Repo Analysis logo

Repo Analysis

Organization
ovh
repo-analysis

Analyze uncommitted changes in the repository, group them into logical commits, and determine the appropriate version bump

Overview

Publisherovh
Repositoryshai
Skill namerepo-analysis
Stars
627
Forks
60
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by ovh on GitHub. Read the source before you install it.

Installation

Install the Repo Analysis 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/ovh/shai/tree/main/shai-core/examples/skills/repo-analysis
  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/ovh/shai.git /tmp/shai
mkdir -p .claude/skills
cp -r /tmp/shai/shai-core/examples/skills/repo-analysis .claude/skills/repo-analysis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Repo Analysis 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 Repo Analysis 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 Repo Analysis 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.

Repository Change Analysis

Purpose

Analyze uncommitted changes in the repository, group them into logical commits, determine the appropriate version bump, and guide the user through committing each group cleanly.

Procedure

1. Gather All Changes

  • Run git status to see the full list of modified, staged, deleted, and untracked files.
  • Run git diff and git diff --staged to inspect the actual changes.
  • If the diff is large, review files one by one using git diff -- <file> or git diff --staged -- <file>.

2. Identify Logical Change Groups

Analyze the changes and group them into logical features/fixes. Each group should:

  • Represent a single coherent concern (e.g., "add TUI status bar", "refactor session persistence", "fix pty leak").
  • Be independently committable without breaking the build.
  • Map to a conventional commit type (feat:, fix:, refactor:, docs:, test:, chore:, ci:).

Present the proposed grouping to the user in a structured format:

## Proposed Commits

### Commit 1 — feat: <short description>
- **Files:** list of files
- **Rationale:** why these belong together

### Commit 2 — fix: <short description>
- **Files:** list of files
- **Rationale:** why these belong together

...

Wait for user confirmation before proceeding.

3. Determine Version Bump

Based on the full set of changes, determine the appropriate version bump following Semantic Versioning:

Change TypeVersion BumpExamples
Major (X.0.0)Breaking changes, API removals, incompatible behavioral changesRenaming/removing public APIs, changing config format, removing features
Minor (x.Y.0)New features, backward-compatible additionsNew tools, new commands, new config options, new capabilities
Patch (x.y.Z)Bug fixes, refactors, docs, choresFixes, code cleanup, dependency updates, documentation
Decision Guidelines
  • If any change introduces a breaking change → major bump.
  • Else if any change adds a new feature → minor bump.
  • Else → patch bump.
  • When in doubt, prefer the lower bump unless the user specifies otherwise.

Present the recommendation:

## Version Recommendation
- **Current version:** x.y.z
- **Proposed version:** x.y.z+1 (or X+1.0.0 / x.Y+1.0)
- **Bump type:** major/minor/patch
- **Rationale:** <brief explanation>

Wait for user confirmation before proceeding.

4. Stage and Commit Each Group

For each logical change group:

  1. Stage the relevant files: git add <files> (or git add -p for partial staging).
  2. Commit with a clear conventional-commit message:
    bash
    git commit -m "feat: short description" -m "Detailed explanation of what and why."
  3. Verify the commit succeeded with git log --oneline -1.

5. Update Version Numbers

If a version bump is needed:

  1. Check the current version: grep '^version' shai-cli/Cargo.toml | head -1
  2. Update the version in all crate manifests:
    • shai-cli/Cargo.toml
    • shai-core/Cargo.toml
    • shai-llm/Cargo.toml
    • shai-macros/Cargo.toml
    • Also update Cargo.lock with cargo check or cargo build.
  3. Commit the version bump:
    bash
    git add -A
    git commit -m "chore: release vX.Y.Z"

6. Final Verification

  • Run cargo fmt and cargo clippy to ensure code quality.
  • Run cargo test to verify everything compiles and passes.
  • Show the final git log --oneline to confirm the commit history is clean.

Guidelines

  • Never commit secrets, credentials, or .env files.
  • Always confirm the grouping and version bump with the user before committing.
  • Keep commit messages under 72 characters for the subject line.
  • Use the imperative mood in commit messages (e.g., "Add feature X", not "Added feature X").
  • If changes are interdependent, note the order in which commits should be applied.
  • If a single file contains changes belonging to multiple groups, use git add -p to stage hunks selectively.
  • Do not push unless explicitly asked by the user.
  • If the working tree has merge conflicts, resolve them before attempting to commit.

Frequently asked questions

What does the Repo Analysis AI skill do?

Analyze uncommitted changes in the repository, group them into logical commits, and determine the appropriate version bump

Why use Repo Analysis on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ovh/shai/tree/main/shai-core/examples/skills/repo-analysis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Repo Analysis?

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 Repo Analysis?

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

Is the Repo Analysis AI skill free?

Yes. It is published on GitHub by ovh 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 👇