Comments logo

Comments

Organization
LedgerHQ
comments

Stop writing so many comments. Follow these suggestions instead!

Overview

PublisherLedgerHQ
Repositoryledger-live
Skill namecomments
Stars
622
Forks
491
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 LedgerHQ on GitHub. Read the source before you install it.

Installation

Install the Comments 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/LedgerHQ/ledger-live/tree/develop/.agents/skills/comments
  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/LedgerHQ/ledger-live.git /tmp/ledger-live
mkdir -p .claude/skills
cp -r /tmp/ledger-live/.agents/skills/comments .claude/skills/comments
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Comments 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 Comments 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 Comments 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.

Comments in code

🧀 Avoid comments

Comments are code smells because they go out-of-date, bloat context, and lead to confusion.

Don't reference existing comments in the codebase – follow these rules

  • Avoid adding comments – always prefer good names (explainer variables, functions, tests)
  • Use test names to describe behaviour – unit tests are living documentation
  • Good code explains itself – don't add comments that duplicate what the code already conveys

💡 Treatments

When code isn't clear, make it clearer:

  • Rename variables and functions to make comments unnecessary
  • Extract variables and functions to improve readability
  • Use assertions to explain behaviour

Use test names to explain non-obvious details

❌ Bad

ts
it("diffs the current value against resolved when targeted", () => {
  const { result } = renderHook(() => useJsonEditor(makeProps()));
  act(() => result.current.setDiffTarget("resolved"));
  // Current equals resolved → every line is unchanged.
  expect(result.current.diffJson.every((l) => l.state === "none")).toBe(true);
});

✅ Good

ts
it("resets the state of every line when the diff is resolved", () => {
  const { result } = renderHook(() => useJsonEditor(makeProps()));
  act(() => result.current.setDiffTarget("resolved"));
  expect(result.current.diffJson.every((l) => l.state === "none")).toBe(true);
});

Let code speak for itself

❌ Bad

ts
/* Whether the filter trigger should be displayed */
showFilter: boolean;

✅ Good

ts
showFilter: boolean;

Replace comments with explainer variables

Move the comment into a variable name:

Before

ts
// NB `app.trustchain` is an encrypted db path: while the app is password-locked it reads back
// as the ciphertext string. Importing it would regenerate member credentials and null the
// trustchain (LIVE-36130). IsUnlocked re-runs this thunk once the encryption key is set.
// `undefined` must still go through: that is the legitimate "nothing persisted" case.
if (typeof data === "string") return;

After

ts
const dataIsEncrypted = typeof data === "string";
if (dataIsEncrypted) return;

☝️ When comments are necessary

Comments are only for vital information that can't go anywhere else. Always prefer not adding comments. If a comment is the only way, follow these guidelines:

  • Be concise: Use as few words as possible to convey the necessary information.
  • Use JSDocs: Only when describing a shared function.
  • Prefer a link: If the comment is explaining a workaround for a known issue, link to the issue or docs.

❌ Bad

yaml
# pnpm patches add 'patch_hash=HASH' to virtual store paths, which prefab 2.1.0
# (introduced via AGP 8.11) misparses as an option flag due to a clikt bug that splits
# positional path arguments at '='. Pinning prefab to 2.0.0 in gradle.properties avoids
# this; keeping path segments ≤ 80 chars shortens virtual-store paths to reduce the
# likelihood of triggering prefab path-parsing issues as an additional safeguard.
android.prefab.version=2.0.0
virtual-store-dir-max-length=80

✅ Better

yaml
# Workaround for Prefab 2.1.0/Clikt bug
# See: https://github.com/google/prefab/issues/187
android.prefab.version=2.0.0
virtual-store-dir-max-length=80

Frequently asked questions

What does the Comments AI skill do?

Stop writing so many comments. Follow these suggestions instead!

Why use Comments on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LedgerHQ/ledger-live/tree/develop/.agents/skills/comments. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Comments?

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 Comments?

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

Is the Comments AI skill free?

Yes. It is published on GitHub by LedgerHQ 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 👇