This file is the single source of truth for agents entering this repository. Read this file first; after entering apps/, packages/, tools/, or e2e/, read that layer's AGENTS.md for module-level details. Do not copy module details back into the root file; root stays focused on cross-repository boundaries, workflow, and commands.
One-click contribution flow for Open Design (nexu-io/open-design) — even for non-coders. Pick one of four cards (ship a Skill or Design System you made with OD; translate docs; fix a typo / write a blog; report a bug), the agent validates and opens a PR (or issue) for you. Trigger words contribute to open design, ship my OD skill, ship my OD design system, translate OD docs, report an OD bug, od-contribute.
This directory holds design templates — packaged "shapes" the agent renders into a project artifact (decks, prototypes, image/video/audio templates, …). Each entry is a folder with a SKILL.md (same shape as functional skills) plus rendering side files (example.html, assets/, references/, …). If the entry primarily does work on user input — utilities, briefs, asset packagers, fidelity audits — it belongs under ../skills/ instead. See specs/current/skills-and-design-templates.md for the full split. - Listed under /api/design-templates. The shape mirrors /api/skills (same SkillSummary/SkillDetail types)…
Follow the root AGENTS.md first. This package owns user-level end-to-end smoke tests and Playwright UI automation only. For the current coverage posture, recent hardening work, grouped-run status, and known intentional gaps, see docs/testing/e2e-coverage/status.md.
This directory is still only partially standardized. Several historical workflows and helper locations do not yet follow one uniform shape. Do not copy old patterns blindly. For new work, bug fixes, and cleanup, use the ci.yml + comment.atom.yml + autofix.atom.yml + report.atom.yml + .github/scripts/handoff.py system as the reference topology unless a maintainer explicitly chooses a different boundary. Before changing GitHub automation, read the current versions of: If the change affects cross-workflow behavior, update the topology tests instead of relying only…
This directory owns MonoField plugin content and plugin authoring material. For plugin content changes, run: When the daemon CLI is built and available, also validate runnable plugin folders with:
Hyperframes-based video template for retro pixel deck motion design. Use when users want a high-fidelity, multi-scene HTML-to-video composition with advanced transitions, interactive preview controls, and ready-to-render default style.
Luxury dark-editorial HyperFrames template for three-page cinematic storyboards, inspired by haute couture title cards and magazine chapter spreads. Use when the user asks for premium fashion-style motion pages, moody serif-led storytelling, or a high-end dark presentation aesthetic with rich transitions.
Browser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages, filling forms, clicking buttons, taking screenshots, extracting page data, reading selected MonoField browser-tab context, testing web apps, dogfooding MonoField previews, QA, bug hunts, or reviewing app quality. Prefer local MonoField preview URLs unless the user explicitly asks for external browsing.
This directory holds functional skills — capabilities the agent invokes mid-task to do work on user input. Each skill is a folder with a SKILL.md (frontmatter + body) and any side files (assets/, references/, scripts, …) the workflow needs. If the entry primarily renders a design artifact (deck, prototype, image/video/audio template) it belongs under ../design-templates/ instead. See specs/current/skills-and-design-templates.md for the full split. - Listed under /api/skills (functional only). User-imported skills shadow built-in entries with the same frontmatter name. - Asset…
Full-lifecycle AI music album production — concept, lyric drafting, track sequencing, and export. Useful for indie album experiments and brand soundtracks.
Create generative art using p5.js with seeded randomness so every render is reproducible. Useful for procedural posters, motion-style stills, and artistic frame studies.
Apple Human Interface Guidelines as 14 agent skills covering platforms, foundations, components, patterns, inputs, and technologies for iOS, macOS, visionOS, watchOS, and tvOS.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.