work-unit-commits

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

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./internal/assets/skills/work-unit-commits/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

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

The body is well-structured and actionable with concrete examples, commands, and verification-oriented checklists. Its main weakness is redundancy between the Work Unit Checklist and the SDD Relationship section, which hurts conciseness.

Suggestions

Consolidate the duplicated verification items (focused test command/result, runtime harness/result, rollback boundary) so they appear once, with the SDD section referencing the checklist instead of restating it.

Merge the 'Budget is not code-golf' rule and the SDD 'Splitting is bounded' note into a single statement to remove the repeated don't-shrink-the-diff guidance.

Add an explicit validate-then-fix feedback loop (e.g., run the focused test, and if it fails fix and re-run before committing) to push workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean tables and lists, but the SDD Relationship section repeats checklist items (focused test command, runtime harness, rollback boundary) and re-iterates the don't-shrink-the-diff rule already in Critical Rules, so it could be tightened.	3 / 5
Actionability	Concrete rules, a weak-vs-better split table with example Conventional Commit messages, and executable git commands give mostly actionable guidance with only minor gaps.	4 / 5
Workflow Clarity	The PR Relationship section gives a clear 4-step sequence and the Work Unit Checklist provides verification gates (test command + result, runtime harness + result), but there is no explicit validate-fix-retry feedback loop, capping it at 4.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (When to Use, Critical Rules, Checklist, Split Examples, PR/SDD Relationship, Commands) with no nested references; it is a single appropriately-scoped file rather than a signaled multi-file overview, so it sits at 4.	4 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 explicit, third-person, and answers both what and when with concrete trigger phrases. It is specific and distinct, with only minor coverage gaps keeping specificity and trigger quality at 4.

Dimension	Reasoning	Score
Specificity	"Plan commits as reviewable work units" names the domain and the trigger list enumerates several concrete scenarios (commit splitting, chained PRs, keeping tests/docs with code); not a fully comprehensive action list, so it sits at 4 rather than 5.	4 / 5
Completeness	It states what ("Plan commits as reviewable work units") and an explicit when ("Trigger: implementation, commit splitting, chained PRs...") with concrete trigger phrases, satisfying the 5 anchor.	5 / 5
Trigger Term Quality	"Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code" uses natural phrases a user would say, with good coverage but a few synonyms missing, matching the 4 anchor.	4 / 5
Distinctiveness Conflict Risk	The work-unit-commits niche is mostly distinct with clear triggers, but it could overlap with general commit-message or PR skills, matching the 4 anchor rather than a fully conflict-free 5.	4 / 5
	Total	17 / 20 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: 71cf25f

Reviewed: 4 days 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.