note
Update AGENTS.md instructions from user notes. Use when a user asks to add, revise, remove, or reorganize project operating instructions in AGENTS.md. Default to the current project's AGENTS.md, and only target global AGENTS.md when the user explicitly asks for global scope.
Best use case
note is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Update AGENTS.md instructions from user notes. Use when a user asks to add, revise, remove, or reorganize project operating instructions in AGENTS.md. Default to the current project's AGENTS.md, and only target global AGENTS.md when the user explicitly asks for global scope.
Teams using note should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/note/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How note Compares
| Feature / Agent | note | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Update AGENTS.md instructions from user notes. Use when a user asks to add, revise, remove, or reorganize project operating instructions in AGENTS.md. Default to the current project's AGENTS.md, and only target global AGENTS.md when the user explicitly asks for global scope.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Note Apply user-provided notes to AGENTS.md with minimal, precise edits and clear scope handling. ## Scope Resolution 1. Resolve target scope before editing: - `project` (default): modify the current project's AGENTS.md. - `global` (only when explicitly requested): modify global AGENTS.md. 2. Never edit both files unless the user explicitly asks for both. 3. If scope is not explicit, assume `project`. ## Target File Rules 1. For `project` scope: - Prefer `./AGENTS.md` in the current workspace. - If missing, search upward from the current directory for the nearest `AGENTS.md`. - If none exists, create `./AGENTS.md`. 2. For `global` scope: - Prefer `$CODEX_HOME/AGENTS.md` when `CODEX_HOME` is set. - Otherwise use `$HOME/.codex/AGENTS.md`. - If missing, create it. ## Editing Workflow 1. Read the existing target file fully. 2. Convert user input into concrete edits: - Add new rules as concise bullets. - Revise existing rules instead of duplicating them. - Remove rules only when asked. 3. Preserve unrelated instructions and existing structure where possible. 4. Keep wording directive and actionable; avoid narrative text. 5. Write changes directly to the resolved AGENTS.md path. ## Output Expectations 1. Report which AGENTS.md path was modified. 2. Summarize what was added, changed, or removed. 3. Call out assumptions only when necessary (for example, inferred project scope).
Related Skills
sparkle
Integrate, migrate, secure, publish, and troubleshoot Sparkle in macOS apps. Use when working on Sparkle dependency setup (SPM/Carthage/manual), updater wiring (SPUStandardUpdaterController or programmatic setup), Info.plist update keys (SUFeedURL and SUPublicEDKey), appcast/signing workflows, sandboxed updater behavior, or update-check debugging.
gsap
GSAP animations for JARVIS HUD transitions and effects
create-macos-app
Blueprint for setting up a new macOS Xcode project the right way. Use this skill whenever the user asks to create a macOS app, set up a new macOS Xcode project, or bootstrap a macOS application. Covers project creation, scheme configuration, code-level bootstrapping, menu bar setup, build configurations, and linting tooling.
apple-dev
Apple development guidelines for Swift packages (SPM), Xcode projects, Swift Testing framework, and The Composable Architecture (TCA). Load this skill whenever working in an Xcode project (xcodeproj/xcworkspace), a Swift package (Package.swift), writing or fixing Swift tests (Swift Testing, @Test, @Suite,
jupyter-notebook
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成（播客、视频、幻灯片、测验、思维导图等）、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。
Meeting Mastery — AI Meeting Prep, Notes & Follow-Up Engine
You are an elite meeting preparation and follow-up agent. You ensure every meeting is high-value — thoroughly prepared beforehand, cleanly documented during, and actioned after.
obsidian-notes
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
notebooklm-research
Full-autopilot AI research agent powered by Google NotebookLM (notebooklm-py v0.3.4). Ingests sources (URL, text, PDF, DOCX, YouTube, Google Drive), runs deep web research, asks cited questions, and generates 10 native artifact types (audio podcast, video, cinematic video, slide deck, report, quiz, flashcards, mind map, infographic, data table, study guide). Produces original content drafts via Claude, with optional publishing to social platforms via threads-viral-agent integration. Use this skill when the user mentions: NotebookLM, research with sources, create notebook, generate podcast from articles, turn research into content, trending topic research, research pipeline, source-based analysis, cited research answers, generate slides, generate quiz, make flashcards, deep web research, create infographic, compare sources, research report, study guide, source analysis, or knowledge synthesis.
GameDev Study — Video Tutorial to Learning Notes
Generates structured learning materials from game development video tutorials across multiple domains, including Godot, Unity, Unreal Engine, Blender, and Pixel Art.
notebooklm
Interact with Google NotebookLM to query documentation with Gemini's source-grounded answers. Each question opens a fresh browser session, retrieves the answer exclusively from your uploaded documents, and closes.
team-collaboration-standup-notes
You are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remote team coordination patterns.