Skills for Real Engineers. Straight from my .agents directory.
gentle-ai-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 gentle-ai-chained-pr
npx skills add Gentleman-Programming/gentle-ai# or add only this skill to Claude Code: copy the folder
skills/chained-pr/
# into
~/.claude/skills/chained-pr/ (all projects)
.claude/skills/chained-pr/ (one project)
1## Activation Contract23Load this skill when a planned PR may exceed **400 changed lines**, SDD forecasts `400-line budget risk: High` or `Chained PRs recommended: Yes`, or the user asks for chained/stacked PRs, review slices, or reviewer-load control.45## Hard Rules67- Split PRs over **400 changed lines** unless a maintainer explicitly accepts `size:exception`.8- Keep each PR reviewable in about **≤60 minutes**.9- Use one deliverable work unit per PR; keep tests/docs with the unit they verify.10- State start, end, prior dependencies, follow-up work, and out-of-scope items in every chained PR.11- Every child PR must include a dependency diagram marking the current PR with `📍`.12- 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.13- Treat polluted diffs as base bugs: retarget or rebase until only the current work unit appears.14- Do not mix chain strategies after the user chooses one.1516## Decision Gates1718| Condition | Action |19|---|---|20| PR ≤400 changed lines and focused | Keep single PR. |21| PR >400, each slice can land independently | Use Stacked PRs to main. |22| PR >400, feature must integrate before main | Use Feature Branch Chain with tracker. |23| Generated/vendor/migration diff cannot split cleanly | Ask maintainer for `size:exception`. |24| SDD provides `delivery_strategy` | Follow it before apply/PR creation. |2526## Execution Steps27…
Excerpt shown under the repository's MIT license.
More skills in gentle-ai
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
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
