Agent Workflows · For developers

Build MCP servers for customer care agents following Watson Orchestrate specifications.

IBM/ibm-watsonx-orchestrate-adk

Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles.

zjunlp/SkillNet

Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.

automagik-dev/genie

Persistent per-project memory for KMP Starter Template apps.

DevAtrii/Kmp-Starter-Template

A skill your agent uses when writing or modifying the kimi-code terminal UI in apps/kimi-code/src/tui — components, dialogs/selectors, slash commands, themes, streaming render, or the KimiTUI…

MoonshotAI/kimi-code

Generates or refreshes a project's shared repository context file so both Codex and Claude work from the same up-to-date knowledge layer.

withkynam/vibecode-pro-max-kit

Builds a feature backlog, progress log, and optional strict test enforcement for agent-driven work with a single init command.

mylukin/agent-foreman

Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness.

pydantic/pydantic-ai

A skill your agent uses when managing Lanes issues or driving Claude Code sessions through the lanes MCP tools — creating issues, starting/stopping/inspecting sessions, batch-launching work across…

lanes-sh/app

Change-aware next step advisor. An agent skill from sd0xdev/sd0x-harness.

sd0xdev/sd0x-harness

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

swarmclawai/swarmclaw

Explains when to call MemOS's own memory tools to search past conversations, after the automatic per-turn recall hook comes up empty.

MemTensor/MemOS

Synchronize all documentation surfaces after code changes. An agent skill from JayFarei/opentraces.

JayFarei/opentraces

Shape delivery workflow around backlog quality, roles, ceremonies, and engineering feedback.

managedcode/Storage

Build and review high-quality technical docs as well as agent instruction files in your repository.

openclaw/openclaw

Systematic debugging with persistent state across context resets

SpillwaveSolutions/agent-brain

OPC — One Person Company. An agent skill from iamtouchskyer/opc.

iamtouchskyer/opc

Author or review AgentSkills: create, repair, validate, or restructure SKILL.md files and bundled resources.

openclaw/openclaw

Bundles a local MCP server together with its runtime into one installable file, so a user doesn't need Node or Python set up themselves.

anthropics/claude-plugins-official

Reference for spawning, listing, monitoring and stopping agents with claude-flow commands, with agent type families, routing codes and coordination tips.

ruvnet/ruflo

AI 判断改动为链路改动或治理改动时自动调用（不需要用户手动触发），在 docs/projects/{YYYYMMDD}-{项目名}/ 下创建项目目录和核心文档（概览、方案、任务、验证）。跳过条件：单项目改动、纯讨论/探索性问题不调用。

ljxpython/ai-agent-platform

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services.

microsoft/skills

Drive structured autoresearch iteration after evo:discover and the baseline commit.

evo-hq/evo

Take a branch from "code exists (or is about to)" to "ready for Ben's final review" — multi-axis subagent review with verified findings, fixes, ci:check, checkpoint commits, and an updated PR.

VladSez/easy-invoice-pdf

Interview-before-research grilling session that challenges a fuzzy ask against the existing codebase, sharpens vocabulary against CONTEXT.md, and resolves the decision tree branch by branch.

alexandremendoncaalvaro/CorridorKey-Runtime

Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode.

CodeAlive-AI/ai-driven-development

Triggers when the master Agent faces a multi-step complex task and is deciding whether / how to outsource sub-tasks to built-in subagents (browser / doc-editor / data-analyst / extractor /…

OpenLoaf/OpenLoaf

Generate ideas via named methods from creative practice. An agent skill from NousResearch/hermes-agent.

NousResearch/hermes-agent

Drive the @swamp/issue-lifecycle model for interactive issue triage and plan iteration against swamp-club lab issues.

swamp-club/swamp

A skill your agent uses when starting any conversation - establishes how to locate and invoke skills, mandating Skill tool usage before ANY response including clarifying questions

NoobyGains/godmode

Structured fortune-telling workflow skill using MCP tools. An agent skill from tradecatlabs/fatecat.

tradecatlabs/fatecat

Work with local LibriScribe book projects through its MCP tools.

guerra2fernando/libriscribe

Interviews you about what a skill should do, writes an eval spec from your answers, then loops through run, diagnose and improve until the skill is ready to ship.

edonadei/caliper

Every AGENTS.md must have a sibling CLAUDE.md symlink pointing to it.

pdparchitect/noodle

Skills for accessing and searching docs in DeepWiki/GitHub’s public code repositories can help users understand open-source project source codes, and users can also ask questions directly about the…

aahl/skills

Scaffold and build Claude Code skills from plans or descriptions.

AgriciDaniel/skill-forge

Delegates repository analysis or implementation to the Codex CLI in a single non-interactive run, with a read-only sandbox by default.

CherryHQ/cherry-studio

Adds an MCP server to Warp's global or project-level config file, keeping existing servers and choosing between command-based and URL-based setups.

warpdotdev/warp

Collaboration protocol for Ralph loop (Plan → Act → Reflect → Refine).

GetStream/stream-chat-react

Admin and maintenance workflows for Ogham shared memory. An agent skill from ogham-mcp/ogham-mcp.

ogham-mcp/ogham-mcp

Convert user conversation into macro workflow requests and present curated clarification or final artifacts.

SeemSeam/claude_codex_bridge

Activate, switch, combine, or close TavernWeave Soul as a portable current-task teaching overlay with 阿瞳 for warm guidance, MTTT.sir for strict learning examination, 灵魂杀手 for blunt frontend and…

LiarMTTT/TavernWeave

A skill your agent uses when user explicitly requests planning with files, or asks for persistent tracking of a complex task.

NikiforovAll/github-copilot-rules

[power-bi] Power BI Requirements Gathering — a structured, conversation-driven skill that captures everything needed before building a Power BI solution.

lukasreese/powerbi-claude-skills

Learns the words a user habitually writes to their coding agent that make its answers worse ("be 100% sure", "don't assume", "full review", "are you sure?", "all fine, right?"), from what they…

joetawil7/first-pass

为 Vivado 工程建立或审查 XDC 时钟、I/O 延迟和时序例外，依据板级与接口参数验证对象和约束覆盖；不猜引脚、频率或外设时序，不用例外掩盖违例。

mapleleavessssssss-wq/vivado-mcp

Check whether Claude Code CLI is ready in this environment and optionally toggle the turn-end review gate.

sendbird/cc-plugin-codex

Produce an experiment blueprint from a research hypothesis. An agent skill from OpenRaiser/NanoResearch.

OpenRaiser/NanoResearch