Collection logo

Collection

Organization
luna-prompts
collection

Choose which SkillNote skill collection is active for this project. Use when user says "change collection", "switch skills", "use frontend skills", "show collections", or at first session in a new project when recommended.

Overview

Publisherluna-prompts
Repositoryskillnote
Skill namecollection
Stars
68
Forks
12
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by luna-prompts on GitHub. Read the source before you install it.

Installation

Install the Collection AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/luna-prompts/skillnote/tree/master/plugin/skills/collection
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/luna-prompts/skillnote.git /tmp/skillnote
mkdir -p .claude/skills
cp -r /tmp/skillnote/plugin/skills/collection .claude/skills/collection
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Collection in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Collection on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Collection is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SkillNote Collection Manager

Help the user choose which skill collection to sync for the current project.

Step 1: Fetch collections

Run this in Bash to get available collections:

bash
curl -sf "http://${CLAUDE_PLUGIN_OPTION_HOST:-localhost}:8082/v1/collections" 2>/dev/null || echo "[]"

Step 2: Show picker — MUST use AskUserQuestion

You MUST call the AskUserQuestion tool. Do NOT print a table or ask a text question.

Call AskUserQuestion with these EXACT parameters:

  • header: "SkillNote"
  • question: "Pick a collection for this project:"
  • Build options in this order:
    1. Recommended first: if basename(cwd) (lowercase, non-alphanumeric replaced with -) matches an existing collection name, put that option first and append · Recommended to its description. Example description: "12 skills · Recommended".
    2. All other existing collections, each with label = name, description = "{count} skills".
    3. If .skillnote.json exists, add "(current)" to the currently-active collection's label.
    4. {"label": "Create new collection…", "description": "type a name next"}
    5. {"label": "Skip (use no collections)", "description": "no skills synced"}

Example AskUserQuestion call:

json
{
  "header": "SkillNote",
  "question": "Pick a collection for this project:",
  "options": [
    {"label": "frontend (current)", "description": "12 skills · Recommended"},
    {"label": "backend", "description": "8 skills"},
    {"label": "devops", "description": "3 skills"},
    {"label": "Create new collection…", "description": "type a name next"},
    {"label": "Skip (use no collections)", "description": "no skills synced"}
  ]
}

Step 3: Apply selection

Branch based on what the user picked:

3a. Existing collection or "(current)" option

Strip any (current) suffix. Then run:

bash
echo '{"collections": ["<SELECTED_NAME>"]}' > .skillnote.json
skillnote-sync --force 2>/dev/null || true

Tell the user: "Switched to {name}. Skills will refresh."

3b. "Create new collection…"

Ask the user for a name in a plain text turn:

What should the new collection be called? (lowercase letters, numbers, hyphens, underscores — example: my-project)

Wait for their reply. Validate: name must match ^[a-z0-9_-]+$, be 1–128 chars, and not contain anthropic or claude. If invalid, explain and re-prompt once.

Create the collection:

bash
curl -sf -X POST "http://${CLAUDE_PLUGIN_OPTION_HOST:-localhost}:8082/v1/collections" \
  -H "Content-Type: application/json" \
  -d '{"name": "<NAME>", "description": ""}'

If curl returns a 409 conflict, the collection already exists — tell the user and offer to activate it instead (one-question AskUserQuestion: Yes, activate / No, pick a different name).

On success, write the name to .skillnote.json and run sync the same way as 3a.

3c. "Skip (use no collections)"

Write an empty collections list:

bash
echo '{"collections": []}' > .skillnote.json
skillnote-sync --force 2>/dev/null || true

Tell the user: "Skipped. No skills will be synced to this project."

Rules

  • ALWAYS use AskUserQuestion — never print a table or numbered list
  • Keep 12-15 skills per collection for best Claude Code performance
  • User can change collections anytime by saying "change collection"

Frequently asked questions

What does the Collection AI skill do?

Choose which SkillNote skill collection is active for this project. Use when user says "change collection", "switch skills", "use frontend skills", "show collections", or at first session in a new project when recommended.

Why use Collection on TypingMind?

Because you install it once and use it with any model. Collection is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Collection in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/luna-prompts/skillnote/tree/master/plugin/skills/collection. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Collection?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Collection?

As many as you like. As long as a model supports skills, you can use Collection with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Collection AI skill free?

Yes. It is published on GitHub by luna-prompts under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇