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

83%

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

78%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 an efficient, well-organized library reference with near-executable code examples and sensible high-level-to-low-level ordering. Its weaknesses are minor: duplicated fence-constant listings, a few undefined contextual variables in examples, and reference-style rather than workflow-style guidance.

Suggestions

Remove the duplicated fence-constant entries: either drop the four fence rows from the 'Key Exports' table or replace the 'Fence Constants' code block with a pointer to the table, keeping one canonical listing.

Make examples self-contained: show the import for 'yamlStringify' and note where 'result' and 'currentSpec' come from (e.g., a one-line comment) so snippets are copy-paste runnable.

Add a one-line decision guide near the top (e.g., 'Use pipeYamlRender for AI SDK streams; use createYamlStreamCompiler for custom sources') to sequence the three integration approaches explicitly.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — no basic YAML/library explanations — but the four fence constants appear twice (the 'Fence Constants' code block and again in the 'Key Exports' table), a trimmable redundancy. Fits 'efficient; minor instances of over-explanation that could be trimmed' rather than 'every token earns its place'.	4 / 5
Actionability	Concrete TypeScript examples with imports, an options list, and a method list for the streaming compiler — mostly copy-paste ready. Minor gaps keep it below 5: 'result', 'currentSpec', and 'yamlStringify' are used without definition or import, so examples are not fully self-contained.	4 / 5
Workflow Clarity	A reference-style skill organized high-level to low-level with useful when-to-use cues ("drop-in replacement for pipeJsonRender", "For multi-turn edits, pass the previous spec", and the push/flush/reset lifecycle comments). No destructive or batch operations requiring validation checkpoints, but the content is presented as reference sections rather than a sequenced workflow with explicit checkpoints, matching anchor 4.	4 / 5
Progressive Disclosure	The skill is a single self-contained file (no references/, scripts/, or assets/ bundle directories exist) with ten clean section headers and its own navigation via the 'Key Exports' table. Content is appropriately placed, easy to navigate, with nothing that needs splitting at this size — matching the well-organized single-file structure of the top anchor.	5 / 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.

The description is strong: it states concrete capabilities in neutral voice and pairs them with an explicit 'Use when' clause containing natural, library-specific trigger terms. Its only weakness is moderate specificity phrasing (noun phrases rather than action verbs) and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ("YAML wire format for json-render") and three concrete capabilities ("streaming parser, prompt generation, and AI SDK transform"), matching the 'several specific actions; minor gaps' anchor. Not 5 because capabilities are phrased as noun phrases and omit edit modes and the streaming compiler; not 3 because coverage clearly exceeds 1-2 actions.	4 / 5
Completeness	Explicitly answers both what ("YAML wire format... with streaming parser, prompt generation, and AI SDK transform") and when ("Use when working with...") with concrete trigger phrases, matching the anchor-5 example structure. Not 4 because the when-clause is fully explicit rather than only implied.	5 / 5
Trigger Term Quality	The trigger clause lists natural phrases a user of this library would say: "@json-render/yaml, YAML-based spec streaming, yaml-spec/yaml-edit fences, or YAML prompt generation". Good coverage with synonyms, but a few natural variations (e.g., 'render YAML specs', 'YAML streaming') are missing, so it fits anchor 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	A clearly-scoped niche anchored on the unique package name "@json-render/yaml" and distinctive fence names ("yaml-spec/yaml-edit fences"), giving minimal overlap risk with generic YAML skills. Clear niche with distinct triggers matches anchor 5.	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: c2600d7

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.