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.

65

Quality

82%

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

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.

A well-structured, token-efficient reference skill: executable quick-start and streaming examples, concrete handler and adapter tables, and a clearly signaled map to the published docs. The main gaps are the thin webhook-setup section and reference tables inlined in the overview.

Suggestions

Add a minimal concrete webhook route example (e.g., an app/api/webhooks/slack/route.ts handler delegating to bot.webhooks.slack) so the webhook setup section matches the actionability of the rest of the body.

Trim the marketing tagline ("Write bot logic once, deploy everywhere") and the opening sentence that restates the description to tighten token efficiency.

Consider moving the full adapter inventory and community/coming-soon lists into a referenced doc (consistent with the node_modules docs pattern) and keeping only the official adapters table in the overview.

DimensionReasoningScore

Conciseness

The body is dense tables, lists, and code with no explanation of concepts Claude already knows, but "Write bot logic once, deploy everywhere" and the opening line restating the description are minor padding that keeps it off the lean 5 anchor.

4 / 5

Actionability

The quick start, streaming example, and JSX card example are executable TypeScript, and the handler/adapter tables give concrete package and factory names, but webhook setup only says "Wire those directly to your HTTP framework routes" without a concrete route example — a minor gap versus the copy-paste-complete 5 anchor.

4 / 5

Workflow Clarity

A clear directive sequence is present ("Read these before writing code" with a prioritized doc list, then quick start, then handler wiring), and it correctly defers to exact API docs; no validation checkpoints are needed since the skill involves no destructive or batch operations, so it sits between the implicit-checkpoint 3 and explicit-validation 5 anchors.

4 / 5

Progressive Disclosure

With no bundle files provided, the body acts as an overview that points one level deep to clearly signaled published docs (each node_modules/chat/docs/*.mdx path annotated with its topic), which is good structure; reference-style inventory tables are inlined that could be split out, leaving minor organization gaps versus the 5 anchor.

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.

A strong description that explicitly states both what it covers and when to use it, with concrete platform names as natural triggers. Its main weakness is listing capabilities as topics rather than actions, which slightly blunts specificity.

DimensionReasoningScore

Specificity

"Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup" lists several specific, concrete items covering the SDK surface, but they are topics ("covers X") rather than the concrete actions of the 5 anchor, and "expert guidance" is slightly fluffy.

4 / 5

Completeness

It explicitly answers both what ("Vercel Chat SDK expert guidance. Covers the Chat class, adapters, threads, messages, cards, modals, streaming, state management, and webhook setup") and when with concrete trigger phrases ("Use when building multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase"), matching the top anchor; the 4 anchor's caveat that 'when' could be more specific does not apply here.

5 / 5

Trigger Term Quality

"multi-platform chat bots — Slack, Telegram, Microsoft Teams, Discord, Google Chat, GitHub, Linear — with a single codebase" plus "webhook" gives good natural keyword coverage users would actually say, but common variations like "chatbot", "messaging bot", or package names are missing.

4 / 5

Distinctiveness Conflict Risk

The multi-platform bot niche with eight named platforms and a single-codebase framing is mostly distinct with specific triggers, but "chat" broadly overlaps with AI chat-UI / useChat-style skills, leaving minor conflict risk rather than the minimal risk of the 5 anchor.

4 / 5

Total

17

/

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.

Validation — 14 / 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.