remove-llm-comments

Remove and tighten unnecessary LLM-generated comments — including narration disguised as "why", restated constraints, and why-comments a named symbol or the code structure already conveys. Use while editing, and as the final narration-comment pass before opening an MR or pushing, to strip the LLM narration the model left behind.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable worked-example playbook with excellent organization and concrete before/after code. The one gap is workflow clarity: a batch comment-deletion pass has no verification step to confirm removed comments were not load-bearing before pushing.

Suggestions

Add an explicit verification checkpoint to the workflow, e.g. after cleanup run the test suite or re-read the diff to confirm no deleted comment was load-bearing, before opening the MR.

Turn the final Quick checklist into a gated sequence that ends with 'verify tests/diff pass before pushing' so the destructive batch edit has a feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean and example-driven: every section is a worked before/after Rust snippet or a direct rule, with no padding explaining concepts Claude already knows (it assumes Rust competence). Not a level-2 'could be tightened' case because the prose is purposeful rationale tied to each example.	3 / 3
Actionability	Fully concrete guidance: a discriminator rule, explicit per-case actions ('delete', 'tighten', 'say it once'), real before/after code, and a 5-item Quick checklist — copy-paste-ready instruction rather than vague direction.	3 / 3
Workflow Clarity	A sequenced Quick checklist and the 'sequential passes, not independent rules' framing give an explicit order, but there is no validation/verification checkpoint for what is a batch edit that deletes content. The rubric caps workflow_clarity at 2 when destructive/batch operations lack a feedback loop, so it is not a 3.	2 / 3
Progressive Disclosure	No bundle files exist, so this is scored on organization: the body is split into clearly headed, well-signaled sections (When to run, discriminator, easy cases, tighten, de-duplicate, true-why, Rust traps, scope, checklist) with easy navigation and no nested references.	3 / 3
	Total	11 / 12 Passed

Description

85%

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, specific description with an explicit what-and-when structure and a distinct niche. Its only weakness is trigger-term quality: it relies on author-coined jargon ('narration-comment') rather than the phrasings a user would naturally say.

Suggestions

Add natural-user phrasings such as 'clean up comments', 'remove AI/LLM comments', or 'strip unnecessary comments' alongside the coined 'narration' terminology so the description matches what users actually say.

Soften or gloss the jargon 'narration-comment pass' (e.g. 'a final comment-cleanup pass') to keep the trigger terms recognizable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Remove and tighten unnecessary LLM-generated comments') and enumerates specific subtypes (narration disguised as 'why', restated constraints, why-comments a named symbol conveys), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers what ('Remove and tighten unnecessary LLM-generated comments...') and when ('Use while editing, and as the final narration-comment pass before opening an MR or pushing'), with an explicit 'Use...' trigger clause.	3 / 3
Trigger Term Quality	It includes relevant terms a user might say ('LLM-generated comments', 'MR', 'pushing', 'editing') but leans on coined jargon ('narration-comment pass', 'why-comments a named symbol... already conveys') that users would not naturally say, and misses common variations like 'clean up comments' or 'AI comments'.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (LLM-narration comment cleanup as an MR/push backstop) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Commit: 78fa8a1

Reviewed: about 10 hours 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.