gentle-ai-branch-pr

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

Quality

80%

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

78%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.

A highly actionable, well-structured reference with executable commands and templates and clear workflow checkpoints. Its main gaps are mild command/checklist repetition and a monolithic single-file structure with no progressive disclosure into bundle files.

Suggestions

Move the full PR body template and Conventional Commits reference into separate reference files (e.g., PR_TEMPLATE.md, CONVENTIONAL_COMMITS.md) linked from SKILL.md to improve progressive disclosure.

Deduplicate the test commands and contributor checklist rules that recur across the PR Body Format, Automated Checks, and Commands sections to tighten conciseness.

Make the workflow's validation feedback loop explicit (e.g., 'if checks fail: fix and re-run until green') to lift workflow clarity toward 5.

Dimension	Reasoning	Score
Conciseness	Lean reference material with no padding of concepts Claude already knows; every section earns its place. Mild redundancy (test commands and checklist rules recur across PR Body Format, Automated Checks, and Commands) keeps it just below a 5.	4 / 5
Actionability	Fully executable guidance throughout: concrete gh/git/go commands, exact regex patterns, a complete PR body template, and a copy-paste-ready 'gh pr create' heredoc example covering the common case.	5 / 5
Workflow Clarity	Clear numbered sequence with validation checkpoints present (confirm issue approved in step 1, run local checks in step 4, all checks must pass in step 7) plus a How-to-Fix table. Not a 5 because the validate-fix-retry feedback loop is implicit in the workflow block rather than spelled out as an explicit loop.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, but it is a ~300-line monolithic file with no bundle references — content that could be split (full PR template, Conventional Commits reference, command catalog) is all inlined. Not a 4 because no content is actually offloaded to separate one-level-deep files.	3 / 5
	Total	16 / 20 Passed

Description

82%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.

A strong, third-person description that explicitly states both capability and trigger conditions with concrete phrases. Its only weakness is modest action specificity and reliance on the 'PR' abbreviation rather than spelling out synonyms.

Suggestions

Spell out 'pull request' alongside 'PR' and add a synonym like 'submitting' to broaden trigger-term coverage toward a 5.

List one or two more concrete actions (e.g., 'apply type labels', 'validate against CI checks') to raise specificity from 3 toward 4-5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Gentle AI pull requests') and 1-2 concrete actions ('Create', 'issue-first checks') but is not comprehensive; it does not enumerate the full set of PR-related actions. Not a 4 because only a couple of actions are named rather than several specific ones.	3 / 5
Completeness	Clearly answers both 'what' ('Create Gentle AI pull requests with issue-first checks') and 'when' with concrete, explicitly-labeled trigger phrases ('Trigger: creating, opening, or preparing PRs for review'). Matches the anchor for explicit what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Explicit 'Trigger:' clause lists natural user phrases ('creating, opening, or preparing PRs for review'). Good keyword coverage but relies on the 'PR' abbreviation and omits synonyms like 'submitting' or 'pull request' spelled out, so it falls short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Scoped to a named repo workflow ('Gentle AI pull requests') with issue-first gating, giving it a clear niche and distinct triggers with minimal overlap risk against generic skills.	5 / 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: skills/branch-pr/SKILL.md
Commit: a245f26

Reviewed: 1 day 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.