Git Delivery logo

Git Delivery

CommunityPopular
ryan4yin
git-delivery

Writes commit messages, pull/merge request and issue text, and review replies that follow the target repository's conventions, and cleans up after merge. Use when committing, opening or updating a PR/MR or issue, answering code review, or finishing after a reviewed change merges.

Overview

Publisherryan4yin
Repositorynix-config
Skill namegit-delivery
Stars
2.1K
Forks
104
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by ryan4yin on GitHub. Read the source before you install it.

Installation

Install the Git Delivery 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/ryan4yin/nix-config/tree/main/agents/skills/git-delivery
  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/ryan4yin/nix-config.git /tmp/nix-config
mkdir -p .claude/skills
cp -r /tmp/nix-config/agents/skills/git-delivery .claude/skills/git-delivery
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Git Delivery 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 Git Delivery 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 Git Delivery 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.

Git Delivery

A diff that needs a long explanation is a diff to fix first: rename the thing, split the commit, or put the reason in a comment at its primary location. Delivery text carries only what no artifact can show, for a reader without the task's context: the reviewer now, and the maintainer reading git log or git blame years later. The caps below are the standard: a draft over a cap is cut until it fits, not justified. This skill grants no authorization.

Read examples.md for short messages and descriptions that follow these rules.

Before writing

Run git log --no-merges -n 20 -- <touched paths> and read any contribution guide and PR template, every time, even for a one-line change. Name in one line the convention you followed and where you found it.

  1. The repository's conventions override the defaults below. Supply required metadata (sign-off, links, AI disclosure) only when true; never invent identities, and do not carry one repository's requirements into another.
  2. Identify the comparison base and destination separately. Report an identity or hosting-account mismatch instead of editing Git config.
  3. Describe what is actually delivered: the staged diff for a commit, the full diff against the base for a PR — not the task title or an earlier attempt.
  4. Collect what the diff cannot show: the problem and its impact, costs and side effects (with numbers when measured), and rejected alternatives a reader would otherwise propose. The caps decide what survives. Ask instead of inventing a reason.

Commit messages

  • Subject: the repository's prefix convention, defaulting to Conventional Commits; imperative, aiming at 50 characters with 72 as the ceiling.
  • Body: zero lines unless the change has an effect the diff does not show — data deleted or rewritten outside the changed lines, a stored format or an option other code reads changing meaning, or a running system touched beyond what the changed lines say. A version bump, a config value, a moved and re-grouped file, or a formatter, lint, or build setting states its own effect: no body. When a trigger applies: at most 2 sentences and 40 words, and every sentence names an effect, not a motive. Otherwise the reason goes in the subject when it fits inside the ceiling. Never in a body: file lists, change counts, the measurement that motivated the change, alternatives, or how the problem was found.
  • Summarize an issue instead of only linking it; cite another commit by abbreviated hash and subject. Trailers go last in the repository's format (Fixes:, Refs:, Signed-off-by:, BREAKING CHANGE:), and credit other people only as the repository's policy allows. Notes meant only for current reviewers, such as changes since the last round, stay out.
  • Pass the message with git commit -F <file> or one -m per paragraph. If a hook rejects the commit, nothing was committed: fix the cause and commit again, since --amend would rewrite the previous commit.

Pull/merge requests

The description often becomes the squash-merge message. Check for an existing open PR for the same branch or issue.

  • Title: a commit subject for the whole change.
  • Body: at most 80 words normally, or 160 only for migration or rollback steps, a risk the reviewer must weigh, or a measured result the reviewer cannot see. Use short paragraphs or up to 5 bullets to separate distinct points; brevity should make the change easy to scan. Lead with the changed behavior and its effect. Follow the repository template when one exists; check only boxes that are true. Add only what the change needs: a breaking change names the affected interface, before and after, and the migration; an operational one names the operator effect and measured impact; a cross-cutting one says why the breadth is necessary and where review should start.
  • Self-check before submitting: count. Subject ≤72 characters; commit body 0 lines, or ≤2 sentences and ≤40 words; description ≤80 words, or ≤160 with one of the named triggers. Over a cap, cut in this order until under: anything the diff already shows, then supporting numbers, then alternatives, then adjectives. Report the counts with the draft.
  • Do not add default Summary/Changes/Test Plan headings, pasted commands, CI logs, commit lists, or exhaustive file lists, and cut any sentence a reviewer cannot act on. Replace internal process terms (plan steps, task numbers, agent names) with the behavior they refer to.
  • Verification: report the checks that establish behavior or coverage, with revision and platform; skip routine lint. A build does not show runtime behavior. Once the code changes, an earlier result is historical: rerun it or label it and say what remains unverified.
  • Fixes #123 only for a verified issue in the target repository that this change resolves; Refs only links.
  • Write as if the diff had been written in one pass: state what is excluded and why, not who asked or how the branch evolved. When later commits change scope, risk, or migration, rewrite title and description. After a follow-up push, answer in the existing threads, naming the new commit; do not post a separate summary of what changed since the last round unless the repository's guide or a reviewer asks.
  • Pass multiline text from a file (gh pr create --body-file) and keep the configured Git transport and identity when submitting fails. Before publishing, review the exact outgoing text for internal identifiers, private paths, and anything not already public in that repository.

Review replies

  • Treat each comment as a claim to check against the code and the repository's rules; reviewers and review bots can be wrong. Ask when a comment is unclear.
  • If a reviewer misunderstood the code, make the code clearer or add a comment first; a reply alone does not help later readers.
  • Answer in the thread, naming the commit (Fixed in 1a2b3c4: ...). Keep replies to accepted comments short; give declined ones the full reasoning and the tradeoff weighed. Skip filler.
  • Resolve a thread only when addressed and the repository expects authors to resolve. Never claim a fix or check that did not happen. An approval covers only what that reviewer reviewed, and notify only relevant reviewers.

After merge

For a confirmed-merged PR the agent opened: identify its branches and worktrees from the task record, not by name pattern; remove a worktree only when clean and from outside it; delete the local branch with git branch -d and report when it refuses instead of forcing; fast-forward the default branch only when its checkout is clean and not diverged, then verify. Keep branches while review is open; deleting a remote branch needs separate authorization.

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 Git Delivery AI skill do?

Writes commit messages, pull/merge request and issue text, and review replies that follow the target repository's conventions, and cleans up after merge. Use when committing, opening or updating a PR/MR or issue, answering code review, or finishing after a reviewed change merges.

Why use Git Delivery on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ryan4yin/nix-config/tree/main/agents/skills/git-delivery. 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 Git Delivery?

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 Git Delivery?

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

Is the Git Delivery AI skill free?

Yes. It is published on GitHub by ryan4yin 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 👇