skill mirrors.

Asymmetric-al/core

Multi-agent UX for OpenClaw Control UI — agent selector, per-agent sessions, session history viewer with search, agent-filtered Sessions tab with friendly names, Create Agent wizard, emoji picker…

LeoYeAI/openclaw-master-skills