Work Unit Commits logo

Work Unit Commits

OrganizationPopular
Gentleman-Programming
work-unit-commits

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Overview

PublisherGentleman-Programming
Repositorygentle-ai
Skill namework-unit-commits
Stars
7K
Forks
760
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 Gentleman-Programming on GitHub. Read the source before you install it.

Installation

Install the Work Unit Commits 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.
  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/Gentleman-Programming/gentle-ai.git /tmp/gentle-ai
mkdir -p .claude/skills
cp -r /tmp/gentle-ai/internal/assets/skills/work-unit-commits .claude/skills/work-unit-commits
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Work Unit Commits 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 Work Unit Commits 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 Work Unit Commits 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.

When to Use

Load this skill when deciding what belongs in each commit or PR.

Use it for:

  • Splitting a feature into reviewable work.
  • Preparing commits before opening a PR.
  • Turning a large change into chained or stacked PRs.
  • Keeping reviewer cognitive load healthy.
  • Applying SDD tasks without accidentally producing a PR above 400 changed lines.
  • Closing an ODD task with a work-unit commit.

Critical Rules

RuleRequirement
Commit by work unitA commit represents a deliverable behavior, fix, migration, or docs unit.
Do not commit by file typeAvoid models, then services, then tests if none works alone.
Keep tests with codeTests belong in the same commit as the behavior they verify.
Keep docs with the user-visible changeDocs belong with the feature or workflow they explain.
Tell a storyA reviewer should understand why each commit exists from its diff and message.
Future PR-readyEach commit should be a candidate chained PR when the change grows.
SDD workload guardIf SDD tasks forecast a >400-line change, group commits into chained PR slices before implementation.
Budget is not code-golfNever shrink a diff by deleting comments, blank lines, docs, or tests, or by compressing code, to fit the review budget (400 by default, or the session review_budget_lines). Slice by work unit or report the overage.

Work Unit Checklist

Before committing, confirm:

  • The commit has one clear purpose.
  • The repo still makes sense after applying only this commit.
  • Tests or docs for this unit are included when relevant.
  • Rollback is reasonable without reverting unrelated work.
  • Focused test command and exact result are recorded.
  • Runtime harness command/scenario and exact result are recorded, or explicit N/A explains why no runtime boundary exists.
  • Rollback boundary names the exact files/behavior removable without unrelated work.
  • The commit message explains the outcome, not the file list.

Split Examples

Weak splitBetter work-unit split
add modelsfeat(auth): add token validation domain model and tests
add servicesfeat(auth): wire token validation into login flow
add testsTests included with each behavior commit
update docsDocs included with the user-facing change they explain

PR Relationship

Use work-unit commits as the foundation for chained PRs:

  1. Build the smallest independent work unit.
  2. Include verification for that unit.
  3. Commit it with a Conventional Commit message.
  4. If the PR approaches 400 changed lines, promote commits or groups of commits into chained PRs.

SDD Relationship

When sdd-tasks produces a Review Workload Forecast:

  • Low risk: keep work-unit commits inside one PR.
  • Medium risk: commit by work unit and monitor changed lines before PR creation.
  • High risk: follow SDD delivery_strategy — ask on ask-on-risk, auto-slice on auto-chain, require size:exception on over-budget single-pr, or record accepted size:exception on exception-ok.
  • Count authored additions plus deletions for the >400 threshold. Exclude generated goldens from that authored count, but include every generated file in complete snapshot identity and receipt validation.
  • Splitting is bounded: after one honest slicing pass, if no cohesive work-unit split fits the budget, stop and report the smallest honest count with a size:exception recommendation. Do not iterate shrinking the code to reach the number.

Each SDD work unit should map cleanly to a commit or PR with:

  • clear start state,
  • clear finished state,
  • verification in the same unit,
  • rollback that does not remove unrelated work.

Its implementation evidence MUST include:

  • Focused test command and exact result.
  • Runtime harness command/scenario and exact result, or explicit N/A with reason.
  • Rollback boundary stated independently of commit creation; uncommitted work units still require it.
  • When fixing a bounded review ledger, group atomic work units inside the single correction transaction; work-unit count never creates another fix budget.

ODD Relationship

Organic Driven Development (ODD) closes every substantial task with a work-unit commit on the feature branch, not only SDD tasks:

  • Every ODD task closes with at least one work-unit commit, branch first when on the default branch, with tests and docs alongside the behavior and a Conventional Commit message.
  • The native review candidate is that commit, or the PR slice it belongs to when review is deferred, against the previous reviewed boundary. It is never a TODO checkbox and never the accumulated feature branch.
  • The running authored line count from work-unit commits feeds the same delivery-strategy vocabulary as SDD: ask-on-risk, auto-chain, single-pr, exception-ok.
  • The ODD feature document records the commit identity as evidence and, once a delivery strategy applies, the chosen chain strategy and slice boundaries (which commits each PR holds).

Commands

bash
# Review the story before committing
git diff --stat
git diff --cached --stat

# Check recent commit style
git log --oneline -5

Frequently asked questions

What does the Work Unit Commits AI skill do?

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Why use Work Unit Commits on TypingMind?

Because you install it once and use it with any model. Work Unit Commits 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 Work Unit Commits in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Gentleman-Programming/gentle-ai/tree/main/internal/assets/skills/work-unit-commits. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Work Unit Commits?

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 Work Unit Commits?

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

Is the Work Unit Commits AI skill free?

Yes. It is published on GitHub by Gentleman-Programming 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 👇