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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 concrete commands, regexes, and validation checkpoints supporting clear end-to-end workflows. Its main weakness is redundancy — several repo-specific facts are restated across multiple sections — and a monolithic inline structure with no bundle files to offload detail.

Suggestions

Consolidate repeated facts: state the GraphQL 403 'AddLabelsToLabelable' error, the cross-fork base-ref limitation, and the pre-existing test-failure list once in their canonical section and reference them elsewhere rather than re-explaining in the scope table, verification protocol, and anti-patterns.

Move the anti-patterns table and/or the 'Standard honest-rewrite pattern' into a reference file under references/ to reduce inline length and improve progressive disclosure.

Trim the overlap between 'Hard rules' and the workflow sections, which restate the same Closes-vs-Refs, single-scope-title, and 400-line-budget constraints.

DimensionReasoningScore

Conciseness

Mostly efficient and avoids explaining general concepts Claude already knows, but repeats the same repo-specific facts multiple times — the GraphQL 403 'AddLabelsToLabelable' error, the cross-fork base-ref limitation, and the pre-existing test failures each appear in 3+ sections (hard rules, scope table, verification protocol, anti-patterns), which could be consolidated.

2 / 3

Actionability

Provides fully executable, copy-paste-ready guidance: concrete `gh pr view --json ...` commands, exact branch-name and PR-title regexes, specific file paths, and a literal PR body section template with emoji headers — no vague direction.

3 / 3

Workflow Clarity

Multi-step processes (Issue workflow, PR workflow, Verification protocol) are clearly sequenced with explicit validation checkpoints — API cross-checks, `git stash` baseline, `gh pr checks --json`, and round-trip body verification — plus a pre-PR self-audit checklist and feedback loops for error recovery.

3 / 3

Progressive Disclosure

Sections are well-organized and the 'Source of truth' and 'References' tables point one level deep to real repo files (CONTRIBUTING.md, skills/*/SKILL.md), but no bundle files exist and the ~290-line body is largely monolithic inline content (e.g. the anti-patterns table and standard honest-rewrite pattern) that could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, trigger-rich, and repo-gated, cleanly answering both what the skill does and when to load it. It uses third-person/imperative voice with no first- or second-person phrasing. It is a strong, low-conflict trigger description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage' — each naming a distinct capability rather than vague language.

3 / 3

Completeness

Explicitly answers both what (the enumerated workflow capabilities) and when ('Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope'), with an explicit 'Load whenever' trigger clause.

3 / 3

Trigger Term Quality

Natural trigger phrases a contributor would say appear explicitly: 'opening an issue, drafting or editing a PR body, splitting a change into chained/stacked PRs, or auditing a PR before requesting review', with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Tightly gated to a single repo ('the active repo is Gentleman-Programming/gentle-ai') and an external-collaborator role, giving it a clear niche unlikely to trigger for unrelated skills.

3 / 3

Total

12

/

12

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.