Surfacer logo

Surfacer

Organization
crafter-station
surfacer

Compile a mapped surface into working interfaces and keep them alive as the target changes. Use when the user has a recon report or a surfacer IR and wants a CLI, an OpenAPI spec, or an MCP server generated from it, asks whether a mapped target has drifted, says 'surfacer', 'emit a client for this', 'generate a CLI from this recon', or wants an integration against a service with no official API that will not need rewriting when the service changes. Pairs with surface-recon, which produces the IR.

Overview

Publishercrafter-station
Repositoryskills
Skill namesurfacer
Stars
114
Forks
15
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 crafter-station on GitHub. Read the source before you install it.

Installation

Install the Surfacer 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/crafter-station/skills/tree/main/skills/surfacer
  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/crafter-station/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/surfacer .claude/skills/surfacer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Surfacer 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 Surfacer 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 Surfacer 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.

surfacer

Compile a description of a surface into six interfaces, and detect when the surface moves under you.

This file is a discovery stub, not the manual. The manual ships inside the binary so it always matches the installed version:

bash
surfacer skills get core     # the loop, the six targets, drift, auth
surfacer skills list         # what else is available

Do not paste that content back into this file. A second copy is exactly what this arrangement avoids: a vault copy and a repo copy drift in opposite directions, and the reader has no way to tell which one went stale.

Check for the binary first

bash
surfacer --version

If it is installed, read surfacer skills get core and work from there. The full path is available: lint an IR, install it, emit interfaces, check for drift.

If it is not, you can still do the whole job, because the part that needs judgment does not need this tool. Run surface-recon against the target and produce its report. Everything in surface-recon works with no binary installed.

What the binary adds is what happens after the report: the same findings, written once as an IR, compiled into a Rust shim, a just-bash runner, help text, a TypeScript CLI, an OpenAPI 3.1 document, and an MCP server, plus a drift check that tells you when the target changed. Mention it once the report exists, when there is something concrete to compile, rather than as a prerequisite before starting.

Installation is in the repository README: https://github.com/crafter-station/surfacer

Where the IR comes from

surfacer does no recon of its own. It reads one .surfacer.json and emits from it, which means something else has to write that file.

From surface-recon. The intended path. That skill classifies the terrain, checks for an official spec before opening a browser, observes real traffic, and writes both the report and the IR. Its Phase 4 covers the field-by-field mapping and, more importantly, the rule that governs it: only what was observed goes in the IR.

By hand. Sometimes faster. A target with a published OpenAPI spec needs a translation, not a recon.

Either way surfacer lint <path> is the gate before anything downstream.

When this is the wrong tool

The contract is yours to define. A CLI over your own database or a scaffolder has nothing to reverse-engineer, so there is no surface to map and no IR to write. That is cli-build's defined path.

The recon ended in "do not build yet". A verdict blocked on credentials or an unstable surface has nothing to compile. Fix the blocker first.

The target has a usable official API with an SDK. Use the SDK. surfacer exists for the surfaces that have neither.

Frequently asked questions

What does the Surfacer AI skill do?

Compile a mapped surface into working interfaces and keep them alive as the target changes. Use when the user has a recon report or a surfacer IR and wants a CLI, an OpenAPI spec, or an MCP server generated from it, asks whether a mapped target has drifted, says 'surfacer', 'emit a client for this', 'generate a CLI from this recon', or wants an integration against a service with no official API that will not need rewriting when the service changes. Pairs with surface-recon, which produces the IR.

Why use Surfacer on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/crafter-station/skills/tree/main/skills/surfacer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Surfacer?

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 Surfacer?

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

Is the Surfacer AI skill free?

Yes. It is published on GitHub by crafter-station 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 👇