Tooluck logoTooluck
SKILL.md

chained-pr

Agent skill fromGentleman-Programming/gentle-ai

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

How to install chained-pr

install chained-pr
# install the gentle-ai pack with the skills CLI
npx skills add Gentleman-Programming/gentle-ai

# or add only this skill to Claude Code: copy the folder

internal/assets/skills/chained-pr/

# into

~/.claude/skills/chained-pr/ (all projects)

.claude/skills/chained-pr/ (one project)

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

MITFull file
1## Activation Contract
2
3Load 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.
4
5## Hard Rules
6
7- Split PRs over **400 changed lines** unless a maintainer explicitly accepts `size:exception`.
8- 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.
9- 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.
10- Keep each PR reviewable in about **≤60 minutes**.
11- Use one deliverable work unit per PR; keep tests/docs with the unit they verify.
12- State start, end, prior dependencies, follow-up work, and out-of-scope items in every chained PR.
13- Every child PR must include a dependency diagram marking the current PR with `📍`.
14- 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.
15- Treat polluted diffs as base bugs: retarget or rebase until only the current work unit appears.
16- Do not mix chain strategies after the user chooses one.
17
18## Decision Gates
19
20| Condition | Action |
21|---|---|
22…

Excerpt shown under the repository's MIT license.

More skills in gentle-ai

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates