Core

Organization

crafter-station

core

Canonical skillkit workflow served by the installed CLI. Read before auditing skill packs or analyzing skill usage, context cost, conflicts, coverage, and token burn.

Overview

Publisher	crafter-station
Repository	`skill-kit`
Skill name	`core`
Stars	79
Forks	9
Bundled files	1
Links	Skill source Repository Homepage

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 crafter-station on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/crafter-station/skill-kit/tree/main/packages/cli/src/skill-data/core
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.

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/crafter-station/skill-kit.git /tmp/skill-kit
mkdir -p .claude/skills
cp -r /tmp/skill-kit/packages/cli/src/skill-data/core .claude/skills/core

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Core 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 Core 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 Core 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.

skillkit core

Skillkit is a local-first observability and structural-audit CLI for AI agent skills. It reads local skill directories and agent session stores. It does not require an account or send telemetry.

Choose the command

Audit an uninstalled skill, subset, or repository: skillkit audit <path>
See which installed skills are used: skillkit stats
Inspect private usage receipts: skillkit receipts --pending
Read receipts from another Mac in the tailnet: skillkit receipts --remote user@mac.tailnet.ts.net --all --json
Check installed-skill and database health: skillkit health
Measure always-loaded context and MCP schemas: skillkit context --mcp
Compare context before and after installing a pack: skillkit context --save-baseline <name>, then skillkit context --compare <name>
Measure observed dead weight for one skill: skillkit coverage <skill-path>
Find overlapping triggers: skillkit conflicts
Trace one invocation: skillkit trace <prompt>
Inspect subscription token burn: skillkit burn
Remove unused skills: run skillkit prune first, then add --yes only when deletion is intended

Audit a skill pack

Use audit for static analysis that does not depend on installation or session history:

bash
skillkit audit ./skills
skillkit audit ./skills/testing ./skills/release
skillkit audit ./skills --include "rn-*"
skillkit audit ./skills --json --strict

The report separates three context layers:

Catalog cost: name and description, available during discovery
Activation cost: the selected SKILL.md
On-demand cost: files under references/

It checks metadata, estimated tokens, line count, bundled references, scripts and assets, broken or unsafe pointers, unreferenced files, explicit reference-routing instructions, duplicate names, and similar descriptions.

--strict exits with status 1 when warnings or errors are present. Token counts are local estimates based on character length, so treat them as consistent budget signals rather than provider-exact billing values.

Usage and context workflow

On a new installation, scan before interpreting usage:

bash
skillkit scan
skillkit stats --all --days 90
skillkit health
skillkit receipts --pending
skillkit receipts --remote user@mac.tailnet.ts.net --all --json

Before adding a large skill pack or MCP server:

bash
skillkit context --save-baseline before
skillkit context --mcp
skillkit context --mcp --compare before

Use coverage only when observed traces matter. Use audit for filesystem structure and best-practice conformance.

Automation

Add --json when the command supports machine-readable output. Use audit --json --strict in CI. Agent filters such as --claude, --codex, --cursor, --gemini, and --opencode narrow commands that read installed skills or sessions.

Remote receipt collection runs Skillkit beside the source sessions, requires an exact version match, and transfers only private receipt JSON. Do not copy raw remote transcripts or the remote Skillkit database. Do not treat unmeasured MCP servers as zero cost. Do not run prune --yes unless deletion is explicitly intended.

Read references/commands.md when exact flags, aliases, JSON behavior, data locations, or the full command catalog are needed. The same reference is included by skillkit skills get core --full.

Bundled files

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

references/commands.md4 KB

Frequently asked questions

What does the Core AI skill do?

Canonical skillkit workflow served by the installed CLI. Read before auditing skill packs or analyzing skill usage, context cost, conflicts, coverage, and token burn.

Why use Core on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crafter-station/skill-kit/tree/main/packages/cli/src/skill-data/core. 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 Core?

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 Core?

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

Is the Core AI skill free?

It is published on GitHub by crafter-station. Check the repository for licensing terms. 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

Qdrant

NousResearch

OrganizationPopular

Vector search engine for production RAG systems.

Tensorrt Llm

High-throughput LLM inference on NVIDIA GPUs.

Internal Comms

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal…

Claude Opus 4 5 Migration

anthropics

OrganizationPopular

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

skillkit core

Choose the command

Audit a skill pack

Usage and context workflow

Automation

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now