chat-sdk

Vercel Chat SDK expert guidance. Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup.

Quality

82%

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

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-organized API reference with strong executable examples, but it is a monolithic single-file document with some verbosity and inline time-sensitive markers rather than progressively disclosed bundle files.

Suggestions

Move the full Public API Reference and per-platform adapter sections into reference files (e.g., references/api.md, references/adapters.md) and keep SKILL.md a concise overview with one-level-deep links.

Remove duplicated content (the reaction example prose + code block, the duplicate #11 gotcha) and drop the borderline off-topic 'Companion Web UI and Card Design' section.

Relocate time-sensitive markers like 'new — Mar 6, 2026' into a dedicated changelog/old-patterns section so they don't clutter the main guidance.

Dimension	Reasoning	Score
Conciseness	Mostly high-signal API reference and code, but contains duplication (the reaction example appears as prose and again as a code block), an off-topic "Companion Web UI and Card Design" section, duplicate gotcha numbering (two #11), and inline time-sensitive markers ("new — Mar 6, 2026") not isolated in a deprecated/old-patterns section, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready TypeScript/TSX for Chat config, all platform adapters, cards, modals, webhook routes, and integration patterns with concrete env vars and options.	3 / 3
Workflow Clarity	A clear Quick Start and well-organized numbered Gotchas give sequence, but this is reference-style documentation with no validation checkpoints or error-recovery feedback loops for the webhook-deploy and adapter-setup flows.	2 / 3
Progressive Disclosure	No bundle files exist and the entire ~570-line API reference, per-platform adapter details, and gotchas are inline in SKILL.md; sections are well-headed but content that should be split into reference files is monolithically inlined.	2 / 3
	Total	9 / 12 Passed

Description

100%

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, concise description that names concrete capabilities, enumerates platforms, and provides an explicit 'Use when' trigger. Voice is appropriately third-person/imperative with no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability areas — "the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup" — alongside enumerated target platforms, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states what it covers ("Vercel Chat SDK expert guidance. Covers...") and when to use it ("Use when building multi-platform chat bots"), satisfying both what and when with an explicit trigger clause.	3 / 3
Trigger Term Quality	"multi-platform chat bots" plus "Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear" are natural terms a user would say when needing this skill; coverage is broad.	3 / 3
Distinctiveness Conflict Risk	The Vercel Chat SDK niche with single-codebase multi-platform bot adapters and named platforms is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 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
skill_md_line_count	SKILL.md is long (666 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/chat-sdk/SKILL.md
Commit: 11c74d6

Reviewed: about 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.