jq

Use when the user needs to query, filter, reshape, extract, create, or construct JSON data — including API responses, config files, log output, or any structured data — or when helping the user write or debug JSON transformations.

Quality

91%

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

90%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 jq quick-reference with executable examples and genuinely useful gojq-specific differences. The only soft spots are the lack of any workflow/validation structure (acceptable for a reference skill but keeps workflow_clarity just under the top) and a monolithic layout that could optionally split examples out.

Suggestions

Consider moving the nine 'Common Patterns' examples into a separate references/EXAMPLES.md and linking to it from the body, which would shorten the main file and sharpen progressive_disclosure.

Add a brief validation tip for risky transforms (e.g., pipe through `jq -e` or diff input vs. output) to give the skill an explicit checkpoint pattern for batch JSON rewrites.

Trim or fold the 'Tips' section into the relevant pattern examples to reduce slight overlap with the Common Patterns section.

Dimension	Reasoning	Score
Conciseness	Lean reference material that assumes Claude's competence — no padding about what JSON or jq is; every section (flags table, gojq differences, one-line patterns, tips) earns its place.	5 / 5
Actionability	All nine common-pattern examples are fully executable, copy-paste ready `echo '...' \| jq '...'` snippets covering the common cases, plus a concrete flags table and file-argument syntax.	5 / 5
Workflow Clarity	Well-organized for a single-task reference skill with an unambiguous action (run jq with a filter) and no destructive/batch operations, but it exceeds 50 lines and contains no explicit multi-step workflow or validation checkpoints, sitting just below the top anchor.	4 / 5
Progressive Disclosure	Clear section headers (Supported Flags, Differences, Common Patterns, Tips) make navigation easy and no external references are needed, but as a single inline file over 50 lines there is minor room to separate the reference tables from the pattern examples.	4 / 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 strong, well-structured description that pairs concrete capabilities with explicit 'Use when' triggers and a clear JSON-processing niche. It would benefit only from adding the '.json' extension and the 'parse' verb to round out natural trigger terms.

Dimension	Reasoning	Score
Specificity	Lists six concrete actions on JSON data — 'query, filter, reshape, extract, create, or construct' — giving comprehensive coverage of distinct operations rather than vague language.	5 / 5
Completeness	Explicitly answers both 'what' (query/filter/reshape/extract/create/construct JSON) and 'when' via a concrete 'Use when the user needs to...' clause with multiple trigger phrases, matching the top anchor's structure.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('JSON data', 'API responses', 'config files', 'log output', 'structured data', 'JSON transformations') but omits the '.json' file extension and the common verb 'parse' that users would naturally say.	4 / 5
Distinctiveness Conflict Risk	JSON processing is a clear, narrow niche with distinct triggers (API responses, config files, log output) and minimal overlap risk with other skills.	5 / 5
	Total	19 / 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: charmbracelet/crush
Path: internal/skills/builtin/jq/SKILL.md
Commit: 8f63ee5

Reviewed: about 6 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.