writing-hashql-diagnostics

HashQL diagnostic writing patterns using hashql-diagnostics crate. Use when creating error messages, warnings, Labels, Messages, Severity levels, Patches, Suggestions, or improving diagnostic quality in HashQL code.

Quality

85%

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 content is lean, well-structured, and action-oriented, with executable Rust examples and clean progressive disclosure to a single real reference file. Its only shortfall is that a couple of representative examples (category definitions, span selection) live only in the reference rather than inline.

Suggestions

Inline one minimal category-definition snippet and one span-selection snippet in the Quick Reference so the core workflow is fully executable without opening the reference.

Consider adding a one-line 'verify' note pointing to the compiletest/testing-skill reference so the diagnostic-writing workflow has an explicit validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — DO/DON'T principles, a severity table, and tight Rust snippets — with no padding or explanation of concepts Claude already knows; only minor, near-trivial overlap between the Core Principles and Message Style sections.	5 / 5
Actionability	Provides several copy-paste-ready Rust examples covering the common cases (creating a diagnostic, adding suggestions), but a full category-definition example and a complete span-selection example are only in the referenced file rather than inline.	4 / 5
Workflow Clarity	This is a single-purpose reference/style skill (no destructive or batch operation), so the simple-skill exception applies: the single action of writing a diagnostic is unambiguous and well-structured, and no validation cap is triggered.	5 / 5
Progressive Disclosure	SKILL.md is a clear overview with a well-signaled, one-level-deep reference to a real references/guidelines.md file plus an external skill link; detail is appropriately split out and navigation is easy.	5 / 5
	Total	19 / 20 Passed

Description

78%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 clearly answers both what the skill does and when to use it, with concrete capability enumeration and a distinct niche. Its only weakness is that trigger/capability coverage is strong but not exhaustive enough to max out every dimension.

Suggestions

Add a couple of natural user phrases (e.g. 'compiler errors', 'fix diagnostics', 'did you mean') to broaden trigger_term_quality toward a 5.

Mention categories and span selection explicitly in the capability list to round out specificity and completeness.

Dimension	Reasoning	Score
Specificity	Names the domain (HashQL diagnostics via the hashql-diagnostics crate) and lists several concrete actions — 'creating error messages, warnings, Labels, Messages, Severity levels, Patches, Suggestions, or improving diagnostic quality' — with minor coverage gaps (categories/spans only implied).	4 / 5
Completeness	Explicitly states both the 'what' (diagnostic writing patterns using the crate) and the 'when' via a clear 'Use when creating... or improving diagnostic quality' clause; the 'when' could be slightly more specific but is concrete.	4 / 5
Trigger Term Quality	Includes natural developer-facing terms like 'error messages', 'warnings', 'Labels', 'Messages', 'Severity', 'Patches', and 'Suggestions', giving good keyword coverage, though a few natural synonyms (e.g. 'compiler error', bare 'diagnostic') are missing.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche — HashQL diagnostics through a specific crate — with distinct triggers and minimal realistic overlap with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: hashintel/hash
Path: .claude/skills/writing-hashql-diagnostics/SKILL.md
Commit: 0144f9c

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.