json-render

AI chat response rendering guidance — handling UIMessage parts, tool call displays, streaming states, and structured data presentation. Use when building custom chat UIs, rendering tool results, or troubleshooting AI response display issues.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/vercel/skills/json-render/SKILL.md

Quality

Content

75%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 highly actionable with complete, executable code and a clear troubleshooting/decision structure. It loses points mainly on conciseness (some redundant migration restatement) and progressive disclosure (no separate reference files despite the length).

Suggestions

Tighten or consolidate the v5-vs-v6 migration restatements that appear in both 'Common Mistakes' and 'Client-Side Requirements' to remove redundancy.

Move the longer code reference blocks (full manual rendering pattern, ToolResultCard variants) into a one-level-deep reference file and link from the overview to improve progressive disclosure.

Add an explicit validation/checkpoint note in the server-side flow (e.g. verify validateUIMessages output before streaming) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code, but several sections restate basic v5-vs-v6 migration facts and re-explain the manual rendering logic that overlaps with the tool-result card section, adding padding that could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready TSX/TS examples covering the common cases — manual parts iteration, ToolResultCard rendering, server route, and client useChat — with specific API names and status values.	5 / 5
Workflow Clarity	The decision tree and 'Common Mistakes' cause/fix pairs give a clear sequenced path with error-recovery guidance, though there is no explicit validation checkpoint for the destructive/batch-adjacent server conversion step.	4 / 5
Progressive Disclosure	Content is well-sectioned with a clear overview, recommended vs manual paths, and a decision tree, but everything is inlined in one file with only an external skill pointer (ai-elements) rather than one-level-deep reference files.	4 / 5
	Total	16 / 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 strong: it states concrete capabilities and includes an explicit 'Use when' trigger covering multiple natural scenarios. It is concise and third-person, with only minor gaps in trigger synonym coverage and slight overlap risk with related skills.

Suggestions

Add a couple of natural user synonyms such as 'chat interface' or 'AI message display' to broaden trigger coverage.

Consider clarifying the boundary with the related ai-elements skill to reduce overlap risk.

Dimension	Reasoning	Score
Specificity	Names the domain (AI chat response rendering) and lists several concrete actions — 'handling UIMessage parts, tool call displays, streaming states, and structured data presentation' — with only minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what it does (rendering UIMessage parts, tool calls, streaming states) and when to use it via a clear 'Use when building custom chat UIs, rendering tool results, or troubleshooting...' clause with concrete triggers.	5 / 5
Trigger Term Quality	Natural user-facing phrases like 'building custom chat UIs, rendering tool results, or troubleshooting AI response display issues' are present, but it lacks synonyms/variants users might say (e.g. 'chat interface', 'AI messages').	4 / 5
Distinctiveness Conflict Risk	The niche (AI SDK v6 chat response rendering) is fairly distinct with clear triggers, though it could overlap with a sibling 'ai-elements' skill referenced in the body.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/json-render/SKILL.md
Commit: 1dc1958

Reviewed: 9 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.