Skill Push logo

Skill Push

Organization
luna-prompts
skill-push

Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.

Overview

Publisherluna-prompts
Repositoryskillnote
Skill nameskill-push
Stars
68
Forks
12
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Skill Push 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-codex/skills/skill-push
  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-codex/skills/skill-push .claude/skills/skill-push
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Push 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 Skill Push 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 Skill Push 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.

Skill Push

Create and push reusable skills to the SkillNote registry so every connected agent learns from repeated patterns.

Resolve the host

bash
HOST=$(cat ~/.skillnote/host 2>/dev/null | tr -d '[:space:]'); HOST=${HOST:-localhost}
API="http://${HOST}:8082"

(In Python: host = (open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost').)

When to Act

  • The user gave the same instruction or convention 2+ times this session.
  • The user explicitly asks to create, save, or push a skill.
  • Session retrospective — review for saveable patterns before wrapping up.

Only suggest for PERSISTENT conventions, not temporary workarounds.

Step 1: Confirm (REQUIRED — never skip)

If the user did not explicitly ask to create a skill, you MUST ask first. Tell the user what you noticed in one sentence, then ask: "Want me to save this as a SkillNote skill?" Wait for an explicit yes before drafting anything.

Skip this step only when the user already said "create a skill for X" / "save this pattern" / "push a skill" in their own words.

Step 2: Draft

Collaborate on three fields:

  • name: lowercase letters, hyphens, digits; max 64 chars. Also the slug.
  • description (max 1024 chars — THIS IS THE TRIGGER): what the skill does + explicit trigger keywords. Agents pick a skill based solely on its description.
  • content: instructions under ~200 lines, starting with # Title, actionable with examples.

Show the full draft to the user.

Step 3: Check if it exists

python
import urllib.request, json, os
host = open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost'
api = f"http://{host}:8082"
try:
    resp = urllib.request.urlopen(f"{api}/v1/skills/<SLUG>")
    print(f"EXISTS: v{json.loads(resp.read()).get('current_version', '?')}")
except urllib.error.HTTPError as e:
    print("NEW" if e.code == 404 else f"ERROR: {e.code}")

Step 4: Choose a collection

python
import urllib.request, json, os
host = open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost'
api = f"http://{host}:8082"
try:
    cols = json.loads(urllib.request.urlopen(f"{api}/v1/collections").read())
    for c in cols: print(f"  - {c['name']} ({c['count']} skills)")
    if not cols: print("  (no collections yet)")
except Exception as e:
    print(f"Could not fetch: {e}")

Every skill must belong to at least one collection. Present the list above and ask the user (plain text) which collection to use, or to type a new name. New names must match ^[a-z0-9_-]+$, 1–128 chars, and cannot contain anthropic or claude. A skill cannot be pushed without a collection.

Step 5: Final review

Show the complete skill preview. Emphasize: "Does the description have good trigger keywords?" Wait for approval.

Step 6: Push

New skill

python
import json, urllib.request, os
host = open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost'
api = f"http://{host}:8082"
payload = json.dumps({"name": "<NAME>", "slug": "<NAME>", "description": "<DESC>", "content_md": "<CONTENT>", "collections": ["<COL>"]}).encode()
req = urllib.request.Request(f"{api}/v1/skills", data=payload, headers={"Content-Type": "application/json"}, method="POST")
try:
    result = json.loads(urllib.request.urlopen(req).read())
    print(f"Created: {result['slug']} v{result['current_version']}")
except urllib.error.HTTPError as e:
    print(f"Error: {json.loads(e.read())}")

Existing skill (update)

python
import json, urllib.request, os
host = open(os.path.expanduser('~/.skillnote/host')).read().strip() if os.path.exists(os.path.expanduser('~/.skillnote/host')) else 'localhost'
api = f"http://{host}:8082"
payload = json.dumps({"name": "<NAME>", "description": "<DESC>", "content_md": "<CONTENT>", "collections": ["<COL>"]}).encode()
req = urllib.request.Request(f"{api}/v1/skills/<SLUG>", data=payload, headers={"Content-Type": "application/json"}, method="PATCH")
try:
    result = json.loads(urllib.request.urlopen(req).read())
    print(f"Updated: {result['slug']} v{result['current_version']}")
except urllib.error.HTTPError as e:
    print(f"Error: {json.loads(e.read())}")

After success: link to http://<host>:3000/skills/<slug> for viewing.

Error reference

  • 422: name format wrong or description has XML tags
  • 409: slug exists — switch to PATCH
  • Connection refused: API unreachable (check ~/.skillnote/host)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Skill Push AI skill do?

Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.

Why use Skill Push on TypingMind?

Because you install it once and use it with any model. Skill Push 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 Skill Push in TypingMind?

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

Which AI models can use Skill Push?

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 Skill Push?

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

Is the Skill Push 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 👇