CtrlK
BlogDocsLog inGet started
Tessl Logo

gentle-ai-branch-pr

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

63

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/branch-pr/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 highly actionable with copy-paste-ready commands and a well-sequenced, checkpointed workflow. Its weakness is conciseness — the same rules are repeated across three sections and reference material Claude already knows is inlined rather than split into bundle files.

Suggestions

De-duplicate the rules: state each rule once in Critical Rules and have the Automated Checks table and Contributor Checklist reference it rather than re-explain it.

Trim the Conventional Commits tutorial (format/allowed-types table) to the project-specific mapping and breaking-change rule, assuming Claude's knowledge of the standard format.

Move the full PR body template into a references/ file and keep only a short inline excerpt, enabling one-level-deep progressive disclosure.

DimensionReasoningScore

Conciseness

The body restates the same handful of rules three times (Critical Rules, the Automated Checks table, and the Contributor Checklist) and inlines a Conventional Commits format Claude already knows, so while mostly efficient reference material it could be tightened — matching the 3 anchor rather than 4.

3 / 5

Actionability

It provides fully copy-paste-ready commands (gh issue view, git checkout -b, gh pr create with a complete --body heredoc, gh pr checks) plus concrete regex patterns and a filled example PR, matching the 5 'fully executable, covers common cases' anchor.

5 / 5

Workflow Clarity

The 7-step workflow sequences clearly with explicit checkpoints (confirm status:approved before starting, run local checks, all automated checks pass before merge) and a checklist, but the repeated 'canonical issue-creation workflow contract' phrasing is opaque enough to leave a minor clarity gap, placing it at 4 rather than 5.

4 / 5

Progressive Disclosure

No bundle files exist and everything is inline in a single ~300-line file, yet section headers (When to Use, Critical Rules, Workflow, Branch Naming, PR Body Format, Automated Checks, Conventional Commits, Commands) make navigation easy and content is well-placed, fitting the 4 'good structure, minor organization gaps' anchor rather than the 5 anchor that requires one-level-deep reference files.

4 / 5

Total

16

/

20

Passed

Description

73%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 cleanly answers both what and when with an explicit trigger clause and a distinct, repo-specific niche. Its main weakness is brevity on the specificity of the 'issue-first checks' it performs.

Suggestions

Expand the 'what' to name the concrete checks performed, e.g. 'Create Gentle AI pull requests that link an approved issue, declare one type:* label, and stay within a 400-line review budget.'

Add a couple of natural trigger synonyms (e.g. 'opening', 'submitting', 'preparing a PR for review') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Quotes 'Create Gentle AI pull requests with issue-first checks' — names the domain plus one concrete action, but does not enumerate the several specific checks involved, matching the 1-2-concrete-actions anchor rather than the several-actions anchor at 4.

3 / 5

Completeness

It states the 'what' ('Create Gentle AI pull requests with issue-first checks') and an explicit 'when' ('Trigger: creating, opening, or preparing PRs for review'), but the 'what' is slightly under-specified ('issue-first checks' is not unpacked), so it sits at 4 rather than a fully concrete 5.

4 / 5

Trigger Term Quality

Quote 'Trigger: creating, opening, or preparing PRs for review' gives good keyword coverage of natural PR-creation verbs; it is not comprehensive enough for a 5 because it omits common synonyms a user might say.

4 / 5

Distinctiveness Conflict Risk

The phrase 'Gentle AI pull requests' carves a clear niche tied to a specific repository with distinct triggers, giving minimal overlap with other skills per the 5 anchor.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Gentleman-Programming/gentle-ai
Reviewed

Table of Contents

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.