Ready to supercharge your AI agents?

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

Chained PR · gentleman-programming | DecimalAI

code reviewby gentleman-programming

Chained PR

gentleman-programming/chained-pr

Source gentleman-programming/gentle-ai ↗License MIT

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

SkillScore100Maintained

Automatic

Coding pack

Last verified 10/7/2026

What it changes

Passed 27 of 27 test cases with the skill, and 16 of 27 without it.

Without skill59%

With skill100%

Checks it passed that the model alone missed

Advises stopping after one slicing pass.
Marks the active PR with 📍 in the dependency map.
Selects Stacked PRs to main as the chaining strategy.

and 13 more in the full report

11 fixed16 passed either way0 still failing0 broke

Pass-rate lift: +41 pp
Tokens: -2%
Agent turns: 0%
Response time: -42%

Model gemini-3.6-flashMeasured 10/7/2026v327 of 27 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-chained-pr/SKILL.md https://app.decimal.ai/s/gentleman-programming-chained-pr/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add gentleman-programming-chained-pr, 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-chained-pr/ and pins it in .decimal/skills.lock

decimalai skills add gentleman-programming-chained-pr

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

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

Raw file: /s/gentleman-programming-chained-pr/SKILL.md ↗ · machine-readable summary at /s/gentleman-programming-chained-pr.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

What is the target review duration that each PR slice should aim for to avoid overburdening code reviewers?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies a review time target of 60 minutes per PR slice.	Missed	Passed

case-11 · gemini-3.6-flash · 10/7/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md44 lines2 files

Activation Contract

Load this skill when a planned PR may exceed 400 changed lines, an ODD feature's forecast or running authored changed-line count from work-unit commits exceeds about 400, or the user asks for chained/stacked PRs, review slices, or reviewer-load control.

Hard Rules

Split PRs over 400 changed lines unless a maintainer explicitly accepts size:exception.
The budget constrains how work is sliced, never the code itself. Never delete comments, blank lines, docs, or tests, and never compress or restyle code, to fit under the budget.
Slicing is bounded: make one honest slicing pass. If no cohesive split brings every slice within budget, stop iterating, keep the best cohesive split, and report the final line count with a size:exception recommendation.
Keep each PR reviewable in about ≤60 minutes.
Use one deliverable work unit per PR; keep tests/docs with the unit they verify.
State start, end, prior dependencies, follow-up work, and out-of-scope items in every chained PR.
Every child PR must include a dependency diagram marking the current PR with 📍.
In Feature Branch Chain, create a draft/no-merge tracker PR; child PR #1 targets the tracker branch, later children target the immediate parent branch.
Treat polluted diffs as base bugs: retarget or rebase until only the current work unit appears.
Do not mix chain strategies after the user chooses one.

Decision Gates

Condition	Action
PR ≤400 changed lines and focused	Keep single PR.
PR >400, each slice can land independently	Use Stacked PRs to main.
PR >400, feature must integrate before main	Use Feature Branch Chain with tracker.
Generated/vendor/migration diff cannot split cleanly	Ask maintainer for `size:exception`.
No cohesive split fits the budget after one slicing pass	Stop; deliver the best split, report the overage and why it cannot shrink further, and recommend `size:exception`.
ODD provides `delivery_strategy` and `chain_strategy`	Follow them before the next work-unit commit or PR creation.

Execution Steps

Estimate changed lines and identify independent work units.
Ask for a chain strategy when none is cached and the budget is exceeded.
Create branches/PRs using the chosen strategy only.
Add Chain Context to each PR without replacing the repo PR template.
Verify each PR independently: CI/tests/docs/manual checks, rollback scope, and clean diff.
Keep tracker PR draft/no-merge until all child PRs are reviewed and integrated.

Output Contract

Return the chosen strategy, PR order, current PR boundary, dependency diagram, review budget (additions + deletions), verification plan, and any size:exception rationale.

Track record

Benchmark

27 / 27

test cases passed, vs 16 / 27 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 — 10/6/2026

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

internal/assets/skills/chained-pr/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/6/2026Version v3Bundled 1 file

Other skills for the same job

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

gentleman-programming/gentle-ai-chained-prTrigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.Near-identical description+32 pp pass-rate lift

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