code-commenting

Guidelines for writing self-explanatory code with minimal comments. Covers when to comment (WHY not WHAT), anti-patterns to avoid, annotation tags, public API documentation. Use when writing or reviewing code comments, docstrings, TODO/FIXME tags, code readability, or inline comments.

Quality

88%

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

92%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 tight, well-structured instruction skill that assumes Claude's competence and gives concrete directives with no padding. Its only gap is the lack of an illustrative comment example to anchor the WHY-not-WHAT guidance.

Suggestions

Add one short good-vs-bad comment pair (e.g. a magic-number comment) to make the WHY-not-WHAT rule immediately actionable by example and lift actionability to 5.

Optionally show a one-line JSDoc skeleton to make the 'JSDoc every public API function' directive copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive — 'Comment WHY, not WHAT', a compact tag table, and a terse Never list — with no padding or explanation of concepts Claude already knows; every token earns its place, matching the 5 anchor.	5 / 5
Actionability	Concrete, specific directives ('JSDoc every public API function', 'Do comment: non-obvious algorithm choices, regexes...', defined tag semantics, a Never list) give mostly executable guidance; not a 5 because no illustrative good-vs-bad comment example demonstrates the WHY-not-WHAT transformation.	4 / 5
Workflow Clarity	This is a simple single-purpose instruction skill with an unambiguous action (apply the commenting rules, tags, and Never list), so the simple-skill exception applies; no destructive or batch operation exists that would require validation checkpoints.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references (no bundle files present) and is organized into clear sections (Code Commenting, Annotation Tags, Never), meeting the simple-skill exception for a 5.	5 / 5
	Total	19 / 20 Passed

Description

83%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 concise, third-person, and explicitly covers both what the skill does and when to use it with concrete trigger phrases. It is strong on completeness and trigger quality, with only minor gaps in coverage breadth and distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete coverage areas — 'when to comment (WHY not WHAT), anti-patterns to avoid, annotation tags, public API documentation' — matching the 'several specific actions; minor gaps' anchor; not a 5 because these are topical categories rather than a fully comprehensive action list.	4 / 5
Completeness	Clearly states the 'what' ('Guidelines for writing self-explanatory code with minimal comments. Covers...') and an explicit 'Use when writing or reviewing code comments, docstrings, TODO/FIXME tags...' clause with concrete triggers, matching the 5 anchor; it is not below because both what and when are explicit.	5 / 5
Trigger Term Quality	Natural terms a user would say are present — 'code comments, docstrings, TODO/FIXME tags, code readability, inline comments' — giving good keyword coverage; not a 5 because some synonyms/variants (e.g. 'code review', 'commenting code') are absent.	4 / 5
Distinctiveness Conflict Risk	Code commenting is a clear niche with distinct triggers (docstrings, TODO/FIXME, inline comments), so mostly distinct with minimal conflict; not a 5 due to minor overlap risk with general code-review and readability skills.	4 / 5
	Total	17 / 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: monkilabs/opencastle
Path: src/orchestrator/skills/code-commenting/SKILL.md
Commit: fa0c341

Reviewed: 5 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.