Codedrobe Adapter Dev

Organization

CodeDrobe

codedrobe-adapter-dev

Add, inspect, repair, or validate CodeDrobe Core adapters for Chromium/Electron AI desktop applications. Use when supporting a new app, updating Codex or WorkBuddy compatibility after an app release, discovering installation paths or CDP targets, selecting stable DOM landmarks, adding renderer profiles or transactional host settings, recording lastVerified versions, or writing adapter and real-renderer tests.

Overview

Publisher	CodeDrobe
Repository	`skills`
Skill name	`codedrobe-adapter-dev`
Stars	252
Forks	21
Bundled files	5
License	Apache-2.0
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.
5 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by CodeDrobe on GitHub. Read the source before you install it.

Installation

Install the Codedrobe Adapter Dev 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/CodeDrobe/skills/tree/main/skills/codedrobe-adapter-dev
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/CodeDrobe/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/codedrobe-adapter-dev .claude/skills/codedrobe-adapter-dev

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

Use it in TypingMind

Enable Codedrobe Adapter Dev 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 Codedrobe Adapter Dev 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 Codedrobe Adapter Dev 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.

CodeDrobe Adapter Development

Work in the @codedrobe/core repository. Keep the adapter lightweight and prove selectors against a real installed application; never infer renderer compatibility from an app name, executable path, or screenshot alone.

Read the relevant references

Read references/architecture.md before changing ownership between Core, adapters, renderer profiles, themes, Skills, or Desktop.
Read references/adapter-contract.md before editing adapter code, exports, host settings, or types.
Read references/dom-inspection.md before collecting CDP targets or choosing selectors.
Read references/testing.md before claiming support or updating lastVerified.

Add or repair an adapter

Inspect the current Core tree, adapter registry, tests, CLI help, and working-tree changes.
Locate the actual installed app and record its app version/build. Do not overwrite unrelated local changes.
Launch the real app with loopback CDP on a configurable, unoccupied port. Do not restart or terminate it without authorization.
Inspect /json/list, select the actual renderer, and run codedrobe dom snapshot on every relevant route to collect privacy-preserving semantic DOM evidence.
Choose only cross-route landmarks for the adapter: root, sidebar/navigation, workspace/content, and composer/input. Only rootAny should block (it doubles as the boot detector); declare panels the app can hide — sidebars in popped-out or collapsed windows — as recommended, since compatibility is judged per window.
Put app- or theme-specific layout nodes in theme verification contexts, not the adapter.
Implement the adapter, registry export, types, and focused tests. Add a renderer profile or host-settings module only when the application requires that behavior.
Probe the real renderer, then apply and verify a minimal package. Validate the home and conversation contexts separately.
Restore the renderer and any transactional host settings. Confirm cleanup before finishing.
Update lastVerified only after real-app verification succeeds, including the observed version/build and date.

Compatibility failure workflow

Reproduce with codedrobe probe --app <id> --theme <package>.
Separate adapter landmark failures from theme-specific missing nodes.
Inspect the live DOM and computed layout; do not repair from stale documentation alone.
Prefer a stable alternative selector before broadening any lists.
Keep failure output concrete: requirement name plus every attempted selector.
Add a regression test before updating lastVerified.

Guardrails

Never patch application bundles, app.asar, code signatures, WindowsApps ownership, or user authentication data.
Bind CDP to 127.0.0.1 and reject occupied custom ports instead of killing unknown processes.
Avoid generated CSS-module hashes, localized text, deep child chains, and broad selectors such as body * in adapters.
Keep optional decoration out of adapter requirements.
Preserve custom installation paths and user-selected CDP ports throughout detect, launch, probe, apply, verify, watch, and restore.
Do not add a public theme-publishing path until registry authentication and authorization are complete.

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 Codedrobe Adapter Dev AI skill do?

Why use Codedrobe Adapter Dev on TypingMind?

Because you install it once and use it with any model. Codedrobe Adapter Dev 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 Codedrobe Adapter Dev in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CodeDrobe/skills/tree/main/skills/codedrobe-adapter-dev. 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 Codedrobe Adapter Dev?

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 Codedrobe Adapter Dev?

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

Is the Codedrobe Adapter Dev AI skill free?

Yes. It is published on GitHub by CodeDrobe 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

Skill Host Compat

affaan-m

CommunityPopular

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Brand Voice

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

CodeDrobe Adapter Development

Read the relevant references

Add or repair an adapter

Compatibility failure workflow

Guardrails

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now