Name: gentle-ai-collab-perfect
Rating: 72 (1 reviews)
Author: Gentleman-Programming

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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 strong, actionable contribution workflow with executable commands, explicit validation checkpoints, and clean delegation of mechanics to referenced repo files. Its main weakness is moderate repetition of the 403 error and pre-existing-failure examples across sections.

Suggestions

Consolidate the GraphQL 403 `AddLabelsToLabelable` example and the pre-existing-failure package list so each appears once (e.g. in the verification protocol) and is referenced elsewhere, trimming conciseness waste.

Move the anti-patterns table and the detailed 'Standard honest-rewrite pattern' into a reference file (e.g. references/honest-rewrites.md) and link to it from SKILL.md to reduce the inline body length.

Add a couple of trigger-term synonyms in the description (e.g. 'reviewing a PR', 'PR comment') to round out trigger-term coverage.

Dimension	Reasoning	Score
Conciseness	Dense, high-signal, repo-specific content that assumes Claude's competence (no basic explanations of PRs or Conventional Commits); not a 5 because the GraphQL 403 example and the pre-existing-failure list are each repeated across multiple sections and could be trimmed.	4 / 5
Actionability	Fully executable guidance throughout: concrete `gh pr view --json ...` commands, git branch commands, the exact branch-name and title regexes, and a literal PR-body section template with emojis covering the common cases.	5 / 5
Workflow Clarity	The PR workflow is a clearly numbered 6-step sequence with an explicit 'Local validation' checkpoint, the verification protocol provides validate-then-retry feedback loops, and a pre-PR self-audit checklist closes the loop for this batch/permission-sensitive process.	5 / 5
Progressive Disclosure	Well-sectioned body with a dedicated References list and a 'Source of truth' table that points one level deep to external repo files (CONTRIBUTING.md, sibling SKILL.md files) instead of duplicating mechanics; not a 5 because at ~290 lines some inlined material (anti-patterns table, detailed honest-rewrite pattern) could live in a reference file, and no bundle files are provided to offload it.	4 / 5
	Total	18 / 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.

The description is excellent: it states both what the skill covers and an explicit 'Load whenever...' trigger clause tied to a specific repo and role. It is highly specific and distinctive, with only minor room to add trigger-term synonyms.

Dimension	Reasoning	Score
Specificity	Lists several specific capabilities ('Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage'), matching the 'several specific actions; minor gaps' anchor; not a 5 because the items are process areas rather than concrete atomic verbs.	4 / 5
Completeness	Clearly states what the skill does (the six capability areas) and explicitly when to load it via 'Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the contribution flow is in scope: ...' with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'opening an issue', 'drafting or editing a PR body', 'splitting a change into chained/stacked PRs', 'auditing a PR before requesting review' give good coverage; not a 5 because some synonyms/variants (e.g. 'code review', 'PR comment') are not enumerated.	4 / 5
Distinctiveness Conflict Risk	Scoped to a single named repo and the external-collaborator role, giving a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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/gentle-ai-collab-perfect/SKILL.md
Commit: a245f26

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.