branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or…
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
$ npx -y skills add gentleman-programming/gentle-shell --skill work-unit-commits --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/work-unit-commitsContext preview
The summary Claude sees to decide when to auto-load this skill.
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
name: gentle-ai-work-unit-commits description: "Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code." license: Apache-2.0 metadata: author: gentleman-programming version: "1.0"
Load this skill when deciding what belongs in each commit or PR.
Use it for:
| 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. | | SDD workload guard | If SDD tasks forecast a >400-line change, honor the selected `delivery_strategy`. On chaining paths only, group commits into chained PR slices before implementation. For explicit `single-pr` or `exception-ok`, keep one PR, report the review load, and follow the destination repository's documented contribution/size policy; selection alone does not accept an exception. | | 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. |
Before committing, confirm:
| Weak split | Better work-unit split | |------------|------------------------| | `add models` | `feat(auth): add token validation domain model and tests` | | `add services` | `feat(auth): wire token validation into login flow` | | `add tests` | Tests included with each behavior commit | | `update docs` | Docs included with the user-facing change they explain |
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.
When `sdd-tasks` produces a Review Workload Forecast:
Each SDD work unit should map cleanly to a commit or PR with:
Every ODD task closes with at least one work-unit commit:
# Review the story before committing git diff --stat git diff --cached --stat # Check recent commit style git log --oneline -5
Gentle Shell is a Pi-native coding-agent harness for controlled development with Organic Driven Development, optional SDD/OpenSpec, subagents, TDD evidence, review guardrails, skills, and memory integrations.
Repo: gentleman-programming/gentle-shell
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or…
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained…
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding,…
Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews,…
Use Gentle AI harness discipline for Pi work: clarify first, track ODD work, use applicable…
Create and triage GitHub issues from repository evidence. Trigger: issue creation, bug…