Find the best CLAUDE.md, AGENTS.md and Claude skills

louislamReads credentialsCopilot instructions

uptime-kuma

louislam/uptime-kuma/.github/copilot-instructions.md

hosted monitoring tool for HTTP(s), TCP, DNS, Docker, etc. Built with Vue 3 (frontend) and Node.js/Express (backend), using Socket.IO for real-time communication. - **Languages**: JavaScript, TypeScript

infiniflowAGENTS.md

ragflow

infiniflow/ragflow/AGENTS.md

Docker entrypoint starts the Go services according to its command-line flags, and the frontend development server uses fixed Go backend proxy routes. The Python API, admin, and workers

infiniflowReads credentialsAGENTS.md

ragflow / web

infiniflow/ragflow/web/AGENTS.md

This file provides guidance to Claude Code (claude.ai/code) when working with the RAGFlow frontend (`web/`). ## Project Overview RAGFlow frontend is a React/TypeScript application built with Vite: - **Components**: shadcn/ui - **Styling

OpenHandsAGENTS.md

OpenHands

OpenHands/OpenHands/AGENTS.md

Repository Notes ## General - This repository is the OpenHands Agent Canvas React/TypeScript frontend. ## i18n workflow - After editing `src/i18n/translation.json`, run `npm run make-i18n` to regenerate `src/i18n/declaration.ts` (gitignored, auto-generated) and `scripts/check-translation-completeness.cjs

OpenHandsReads credentialsSkill

verify-openhands

OpenHands/OpenHands/.agents/skills/verify-openhands/SKILL.md

This skill should be used to "verify OpenHands features", "test the Canvas UI like a user", "drive Agent Canvas", "check a UI change in the real app", "create or update the feature map", "run the daily pass" or "run the weekly feature audit". Ships control-openhands (launch, doctor, browser, LLM profiles, conversations, evidence, map tooling, cleanup) and the maintained map of every user-facing feature.

All-Hands-AIReads credentialsSkill

verify-openhands

All-Hands-AI/OpenHands/.agents/skills/verify-openhands/SKILL.md

This skill should be used to "verify OpenHands features", "test the Canvas UI like a user", "drive Agent Canvas", "check a UI change in the real app", "create or update the feature map", "run the daily pass" or "run the weekly feature audit". Ships control-openhands (launch, doctor, browser, LLM profiles, conversations, evidence, map tooling, cleanup) and the maintained map of every user-facing feature.

home-assistantReads credentialsSkill

custom-integration-sources

home-assistant/core/.claude/skills/custom-integration-sources/SKILL.md

Use a local copy of the latest code of every HACS default custom integration to measure how a core change (deprecation, removal, rename, signature change) affects custom integrations. Use when the user asks which or how many custom integrations use something, wants to check custom integration impact, or asks to sync/update the custom integration sources.

No other project uses it yet

home-assistantSkill

ha-merge-queue

home-assistant/core/.claude/skills/ha-merge-queue/SKILL.md

Finds open Home Assistant pull requests that are genuinely ready to merge, checking CI, the merge-gate statuses, code-owner approval, merge conflicts, requested changes and unresolved review threads. Use when looking for PRs to merge, doing merge-queue triage, or asking for "quick wins" from the open PR backlog.

No other project uses it yet

koala73Reads credentialsllms.txt

worldmonitor

koala73/worldmonitor/public/llms-full.txt

# World Monitor > Real-time global intelligence dashboard — AI-powered news aggregation, geopolitical monitoring, and

lobehubReads credentialsAGENTS.md

lobe-chat

lobehub/lobe-chat/AGENTS.md

create `features` directories inside `src/routes`. ## Development ### Starting the Dev Environment ```bash # SPA dev mode (frontend only, proxies API to localhost:3010) bun run dev:spa # Full-stack dev (Next.js + Vite

lobehubSkill

acceptance

lobehub/lobe-chat/.agents/skills/acceptance/SKILL.md

Verify delivery outcomes on the real product, capture inspected evidence, and deliver an acceptance report with the lh CLI: published to LobeHub when signed in, or rendered as a local offline report when not. Use for product acceptance, manual verification, evidence collection, or publishing an existing report, with or without a supplied plan. Reuse valid evidence; run new verification through bounded, lower-cost agent contexts when available.

lobehubSkill

builtin-tool

lobehub/lobe-chat/.agents/skills/builtin-tool/SKILL.md

Use for LobeHub builtin agent tools: manifests, executors, runtimes, inspectors, renders, streaming and intervention.

lobehubSkill

full-text-search

lobehub/lobe-chat/.agents/skills/full-text-search/SKILL.md

Use for product search: FtsSearchRepo, pg_search/pg_like/Elasticsearch, mapping migrations, projections, Outbox sync, reindexing and performance. Excludes agent web search.

lobehubDeletes or force-pushesSkill

pr

lobehub/lobe-chat/.agents/skills/pr/SKILL.md

Create a PR for the current branch (targets `canary` by default), including splitting one cross-layer branch into ordered stacked PRs so a lower layer (db / shared package / server TRPC) merges before its callers (desktop / CLI / UI). Use when the user asks to create / submit a PR, or to split a branch because clients call a server contract that isn't on the trunk yet. Triggers on 'pr', 'create pr', 'submit pr', 'open a PR', 'pull request', 'split this PR', 'stacked PR', 'backend should merge first', '提 PR', '提个 PR', '新建 PR', '拆 PR', '后端先合', '分层合并'.

lobehubSkill

trpc-router

lobehub/lobe-chat/.agents/skills/trpc-router/SKILL.md

Use for server TRPC routers, procedures and API endpoints in apps/server/src/routers.

bytedanceAGENTS.md

deer-flow

bytedance/deer-flow/AGENTS.md

backend with thread-isolated sandboxes, memory, subagents, skills and MCP tools, and a Next.js frontend. IM channels connect through the Gateway. `CLAUDE.md` imports this file; edit guidance here

bytedanceAGENTS.md

deer-flow / frontend

bytedance/deer-flow/frontend/AGENTS.md

Frontend (`frontend/`) The Next.js web interface: threads, streamed runs, artifacts, the workspace and its settings, and the documentation site. The directory map is in [README.md](README.md#project-structure). Visual

bytedanceCLAUDE.md

deer-flow / frontend

bytedance/deer-flow/frontend/CLAUDE.md

CLAUDE.md The frontend agent guidance lives in [AGENTS.md](AGENTS.md) so it is shared across coding agents (Claude Code, Codex, and others). Claude Code imports it below. @AGENTS.md

bytedanceCopilot instructions

deer-flow

bytedance/deer-flow/.github/copilot-instructions.md

super agent harness". - Backend: Python 3.12, LangGraph + FastAPI gateway, sandbox/tool system, memory, MCP integration. - Frontend: Next.js 16 + React 19 + TypeScript + pnpm. - Local dev entrypoint: root `Makefile` starts backend + frontend + nginx

No other project uses it yet

bytedanceSkill

deep-research

bytedance/deer-flow/skills/public/deep-research/SKILL.md

Use for substantial investigations needing current evidence, source comparison, or synthesis across several dimensions. Scale research to the question and requested depth.

Often used withcommunity-led-growth·academic-paper-reviewer·micro-saas-launcher