CtrlK
BlogDocsLog inGet started
Tessl Logo

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review.

67

Quality

80%

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

SKILL.md
Quality
Evals
Security

Quality

Content

73%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 dense, highly actionable instruction skill with strong workflow sequencing and validation culture. Its main cost is token weight: repeated authorization boilerplate and over-engineered sentences inflate the body without adding information, and the branch step lacks a concrete command.

Suggestions

State the authorization requirement once in a single section (e.g. under 'Verification protocol') and reference it elsewhere ('per the authorization rule above') instead of repeating the full sentence in four places.

Make the 'Branch' step concrete: give the actual `git checkout -b <type>/<short-description>` command with one matching example branch name instead of a comment-only block.

Move the chained-PR strategy detail (Stacked vs Feature Branch Chain pros/cons) and the anti-patterns table into referenced files, keeping only the decision rule and a few top anti-patterns inline.

DimensionReasoningScore

Conciseness

The body does not explain concepts Claude already knows, but the authorization boilerplate ("obtain explicit authorization for the exact remote destination, operation and credential/session") repeats nearly verbatim across at least four sections, and several sentences are convoluted (e.g. the rule-3 canonical issue-creation contract sentence). Anchors for 4 require efficiency with only minor over-explanation; the repetition here is more than minor.

3 / 5

Actionability

Provides copy-paste-ready commands (`gh pr view <N> --repo "$TARGET" --json labels,closingIssuesReferences,additions,deletions,changedFiles`), exact regexes, and a per-section PR template mapping. Not a 5 because the 'Branch' step is a comment-only pseudocode block with no executable command, and several rules defer mechanics to external files without a concrete example.

4 / 5

Workflow Clarity

The PR workflow (steps 1-6) is clearly sequenced with explicit validation gates (local validation: `go build`/`go vet`/`go test`), a pre-PR self-audit checklist, and verification-protocol feedback loops ('if different, request separate authorization before editing the body', 'Compare in an isolated clean base or mark baseline unverified'). This matches the anchor with explicit validation steps, error-recovery loops, and a checklist.

5 / 5

Progressive Disclosure

No bundle files exist locally, and the References section lists one-level-deep external repo files clearly with what each provides ('CONTRIBUTING.md — full workflow, label taxonomy...'). Structure is good, but some inline content (the chained-PR strategy section and the long anti-patterns table) is detailed enough that it could live in a referenced file, keeping it at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

87%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, repo-gated description with an explicit load trigger and concrete scope enumeration. The main weaknesses are minor: a couple of capability areas stay abstract and a few natural synonyms (e.g. 'pull request', 'code review') are missing.

Suggestions

Replace abstract noun phrases like 'verification protocol' and 'docstring coverage' with the concrete actions they entail (e.g. 'cross-check PR body claims against the GitHub API', 'verify Go docstring coverage on exported symbols').

Add natural synonym triggers such as 'pull request' spelled out, 'code review', and 'maintainer feedback' so users phrasing the need differently still match.

DimensionReasoningScore

Specificity

Lists multiple concrete capability areas ("Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage") and concrete actions ("opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review"). Not a 5 because a few areas ("verification protocol", "docstring coverage") remain abstract noun phrases rather than concrete actions.

4 / 5

Completeness

Explicitly answers both what (the capability list) and when ("Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review") with concrete trigger phrases. A score of 4 would require the 'when' clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Good natural trigger phrases a contributor would actually say: "opening an issue", "drafting or editing a PR body", "chained/stacked PRs", "auditing a PR", "requesting review", "external collaborator". Not a 5 because common variants like the spelled-out "pull request", "fork", or "code review" are absent.

4 / 5

Distinctiveness Conflict Risk

The trigger is gated on a single named repository ("the active repo is Gentleman-Programming/gentle-ai") plus a specific role (external collaborator), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

18

/

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.