work-unit-commits

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

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is token-efficient and highly actionable, with concrete commands, examples, and a verification checklist. It loses points on workflow clarity and progressive disclosure: the commit/PR process lacks an explicit error-recovery feedback loop, and the specialized SDD material is monolithically inline with no progressive disclosure structure.

Suggestions

Add an explicit feedback loop to the PR Relationship workflow (e.g., run the focused test command, and only commit when it passes; if it fails, fix and re-run) so validation acts as a gate rather than a recorded checkbox.

Move the dense SDD integration details (delivery_strategy, ask-on-risk / auto-chain / size:exception triggers, bounded review ledger rules) into a one-level-deep reference file (e.g., SDD.md) and link to it from a short overview section.

Expand the Commands section with the actual commit-creation command and a complete Conventional Commit example so the core action is copy-paste ready, not just the diff/log inspection helpers.

Dimension	Reasoning	Score
Conciseness	The body is lean: compact tables, a checklist, and terse rules with no padding about concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	Concrete copy-paste git commands, a before/after split-examples table with real Conventional Commit messages, an exact 400-line threshold, and a specific pre-commit checklist make the guidance directly actionable.	3 / 3
Workflow Clarity	The PR Relationship gives a numbered 4-step sequence and the checklist records verification, but there is no explicit validate-then-fix-then-retry feedback loop, leaving checkpoints partly implicit.	2 / 3
Progressive Disclosure	It is a single well-sectioned file with no bundle references, but at ~88 lines the dense SDD-specific material (delivery_strategy, ask-on-risk, size:exception) is inline rather than split into a one-level-deep reference.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, third-person, and clearly answers both what the skill does and when to use it with natural trigger terms. It carves a distinct niche around reviewable work-unit commits with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	"Plan commits as reviewable work units" plus "commit splitting, chained PRs, or keeping tests and docs with code" lists multiple concrete actions rather than vague language, matching the score-3 anchor.	3 / 3
Completeness	It states what ("Plan commits as reviewable work units") and an explicit when ("Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code"), satisfying the what-AND-when anchor.	3 / 3
Trigger Term Quality	"commit splitting", "chained PRs", and "keeping tests and docs with code" are natural phrases a user would say when needing this skill, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	The commit/PR work-unit niche with triggers like "chained PRs" and "keeping tests and docs with code" is distinct and unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/work-unit-commits/SKILL.md
Commit: e01b114

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.