Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Review the story before committing · gentleman-programming | DecimalAI

code reviewby gentleman-programming

Review the story before committing

gentleman-programming/work-unit-commits

Source gentleman-programming/gentle-ai ↗License MIT

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

SkillScore87Maintained

Automatic

Coding pack

Last verified 9/29/2026

What it changes

Passed 20 of 23 test cases with the skill, and 9 of 23 without it.

Without skill39%

With skill87%

Checks it passed that the model alone missed

recommends running git diff --stat
requires recording the exact test command
lists delivery strategy option auto-chain

and 16 more in the full report

11 fixed9 passed either way3 still failing0 broke

Pass-rate lift: +48 pp
Tokens: -2%
Agent turns: 0%
Response time: -46%

Model gemini-3.6-flashMeasured 9/29/2026v520 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/gentleman-programming-work-unit-commits/SKILL.md https://app.decimal.ai/s/gentleman-programming-work-unit-commits/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gentleman-programming-work-unit-commits, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/gentleman-programming-work-unit-commits/ and pins it in .decimal/skills.lock

decimalai skills add gentleman-programming-work-unit-commits

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/gentleman-programming-work-unit-commits/SKILL.md https://app.decimal.ai/s/gentleman-programming-work-unit-commits/SKILL.md

Raw file: /s/gentleman-programming-work-unit-commits/SKILL.md ↗ · machine-readable summary at /s/gentleman-programming-work-unit-commits.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

Which git commands should a developer run before committing to inspect the full story and staged boundaries of their changes?

What was checked, without and with the skill
Checked	Without skill	With skill
recommends running git diff --stat	Missed	Passed
recommends running git diff --cached --stat	Missed	Passed

case-20 · gemini-3.6-flash · 9/29/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md74 linessingle file

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.
Closing an ODD task with a work-unit commit.

Critical Rules

Rule	Requirement
Commit by work unit	A commit represents a deliverable behavior, fix, migration, or docs unit.
Do not commit by file type	Avoid `models`, then `services`, then `tests` if none works alone.
Keep tests with code	Tests belong in the same commit as the behavior they verify.
Keep docs with the user-visible change	Docs belong with the feature or workflow they explain.
Tell a story	A reviewer should understand why each commit exists from its diff and message.
Future PR-ready	Each commit should be a candidate chained PR when the change grows.
Budget is not code-golf	Never 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 split | Better work-unit split |

Track record

Benchmark

20 / 23

test cases passed, vs 9 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/29/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

gentleman-programming / gentle-ai

skills/work-unit-commits/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 9/29/2026Version v5

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

gentleman-programming/gentle-ai-work-unit-commitsPlan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.Near-identical description+20 pp pass-rate lift

More skills from the same source and nearby in the registry, with their headline benchmark lift.