CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gentle-ai-branch-pr

Trigger: preparing branches or PRs for Gentleman-Programming/gentle-ai. Apply this repository's issue-first contribution policy.

Quality

72%

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 delivers strong repo-specific actionability — exact patterns, commands, and label mappings with genuine validation gates in the workflow. Its weaknesses are repetition of authorization boilerplate, a large inline PR-template schematic that belongs in a reference file, and reliance on an external 'canonical issue-creation workflow contract' that is never defined in the bundle.

Suggestions

Move the PR body schematic and the commit-convention tables into reference files (e.g. references/pr-template.md, references/commit-conventions.md) and keep one-line, clearly signaled pointers in SKILL.md.

Deduplicate the authorization/label-mutation gating language: state the 'canonical issue-creation workflow contract' requirements once and reference that section, instead of repeating the full clause in Critical Rules, the Workflow, and the Automated Checks table.

Remove the verbatim duplication between the Test Plan checkboxes and the Contributor Checklist checkboxes in the PR schematic.

DimensionReasoningScore

Conciseness

The content is mostly repo-specific and non-padded (exact regexes, command blocks, label mappings), but the authorization boilerplate ('current direct human instruction binding the exact target/action', 'canonical issue-creation workflow contract') is repeated nearly verbatim in Critical Rules, the taxonomy paragraph, Workflow step 4, and the Automated Checks table, and the checklist test items appear twice within the PR schematic. It fits anchor 3 ('mostly efficient but could be tightened') better than 2, since there is no explanation of concepts Claude already knows.

3 / 5

Actionability

Concrete, executable material dominates: exact branch-name and commit-message regexes, runnable commands (`gh issue view`, `go test ./...`, `gh pr checks`), type-to-label tables, and a full PR body schematic. Not 5 because the central action (creating the PR) deliberately has no command ('this skill provides no executable creation command') and the repeatedly-invoked 'canonical issue-creation workflow contract' is never defined in this file, leaving those gates non-executable.

4 / 5

Workflow Clarity

The Workflow section gives a clear 5-step sequence with real validation checkpoints: verify `status:approved` before proceeding, run local checks before drafting, 'Mark checkboxes only after observed readback', and 'Unknown requiredness is not merge-ready'. Not 5 because error-recovery loops are thin (only 'Fix failing tests before pushing' in the table) and the checkpoints for label mutation defer to an undefined external contract.

4 / 5

Progressive Disclosure

The single-file bundle has no reference files, while ~70 lines of PR-template schematic plus the branch-naming and commit-convention tables are exactly the kind of lookup material that belongs in separate one-level-deep references. Section headers are clear, so navigation works, but this matches anchor 3 ('content that should be separate is inline') rather than 4's 'most content is appropriately placed'.

3 / 5

Total

14

/

20

Passed

Description

66%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 has an explicit, highly distinctive repo-scoped trigger, but undersells the skill's capabilities with a single abstract action phrase. Expanding the 'what' with concrete actions and more natural trigger synonyms would raise specificity and trigger-term quality.

Suggestions

Enumerate the concrete actions in the description, e.g. 'Creates conventionally named branches, drafts PRs against the repository template, and verifies required CI checks' instead of the abstract 'Apply this repository's issue-first contribution policy'.

Add natural trigger synonyms such as 'pull request', 'open a PR', 'commit', or 'contribute to' alongside 'preparing branches or PRs'.

DimensionReasoningScore

Specificity

"Apply this repository's issue-first contribution policy" names the domain and one concrete action, but the description never enumerates what the skill actually does (branch creation, PR drafting, naming/commit conventions, check verification are all body-only). It matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than 4, which expects several listed specific actions.

3 / 5

Completeness

Both parts are present: the 'when' is an explicit trigger clause ("Trigger: preparing branches or PRs for Gentleman-Programming/gentle-ai") and the 'what' is "Apply this repository's issue-first contribution policy". Not 5 because the 'what' is abstract (it doesn't say what applying the policy involves); not 3 because the trigger guidance is explicit, not merely implied.

4 / 5

Trigger Term Quality

"Trigger: preparing branches or PRs for Gentleman-Programming/gentle-ai" includes relevant keywords (branches, PRs, repo name), but misses natural variations users would say such as "pull request", "open a PR", "commit", or "contribution". Not score 4 because keyword coverage is thin beyond the two core terms.

3 / 5

Distinctiveness Conflict Risk

The trigger is pinned to a single named repository ("Gentleman-Programming/gentle-ai"), creating a clear niche with minimal conflict risk against generic branch/PR or git skills. This clearly matches the anchor-5 example of a distinct, well-scoped trigger.

5 / 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

Path

skills/branch-pr/SKILL.md

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.