CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is chat-sdk in vercel/vercel-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

83%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 a tight, actionable overview that assumes Claude's intelligence and routes detail to published node_modules docs via well-signaled one-level references. It is slightly held back by deferring most concrete API surface and lacking explicit verification checkpoints.

Suggestions

Add one or two explicit verification checkpoints (e.g., confirm an adapter's dist/index.d.ts exists before wiring handlers, or check webhook verification) to lift workflow clarity toward a 5.

Inline a short snippet of the core Chat/Thread API signature so the most common calls don't require opening node_modules docs.

Convert the node_modules/docs/*.mdx references into a small bulleted 'reference map' with brief one-line descriptions of each doc to make navigation crisper.

DimensionReasoningScore

Conciseness

The body is lean: tight tables, minimal prose, and assumes Claude's competence — it never explains what a chat bot or adapter is, and every line (event-handler table, adapter inventory, streaming flags) earns its place.

5 / 5

Actionability

Provides copy-paste-ready Quick start and streaming TS/TSX examples plus exact package/factory tables, but defers most concrete API detail to node_modules docs rather than inlining it, leaving minor gaps.

4 / 5

Workflow Clarity

'Start with published sources' gives a clear read-before-code sequence and points to per-task docs before wiring handlers, but there are no explicit validation/verification checkpoints; for this non-destructive integration skill the sequence is clear with minor gaps.

4 / 5

Progressive Disclosure

SKILL.md is an overview that points to one-level-deep references (node_modules/chat/docs/*.mdx, contributing/, guides/), with no nested hops and clear section structure; it falls short of a 5 only because references are plain text paths rather than navigable links and no bundle files are present to confirm the structure.

4 / 5

Total

17

/

20

Passed

Description

88%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 specific, complete, and distinctive: it names the SDK, enumerates concrete capabilities, and gives an explicit 'Use when' trigger anchored on real platform names. Only minor synonym/extension coverage is missing from the trigger terms.

DimensionReasoningScore

Specificity

Lists many concrete capabilities — 'the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup' — covering the domain comprehensively, matching the 'multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

Explicitly answers both 'what' (Vercel Chat SDK expert guidance covering the listed subsystems) and 'when' ('Use when building multi-platform chat bots') with concrete trigger phrasing, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural platform terms (Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear) and the phrase 'chat bots', but lacks common synonyms like 'chatbot' as a single word or file/package extensions; good coverage with a few natural variations missing.

4 / 5

Distinctiveness Conflict Risk

A clear niche — multi-platform chat-bot SDK with named adapters — with distinct triggers (platform names plus 'single codebase') that make overlap with other skills unlikely.

5 / 5

Total

19

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.