yaml

YAML wire format for json-render with streaming parser, prompt generation, and AI SDK transform. Use when working with @json-render/yaml, YAML-based spec streaming, yaml-spec/yaml-edit fences, or YAML prompt generation.

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

82%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 well-structured, highly actionable library skill whose body is dominated by executable TypeScript examples. Its main weaknesses are minor cross-section redundancy and a monolithic single-file structure that could split out a detailed API reference.

Suggestions

Consolidate the fence-type listings so 'yaml-spec/yaml-edit/yaml-patch/diff' appear once rather than in Key Concepts, AI SDK Transform, and Fence Constants.

Move the full Key Exports table and per-export detail into a references/ file (e.g. REFERENCE.md), leaving SKILL.md as a concise overview with a one-level-deep pointer.

Add a brief verify/validation note for the streaming parser flow (e.g. checking getPatches() results) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-driven with minimal over-explanation of known concepts, but fence types are repeated across 'Key Concepts', 'AI SDK Transform', and 'Fence Constants' and the Key Exports table restates earlier details; trimming the redundancy would reach 5.	4 / 5
Actionability	Fully executable, copy-paste-ready TypeScript examples cover the common cases (prompt generation, pipeYamlRender, multi-turn edits, streaming compiler, edit instructions, fence constants).	5 / 5
Workflow Clarity	Usage is sequenced clearly by ascending complexity and the streaming compiler shows a push-flush-reset flow; it is not a destructive or batch operation, so explicit validation checkpoints are not required, but the absence of any verify step keeps it just below 5.	4 / 5
Progressive Disclosure	No bundle files exist, so all content lives in SKILL.md; sections are well-organized with headers and a Key Exports index, but the file exceeds 50 lines and could offload the full export/API reference to a separate reference file.	4 / 5
	Total	17 / 20 Passed

Description

87%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, specific description that pairs a clear capability statement with an explicit trigger clause. Slightly technical in its trigger phrasing but unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('streaming parser, prompt generation, and AI SDK transform') alongside the named domain, with only minor coverage gaps; not a 5 because the actions are somewhat overlapping rather than comprehensively distinct.	4 / 5
Completeness	Clearly answers 'what' (YAML wire format with the three named capabilities) and explicitly provides a 'Use when...' clause with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Good keyword coverage including the package name ('@json-render/yaml'), fence names ('yaml-spec/yaml-edit'), and 'YAML-based spec streaming'; a few more natural synonyms would push it to 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (@json-render/yaml and its specific fence types) with distinct triggers and minimal risk of firing for unrelated skills.	5 / 5
	Total	18 / 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: vercel-labs/json-render
Path: skills/yaml/SKILL.md
Commit: 0f6798b

Reviewed: 2 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.