Best agent workflow skills, page 17

Places, routes, travel times, distances and weather in China through the 高德地图 (Amap) MCP server.

nano-muse/nanoMuse

Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

yologdev/yoyo-evolve

Recall this repository's OwnMem local memory before changing code, and keep it healthy.

grpcer/ownmem

Breaks a project into dependency-aware Tasks on an Agent Kanban board through Realmroot Toolbox, previews them for approval, then follows each Task through review.

saltbo/agent-kanban

PromptScript language expert for reading, writing, modifying, and troubleshooting .prs files.

mrwogu/promptscript

Create, update, and audit repository-local agent skills against the current LLM Gateway codebase.

theopenco/llmgateway

Builds AI chat interfaces and conversational UI with streaming responses, context management, and multi-modal support.

ancoleman/ai-design-components

Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit.

srid/emanote

Track tickets, issues, and progress for your project. An agent skill from Storybloq/storybloq.

Storybloq/storybloq

Execute plan tasks sequentially using subagents. An agent skill from umputun/cc-thingz.

umputun/cc-thingz

Wiring a new tool the AI agent can call (not the recon pipeline): the tool registry, the phase map, the hardcoded dispatch chokepoint, and the duplicated execution paths that make a tool work in…

samugit83/redamon

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review.

meshery/meshery-operator

Build observe-only Polymarket and Kalshi tennis market tooling on the polymarket-tennis Python package (MIT) plus the Live Tennis API free tier.

livetennisapi/livetennisapi-mcp

Project workflow for invoking the local review sub-agents Thomas, Helen, Beck, Jonas, The Reaper, and Heckler during LibreQoS coding sessions.

LibreQoE/LibreQoS

Coordinates and recovers multi-stage Light research projects from a single passport file, with checkpoints, stale-work tracking and rerouting only when you approve.

Light0305/Light-skills

Orchestrate complex Codex coding work with GPT-6.1 Sol at medium reasoning as planner/integrator and reviewer and GPT-6 Luna at max reasoning for exploration, implementation, testing, and research.

donvito/codex-astra-luna-orchestrator

Install and configure Mnemosyne as a Hermes Agent memory provider — local SQLite with vector search, episodic consolidation, and temporal knowledge graphs.

mnemosyne-oss/mnemosyne

A skill your agent uses when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final

Norman-bury/research-writing-skill

Build multi-platform chat bots with Chat SDK (chat npm package).

databuddy-analytics/Databuddy

A production-grade framework for long-running, autonomous agents based on Harness Engineering principles.

thu-nmrc/OpenHarness

Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

Oleafly/Oleafly

Validates an Agent Skill package against a portable contract with a Python checker, then picks the smallest set of instruction, capability or lifecycle primitives for the task.

rohitg00/ai-engineering-from-scratch

Analyzes, generates, and enhances CLAUDE.md files for any project type using best practices, modular architecture support, and tech stack customization.

alirezarezvani/claude-code-skill-factory

Audits the AI skills installed for a project for duplicate names, broad triggers and conflicting instructions, without changing any of them.

Qiuner/birdview

需求澄清 Skill。当用户只给了模糊描述时自动触发，通过业务提问把一句话翻译成完整需求，交给 Boss 流水线执行. An agent skill from echoVic/boss-skill.

echoVic/boss-skill

Generate professional UI/UX designs as layered PSD-like outputs with transparent layers.

bobbyz1x2c3/layer-designer

Manage agent skill dependencies with dotagents. An agent skill from getsentry/sentry-wizard.

getsentry/sentry-wizard

创建高效技能的指南。当用户想要创建新技能（或更新现有技能）以扩展 Claude 的能力，包括专业知识、工作流程或工具集成时，应使用此技能。

LeastBit/Claude_skills_zh-CN

创建、重构或验收可复用技能包。适用于把重复工作流做成跨宿主能力包，并明确触发规则、第一动作、渐进加载、资产模板、脚本校验、触发评测、基线对比、验收证据、闭环治理、公开交付边界和不可伪造的运行证明；也适用于清理冗余参考、拆分人读模板与机器结构数据、补齐首次公开前的验收记录、记录运行反馈、生成写回或不写回决定。当用户提到"做一个 skill / 改 skill / 优化 skill / 评审…

KimYx0207/Kim_Service

Runs a four-part diagnostic on the mem0 plugin, checking the API key, identity resolution, memory search and memory write, then reports one pass-or-fail summary.

mem0ai/mem0

Runs an evidence-bound audit, daily or weekly review through the requirement-ledger CLI, binding scope and authority first and blocking the final report until a handoff check passes.

adand-91/gpt-6-astra-skill

Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases.

10xChengTu/harness-engineering

Find and read papers from the local papers library (repo papers/, mounted at /papers/).

CamusGIT/EvoQuant

Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP.

ojowwalker77/BonsAI

Toolkit for creating and validating skills and subagents. An agent skill from rfxlamia/skillkit.

rfxlamia/skillkit

Gives an agent working in a Go codebase a structural view through a local MCP server: call graphs, blast-radius and impact analysis, and bounded first-call exploration.

ozgurcd/gograph

Drafts and reviews /goal prompts for long-running autonomous agents, turning a vague request into a completion contract with outcome, evidence, constraints and a stop condition.

Michaelliv/pi-goal

Documents the metabot teams command surface for creating durable teams, spawning teammates, dispatching tasks and inspecting their runs across engine sessions.

xvirobotics/metabot

Orchestrates work across specialized AgentRQ workspaces, breaking goals into tasks, assigning them to the right workspace agent, and tracking shared learning notes.

agentrq/agentrq

Start a new task in an isolated Git worktree branched from origin/main so multiple agents can work on the same repo in parallel without conflicts.

michaelshimeles/skills

Writes, optimizes, compresses or audits prompts and Skill instructions for GPT-6 Astra, delivering a copyable prompt by default without executing the task it describes.

gnipbao/gpt6-prompt-writer

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems.

muratcankoylan/Agent-Skills-for-Context-Engineering

A skill your agent uses when starting an issue, bugfix, feature, or refactor that should be driven by multiple coordinated subagents: explore → plan → code → review, with the main agent acting as…

HuangPuStar/FenixAgent

Scaffolds, edits, reloads and debugs a canvas extension that the GitHub Copilot CLI can open in its side panel.

github/gh-aw

Explains how cognee stores session memory by session_id and bridges it into the permanent graph with improve(), including the stages, results and settings.

topoteretes/cognee

Makes persistent agent memory pay off by searching before work starts and saving each decision the moment it settles, rather than batching a summary at the end.

rohitg00/agentmemory

Create, edit, improve, or audit skills for SwarmClaw agents.

swarmclawai/swarmclaw

Use only when user explicitly invokes $loop. An agent skill from breezewish/CodexPotter.

breezewish/CodexPotter