Lap logo

Lap

Organization
Lap-Platform
lap

LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill, skill-install, skill-batch, publish, login, logout, whoami.

Overview

PublisherLap-Platform
RepositoryLAP
Skill namelap
Stars
346
Forks
30
Bundled files
3
LicenseApache-2.0
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.

  • 3 bundled files

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

  • Open source

    Published by Lap-Platform on GitHub. Read the source before you install it.

Installation

Install the Lap 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/Lap-Platform/LAP/tree/main/lap/skills/codex
  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/Lap-Platform/LAP.git /tmp/LAP
mkdir -p .claude/skills
cp -r /tmp/LAP/lap/skills/codex .claude/skills/lap
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lap 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 Lap 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 Lap 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.

LAP CLI

Compile, search, and manage API specs for AI agents.

Command Resolution

IMPORTANT: Always use curl for registry operations (search, get, check). Do NOT use npx for these -- it downloads the package every time and takes minutes. curl is instant.

bash
# Search the registry
curl -s 'https://registry.lap.sh/v1/search?q=<query>'

# Download a spec
curl -sH 'Accept: text/lap' https://registry.lap.sh/v1/apis/<name> -o <name>.lap

# Get API metadata (version, endpoint count)
curl -sH 'Accept: application/json' https://registry.lap.sh/v1/apis/<name>

Only use the CLI (lapsh or npx @lap-platform/lapsh) for operations that require it: compile, publish, skill-install, init.


Agent Flow -- Consuming APIs

Use this flow when a user needs to find, download, or work with an API.

1. Discover

Option A -- curl (fastest):

bash
curl -s 'https://registry.lap.sh/v1/search?q=<query>'

Option B -- CLI:

bash
lapsh search <query> [--tag <tag>] [--sort relevance|popularity|date] [--limit <n>]

Results show name, endpoint count, compression ratio, and a [skill] marker for installable skills.

2. Acquire

Option A -- curl (fastest):

bash
curl -sH 'Accept: text/lap' https://registry.lap.sh/v1/apis/<name> -o <name>.lap

Option B -- Install a skill (if [skill] marker present):

bash
lapsh skill-install <name> --target codex
# Installs to ~/.codex/skills/<name>/

Option C -- Download via CLI:

bash
lapsh get <name> -o <name>.lap
lapsh get <name> --lean -o <name>.lean.lap

Option D -- Compile a local spec:

bash
lapsh compile <spec-file> -o output.lap
lapsh compile <spec-file> -o output.lean.lap --lean

Supported formats: OpenAPI (YAML/JSON), GraphQL (SDL), AsyncAPI, Protobuf, Postman, Smithy. Format is auto-detected.

3. Use

Once you have a .lap file, read it directly -- LAP is designed for AI consumption. Key markers:

MarkerMeaning
@apiAPI name, version, base URL
@endpointHTTP method + path
@paramParameter (query, path, header)
@bodyRequest body schema
@responseResponse status + schema
@requiredRequired fields
@errorError response

Publisher Flow -- Publishing APIs

Use this flow when a user wants to compile, package, and publish an API spec.

1. Authenticate

bash
lapsh login
lapsh whoami        # verify

2. Compile

bash
lapsh compile spec.yaml -o spec.lap
lapsh compile spec.yaml -o spec.lean.lap --lean

3. Generate Skill

bash
# Basic skill (Layer 1 -- mechanical)
lapsh skill spec.yaml -o skills/ --no-ai

# AI-enhanced skill (Layer 2 -- requires claude CLI)
lapsh skill spec.yaml -o skills/ --ai

# Generate and install directly
lapsh skill spec.yaml --install

4. Publish

bash
lapsh publish spec.yaml --provider stripe.com
lapsh publish spec.yaml --provider stripe.com --name charges --source-url https://...
lapsh publish spec.yaml --provider stripe.com --skill          # include skill
lapsh publish spec.yaml --provider stripe.com --skill --skill-ai  # with AI skill

5. Verify

bash
lapsh search <name>   # confirm it appears in registry

6. Batch Operations

bash
# Generate skills for all specs in a directory
lapsh skill-batch specs/ -o skills/

Quick Reference

Core Commands

CommandDescription
compile <spec>Compile API spec to LAP format

Registry Commands

CommandDescription
search <query>Search the LAP registry
get <name>Download a LAP spec
publish <spec>Compile and publish to registry
loginAuthenticate via GitHub OAuth
logoutRevoke token
whoamiShow authenticated user

Setup

CommandDescription
init --target codexSet up LAP for Codex CLI
init --target cursorSet up LAP for Cursor

Skill Commands

CommandDescription
skill <spec>Generate Codex CLI skill from spec
skill-batch <dir>Batch generate skills
skill-install <name> --target codexInstall skill from registry to Codex CLI

Error Recovery

ProblemFix
command not found: lapshnpm install -g @lap-platform/lapsh or use npx @lap-platform/lapsh
Not authenticatedRun lapsh login first
Format detection failedPass -f openapi (or graphql, asyncapi, protobuf, postman, smithy)
403 Forbidden on getSpec may be private or registry may block without User-Agent -- update lapsh
YAML parse errorCheck spec is valid YAML/JSON -- use a linter first
Layer 2 requires claudeInstall Claude CLI or use --no-ai for Layer 1 skills
Provider requiredpublish needs --provider <domain> (e.g., --provider stripe.com)

Environment Variables

VariablePurposeDefault
LAP_REGISTRYOverride registry URLhttps://registry.lap.sh

References

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 Lap AI skill do?

LAP CLI -- compile, search, and manage API specs for AI agents. Use when working with API specifications (OpenAPI, GraphQL, AsyncAPI, Protobuf, Postman), compiling specs to LAP format, searching the LAP registry, generating skills from API specs, or publishing APIs. Commands: init, compile, search, get, skill, skill-install, skill-batch, publish, login, logout, whoami.

Why use Lap on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Lap-Platform/LAP/tree/main/lap/skills/codex. 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 Lap?

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 Lap?

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

Is the Lap AI skill free?

Yes. It is published on GitHub by Lap-Platform under the Apache-2.0 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 👇