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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%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 tight, highly actionable playbook with excellent before/after examples and a clear discriminator. The one gap is the absence of an explicit validation/feedback checkpoint for what is a destructive editing pass.

Suggestions

Add an explicit validation step after the cleanup pass — e.g., re-read the diff to confirm only comments in scope were touched and no real why-information was lost — with a fix-and-retry loop, to lift workflow_clarity above the destructive-operation cap of 3.

Make the 'only touch comments this change introduced or modified' scope-discipline rule part of an explicit ordered checklist step with a verify action, rather than a standalone prose section.

Consider a short 'abort/escalate' trigger for when a comment's why is ambiguous (uncertain whether a named symbol carries it), so Claude has a concrete fallback instead of judgment-only guidance.

Dimension	Reasoning	Score
Conciseness	Lean and efficient; assumes Claude's competence with no padding about what comments or MRs are; every section and example earns its place.	5 / 5
Actionability	Provides concrete before/after Rust code pairs, a clear discriminator rule, and a copy-ready quick checklist covering the common cases.	5 / 5
Workflow Clarity	Sequenced passes and a checklist are present, but this destructive/batch editing skill has no explicit validation or feedback checkpoint (validate->fix->retry), which caps the score at 3 per the rubric.	3 / 5
Progressive Disclosure	Single self-contained file with well-organized, clearly headed sections and no nested references; no bundle files are needed and navigation is trivial.	5 / 5
	Total	18 / 20 Passed

Description

92%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 sharp, well-scoped description that answers what and when concretely with concrete actions and natural triggers. Only minor synonym coverage is missing.

Dimension	Reasoning	Score
Specificity	Names the domain (LLM-generated comments) and multiple concrete actions — remove, tighten, de-duplicate, strip narration — covering the space comprehensively.	5 / 5
Completeness	Explicitly states both 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').	5 / 5
Trigger Term Quality	Includes natural terms users would say ('LLM-generated comments', 'narration', 'before opening an MR or pushing') but misses common synonyms like 'clean up comments' or 'noisy comments'.	4 / 5
Distinctiveness Conflict Risk	Clear niche (LLM narration-comment cleanup) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	19 / 20 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
Path: .claude/skills/remove-llm-comments/SKILL.md
Commit: a2b60b1

Reviewed: 4 days 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.