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

langgeniusReads credentialsAGENTS.md

dify

langgenius/dify/AGENTS.md

applications, agentic workflows, and RAG pipelines. This monorepo contains the backend API (`api/`), frontend application (`web/`), deployment assets (`docker/`), standalone agent backend (`dify-agent

No other project uses it yet

langgeniusAGENTS.md

dify / e2e

langgenius/dify/e2e/AGENTS.md

runner reuses `web/.next/BUILD_ID` when present. Set `E2E_FORCE_WEB_BUILD=1` to force a frontend rebuild. Use `E2E_BROWSER=webkit` for focused cross-browser runs and `E2E_SLOW

No other project uses it yet

langgeniusAGENTS.md

dify / web

langgenius/dify/web/AGENTS.md

Frontend Workflow - Prefer vinext for frontend development. With a local backend, start the API separately and use `./dev/start-web` or `pnpm -C web dev` for the frontend only; the Dev Container

No other project uses it yet

clash-verge-revAGENTS.md

clash-verge-rev / src

clash-verge-rev/clash-verge-rev/src/AGENTS.md

Frontend Architecture Guardrails These rules supplement the repository's root `AGENTS.md`. - **Contract ownership.** Generated event and notice contracts are owned by the backend wire contract. Handwritten payload types are acceptable

No other project uses it yet

clash-verge-revAGENTS.md

clash-verge-rev / src-tauri

clash-verge-rev/clash-verge-rev/src-tauri/AGENTS.md

contract.** Notifications are typed. Event names, status values and payload shapes stay compatible with frontend producers and consumers. - **Synchronization ownership.** Configuration-write serialization precedes configuration-update ownership, which precedes Core

No other project uses it yet

langflow-aiAGENTS.md

langflow

langflow-ai/langflow/AGENTS.md

visual workflow builder for AI-powered agents. It has a Python/FastAPI backend, React/TypeScript frontend, and a lightweight executor CLI (lfx). ## Prerequisites - **Python:** 3.10-3.14 - **uv:** >=0.4 (Python package manager) - **Node.js

langflow-aiReads credentialsSkill

e2e-testing

langflow-ai/langflow/.agents/skills/e2e-testing/SKILL.md

Write and review Playwright E2E tests for Langflow. Trigger when the user asks to write, fix, or review E2E tests, spec files, Playwright tests, or integration tests that exercise the full UI. Also trigger when modifying data-testid attributes, test helpers in tests/utils/, or fixture configuration.

Often used witheverything-claude-code·everything-claude-code-conventions·bun-runtime

nextlevelbuilderSkill

design-system

nextlevelbuilder/ui-ux-pro-max-skill/.claude/skills/design-system/SKILL.md

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Often used withsetup-engine·create-stories·team-level

nextlevelbuilderCLAUDE.md

ui-ux-pro-max-skill / stack

nextlevelbuilder/ui-ux-pro-max-skill/stack/CLAUDE.md

source of truth for tokens (color, type, spacing). 2. **COMMIT to an aesthetic — `frontend-design`.** Do not sample the safe center of the training distribution. Answer four questions first — *purpose

comfyanonymousAGENTS.md

ComfyUI

comfyanonymous/ComfyUI/AGENTS.md

execution-relevant state, produce execution results and errors, and not know about workflow ids, frontend ids, persistence ids, or API-only concepts. - Before touching many files, identify the smallest owner

VercelSkill

gh-stack

vercel/next.js/.agents/skills/gh-stack/SKILL.md

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh stack; or when a stack is checked out.

yangshunAGENTS.md

tech-interview-handbook

yangshun/tech-interview-handbook/AGENTS.md

Vitest, tsdown, Oxlint, Oxfmt, and Vite Task. Vite+ wraps runtime management, package management, and frontend tooling in a single global CLI called `vp`. Vite+ is distinct from Vite

garrytanSkill

design-html

garrytan/gstack/design-html/SKILL.md

Design finalization: generates production-quality Pretext-native HTML/CSS. (gstack)

Often used withplan-tune·ios-clean·document-generate

garrytanSkill

design-review

garrytan/gstack/design-review/SKILL.md

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them; --build checks UI while you build it. (gstack)

Often used withproject-stage-detect·brief-to-tasks·asset-spec

garrytanSkill

plan-ceo-review

garrytan/gstack/plan-ceo-review/SKILL.md

CEO/founder-mode plan review. (gstack)

Often used withplan-tune·ios-clean·document-generate

garrytanDeletes or force-pushesSkill

plan-design-review

garrytan/gstack/plan-design-review/SKILL.md

Designer's eye plan review — interactive, like CEO and Eng review. (gstack)

Often used withplan-tune·ios-clean·plan-devex-review

garrytanSkill

plan-devex-review

garrytan/gstack/plan-devex-review/SKILL.md

Interactive developer experience plan review. (gstack)

Often used withplan-tune·ios-clean·document-generate

garrytanSkill

ship

garrytan/gstack/ship/SKILL.md

Ship it: merge the base, run tests, review the diff, bump VERSION and CHANGELOG, push and create a PR. (gstack)

Often used withios-sync·open-gstack-browser·setup-deploy

garrytanSkill

spec

garrytan/gstack/spec/SKILL.md

Turn vague intent into a precise, executable spec in five phases. (gstack)

ggml-orgSkill

code-review

ggml-org/llama.cpp/skills/code-review/SKILL.md

Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR. Use when the user wants to review a diff, branch, or PR.

Often used withclose-spec·add-new-model·compare-screenshots