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.

58

Quality

66%

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

63%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 a solid, largely executable workflow document with strong validation checkpoints and concrete commands. Its weaknesses are heavy repetition of policy conditions across sections and a monolithic single-file layout that inlines template/example material that belongs in reference files.

Suggestions

State each policy condition (authorization contract, size:exception authority) once in Critical Rules and reference it elsewhere — e.g. replace repeated clauses in the checklist and Automated Checks table with "per Rule 3".

Move the full PR body schematic and the commit-message example set into a references/ file (e.g. references/pr-template.md, references/conventional-commits.md) and keep only the pattern plus one example inline.

Make step 3 of the Workflow concrete by naming the applicable local checks (go test ./..., go run ./internal/gofmtcheck) instead of "run applicable local checks".

DimensionReasoningScore

Conciseness

The body teaches nothing Claude already knows and its tables earn their place, but authorization boilerplate ("a current direct human instruction binding the exact target/action") and size:exception authority conditions are restated verbatim 4-6 times across Critical Rules, Workflow, the checklist, and the Automated Checks table.

3 / 5

Actionability

Concrete executable commands (gh issue view, go test ./..., gh pr checks), exact regex patterns, a full PR-body schematic, and a type-to-label mapping table give mostly copy-paste-ready guidance; minor gaps like "run applicable local checks" and the deliberately non-executable PR-creation step keep it below a 5.

4 / 5

Workflow Clarity

The five-step workflow is clearly sequenced with explicit validation checkpoints (verify status:approved, resolve the default branch rather than assuming main, mark checkboxes only after observed readback, report baseline unverified). Step 3's "run applicable local checks" is vague and error-recovery guidance is thin, so it does not reach a 5.

4 / 5

Progressive Disclosure

The single-file body is well-organized with headers and tables, but ~250 lines inline the full PR-body template and twelve commit-message examples — content that clearly belongs in reference files; no bundle structure exists to offload it.

3 / 5

Total

14

/

20

Passed

Description

70%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 well-formed: third-person, concise, with an explicit trigger clause — better than most. Its main limitation is a thin statement of what the skill covers relative to its actual breadth (branch naming, commit format, CI gating).

Suggestions

Expand the what-clause to name 2-3 more concrete capabilities, e.g. "Create Gentle AI branches and pull requests with issue-first checks, conventional commits, and CI verification."

Add natural trigger synonyms such as "pull request", "open a PR", and "create a branch" to widen trigger coverage.

DimensionReasoningScore

Specificity

"Create Gentle AI pull requests with issue-first checks" names the domain and one concrete action, but omits branch creation, commit-format enforcement, and CI verification that the body actually covers — not comprehensive coverage of capabilities.

3 / 5

Completeness

Both a clear what ("Create Gentle AI pull requests with issue-first checks") and an explicit when ("Trigger: creating, opening, or preparing PRs for review") are present; the what side is narrower than the skill's actual scope, keeping it just below a 5.

4 / 5

Trigger Term Quality

"Trigger: creating, opening, or preparing PRs for review" includes natural phrases users would say, but misses common synonyms such as "pull request" spelled out, "open a PR", and "branch".

4 / 5

Distinctiveness Conflict Risk

The repo-specific qualifier "Gentle AI pull requests" carves a clear niche, but the trigger phrase ("creating, opening, or preparing PRs for review") overlaps generic PR-creation skills, leaving minor conflict risk.

4 / 5

Total

15

/

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.

Validation — 16 / 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.