New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Collab Surface Core

by macro-inc in macro-inc/macro

A skill your agent uses when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces.

AGPL-3.0Auto-check passedKnowledge Management

Install Collab Surface Core

skills CLI
$ npx skills add macro-inc/macro --skill collab-surface-core -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install macro-inc/macro collab-surface-core --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/macro-inc/macro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/collab-surface-core .claude/skills/collab-surface-core && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
collab-surface-core
GitHub stars
4.6k
Token cost
~639 tokens
SKILL.md length
300 words
Files
2
Skills in repo
19
Repo updated
First seen
Licence
AGPL-3.0

At a glance

A skill your agent uses when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces.

  • Adding collaborative markdown
  • SKILL.md covers Choose the entry point and Keep content and lifecycle…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Descriptions to a feature with collab surfaces

What it does

Collab Surface Core is an agent skill from macro-inc/macro. Use when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces. Covers parent entities, service entry points, authorization, content storage, and lifecycle.

Its SKILL.md is about 640 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Knowledge Management, covering Note-taking. The repository describes itself as: Macro is a unified workspace for teams: email, chat, docs, tasks, agents, calls, and CRM — @-linked together with shared AI memory. The licence is AGPL-3.0.

When your agent uses it

  • Adding collaborative markdown
  • Descriptions to a feature with collab surfaces

Example prompts

  • “/collab-surface-core”

What it can do on your machine

Read from SKILL.md and the folder at commit 49418e7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Collab Surface Core loads about 639 tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 300 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~639

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from macro-inc/macro at commit 49418e7, republished under its AGPL-3.0 licence (© macro-inc). 300 words, ~639 tokens.

Download SKILL.mdSave it as .claude/skills/collab-surface-core/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
collab-surface-core
description
Use when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces. Covers parent entities, service entry points, authorization, content storage, and lifecycle.

Collab surface core

Use collab surfaces for collaborative markdown within a feature. Each surface has its own Loro session in sync-service and can exist without a Document row. The surface is a child resource of an app entity: product names, owners, sharing, and discovery belong to the parent.

Choose the entry point

  • A field managed by its parent domain, such as an initiative description: use OwnedSurfaceService through the feature's domain port. The owning domain authorizes callers and chooses the surface id before calling ensure_owned_surface, owned_surface_markdown, or retire_surface.
  • A surface managed through the public API, such as a channel's shared input: use CollabSurfaceService with an access receipt for the parent. Surface reads, connection tokens, and deletion derive their permissions from that parent.

Check surface_ownership and the parent's access resolution when adding a new parent type. Parents marked ParentDomain use their domain's creation and retirement paths; the public API still provides connection tokens. Keep the trusted OwnedSurfaceService behind domain authorization, with adapters supplied by the composition root.

Keep content and lifecycle with their owners

  • The Loro session is the source of truth for content. collab_surfaces records the id, parent, initialization state, timestamps, and soft deletion.
  • Use application-generated UUIDv7 ids and the service's ensure operation. It handles namespace collisions and retries initialization from pending to ready. The id also names the sync session and must never be recycled.
  • Initial markdown seeds a new session. Ensuring an existing surface preserves its content; subsequent edits go through the collaborative session.
  • Wire retirement into the owning feature's cleanup. The parent reference is polymorphic and has no foreign-key cascade. Retirement blocks new connection tokens; it does not reclaim the sync-service session.

Read the domain ports and parent policy before wiring a consumer. The initiative adapter shows how a feature reuses the service through its own domain port.

© macro-inc, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/collab-surface-core of macro-inc/macro.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 49418e7

Compare with similar skills

Collab Surface Core next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Collab Surface Core compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Collab Surface Core this skillmacro-inc/macro4.6k—~639Automated safety check: PassAGPL-3.0
Qmdalsk1992/CloddsBot2.9k3 repos~1.2kAutomated safety check: PassMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Obsidian Canvas BoardsAgriciDaniel/claude-obsidian15k—~1.4kAutomated safety check: PassMIT
Para Memory Filespaperclipai/paperclip99k1 repos~909Automated safety check: PassMIT
Add Frontmatterheyitsnoah/claudesidian2.6k—~951Automated safety check: PassMIT

Similar skills

  • Qmd

    alsk1992/CloddsBot

    Local hybrid search for markdown notes and docs. An agent skill from alsk1992/CloddsBot.

    2.9k GitHub starsUsed in 3 repos~1.2k tokens
    Knowledge ManagementAuto-check passed

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

  • Obsidian Canvas Boards

    AgriciDaniel/claude-obsidian

    Creates, inspects and updates Obsidian JSON Canvas boards in a vault, with text, file, link, group and edge nodes, using safe recoverable edits.

    15k GitHub stars~1.4k tokensUpdated 27 days ago
    Knowledge ManagementAuto-check passed

  • Para Memory Files

    paperclipai/paperclip

    Use a file-based PARA memory system to store, retrieve, and organize durable knowledge across sessions.

    99k GitHub starsUsed in 1 repo~909 tokens
    Knowledge ManagementAuto-check passed

  • Add Frontmatter

    heyitsnoah/claudesidian

    Add or update YAML frontmatter properties to enhance Obsidian note organization.

    2.6k GitHub stars~951 tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

  • My LLM Wiki

    MartinLwx/dotfiles

    Provides access to the user's personal wiki, including notes, research, project documentation, decisions, and archived knowledge.

    140 GitHub stars~2.7k tokensUpdated 18 days ago
    Knowledge ManagementAuto-check passed

More from macro-inc/macro

All 19 skills in this repo

  • Mintlify API

    macro-inc/macro

    Interact with the Mintlify REST API to manage deployments, trigger builds, and query documentation site metadata programmatically.

    4.6k GitHub starsUsed in 2 repos~333 tokens
    Auto-check passed

  • Add Tour

    macro-inc/macro

    Add or change an in-app feature tour (a view's guided flyover) in the web app.

    4.6k GitHub stars~1.8k tokensUpdated today
    Auto-check passed

  • Define Feature Flag

    macro-inc/macro

    Define a frontend feature flag with defineFlag and wire its readers.

    4.6k GitHub stars~780 tokensUpdated today
    Auto-check passed

  • Run App

    macro-inc/macro

    Run the Macro app on Cursor Cloud and pick up edits. An agent skill from macro-inc/macro.

    4.6k GitHub stars~712 tokensUpdated today
    Auto-check passed

  • Add SDK Endpoint

    macro-inc/macro

    Wrap a new backend endpoint in the TypeScript SDK (packages/sdk), or record it as skipped.

    4.6k GitHub stars~1k tokensUpdated today
    Auto-check: notes

  • Cloud Storage Hexagonal Architecture

    macro-inc/macro

    Enforce hexagonal architecture in the Rust backend. An agent skill from macro-inc/macro.

    4.6k GitHub stars~3k tokensUpdated today
    Auto-check passed

Categories

Questions about Collab Surface Core

What does Collab Surface Core do?

A skill your agent uses when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces. Collab Surface Core is an agent skill from macro-inc/macro. Use when adding collaborative markdown, notes, or descriptions to a feature with collab surfaces.

When should I use Collab Surface Core?

Collab Surface Core fits situations like: adding collaborative markdown; descriptions to a feature with collab surfaces.

How do I install Collab Surface Core in Claude Code?

Run `npx skills add macro-inc/macro --skill collab-surface-core -a claude-code`. Or copy the skill folder (.agents/skills/collab-surface-core in macro-inc/macro) into .claude/skills/collab-surface-core in your project. Claude Code loads it when a task matches its description.

How do I install Collab Surface Core in Codex?

Run `npx skills add macro-inc/macro --skill collab-surface-core -a codex`. Or copy the skill folder (.agents/skills/collab-surface-core in macro-inc/macro) into .agents/skills/collab-surface-core in your project. Codex loads it when a task matches its description.

Can I use Collab Surface Core in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add macro-inc/macro --skill collab-surface-core -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/collab-surface-core, .gemini/skills/collab-surface-core, .github/skills/collab-surface-core and .opencode/skills/collab-surface-core in your project.

What does Collab Surface Core need to run?

SKILL.md names no scripts, command-line tools or credentials: Collab Surface Core is instructions for the agent only.

Does Collab Surface Core access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Collab Surface Core safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Collab Surface Core use?

Collab Surface Core is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Collab Surface Core use?

About 639 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Collab Surface Core?

Skills that share tags, products or a category with Collab Surface Core: Qmd (alsk1992/CloddsBot, 2.9k stars), LLM Wiki (lewislulu/llm-wiki-skill, 655 stars), Obsidian Canvas Boards (AgriciDaniel/claude-obsidian, 15k stars) and Para Memory Files (paperclipai/paperclip, 99k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Collab Surface Core?

macro-inc (a GitHub organization) maintains it in macro-inc/macro, which has 4,590 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

Source: macro-inc/macro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.