gentle-ai-branch-pr

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%

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

A highly actionable, well-sequenced PR/branch reference with concrete commands, validation checkpoints, and a clear workflow. Its main weaknesses are notable content duplication across sections and a large single-file footprint with no progressive disclosure into reference files.

Suggestions

Deduplicate the PR body template, the Critical Rules, and the Automated Checks table—the template is reproduced nearly verbatim a third time inside the `gh pr create` example; consolidate to a single canonical source.

Move the large reference material (the full PR body template and the Conventional Commits type→label table) into a `references/` file and link to it from SKILL.md so the overview stays lean, improving progressive_disclosure.

Keep the 'Critical Rules' as the authoritative checklist and have later sections reference it (e.g., 'see Critical Rules') instead of restating each rule inline in the template and checks table.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes competence (no concept padding), but it duplicates the same information across Critical Rules, the PR body template, the Automated Checks table, and the full worked `gh pr create` example, so it is 'mostly efficient but could be tightened'.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands (`gh issue view`, `git checkout -b`, `go test ./...`, `cd e2e && ./docker-test.sh`, a complete `gh pr create`) plus concrete regex patterns and label mappings, matching the score-3 anchor.	3 / 3
Workflow Clarity	The numbered 7-step workflow opens with a validation checkpoint (confirm issue approval), and the Automated Checks table supplies explicit pass/fail validation with 'How to Fix' recovery guidance and a contributor checklist, satisfying the score-3 anchor.	3 / 3
Progressive Disclosure	It is a single well-organized file with clear section headers (no deep nesting), but at ~300 lines with no bundle files it keeps large reference material (full PR template, commit-type table, worked PR example) inline rather than split into one-level-deep references, matching the score-2 anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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

A concise, third-person description that clearly states what it does and when to use it via an explicit trigger clause, scoped to a distinct niche. Its only weakness is moderate specificity—it names the main action but does not list several discrete concrete capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain and primary action ('Create Gentle AI pull requests with issue-first checks') but does not enumerate multiple distinct concrete actions the way the score-3 anchor does, so it stops at 'domain and some actions, not comprehensive'.	2 / 3
Completeness	It answers both 'what' (create issue-first PRs) and 'when' via an explicit 'Trigger:' clause, which is the equivalent explicit-trigger form the rubric requires for a 3.	3 / 3
Trigger Term Quality	The explicit 'Trigger: creating, opening, or preparing PRs for review' covers natural verbs a user would actually say when they need this skill, matching the score-3 anchor's coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	It is scoped to a specific niche ('Gentle AI pull requests' on the Gentleman-Programming/gentle-ai repo) with PR-specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: skills/branch-pr/SKILL.md
Commit: e01b114

Reviewed: about 14 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.