CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

knowledge-update

Corrects outdated LLM knowledge about the Vercel platform and introduces new products. Injected at session start.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/knowledge-update/SKILL.md
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.

The body is a dense, well-organized knowledge-correction document that adds only facts Claude would not know and assumes its competence throughout, backed by an executable vercel.ts example, concrete commands, and explicit behavioral directives. Structure is clear and flat with well-signaled external links, though a few bullets could be tightened and no bundle files are used to offload the longer product entries.

DimensionReasoningScore

Conciseness

The body is a dense list of delta facts Claude does not know (new products, renamed services, changed limits) with no explanation of already-known concepts, and dates/versions are status markers within a corrections section rather than conditional time-based instructions. It is not a 5 because of minor trimmable asides like "a common LLM misconception" and the repeated "Use Fluid Compute" guidance across adjacent bullets.

4 / 5

Actionability

It includes a complete executable vercel.ts example, concrete commands ("npm i workflow@latest", "npx @next/codemod@canary agents-md", "VERCEL_SUPPORT_LARGE_FUNCTIONS=1"), exact doc paths (node_modules/next/dist/docs/, node_modules/eve/docs/README.md), and explicit behavioral directives ("load the `marketplace` skill... BEFORE you recommend a provider"). Not a 5 because several entries are purely declarative facts without executable guidance for the common cases.

4 / 5

Workflow Clarity

As a knowledge-correction skill it has no multi-step workflow, but its single governing action is unambiguous ("If your training data conflicts with this document, trust this document") and sequenced directives exist where behavior matters ("FIRST action is to load the `marketplace` skill... You may confirm scope with the user after loading the skill"). Not a 5 because the body mixes several conditional directives without a consolidated decision path.

4 / 5

Progressive Disclosure

The content is well organized into clearly labeled sections (outdated knowledge, new products, SDKs, Next.js, integrations) with external doc links and related-skill pointers clearly signaled, and a flat single-file structure that suits a session-injected knowledge file. Not a 5 because the body runs past 50 lines and some product entries (e.g. Custom Metrics, Schedules) are long enough that they could live in referenced detail files.

4 / 5

Total

16

/

20

Passed

Description

53%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 clearly states what the skill does (corrects outdated Vercel knowledge, introduces new products) and is domain-distinct thanks to the Vercel focus. However, it provides no explicit "use when" trigger guidance and few natural trigger keywords, so as a standalone description it would not help a model decide when to invoke it — the session-start injection metadata does that work instead.

Suggestions

Add an explicit trigger clause, e.g. "Use when working on Vercel deployments, Fluid Compute, edge/Node.js runtimes, or vercel.ts/vercel.json configuration, or when Vercel knowledge might be outdated."

Name the concrete knowledge areas corrected (runtimes, Fluid Compute, Node.js versions, WebSockets, vercel.ts) instead of the abstract "outdated LLM knowledge", which would raise both specificity and trigger-term coverage.

Include natural user-facing keywords and synonyms — Vercel, deploy, Next.js, Fluid Compute, edge runtime, vercel.json — so the description works even if the skill is ever matched by description rather than injected.

DimensionReasoningScore

Specificity

"Corrects outdated LLM knowledge about the Vercel platform and introduces new products" names the domain and two actions, but both stay abstract (no mention of which knowledge areas or which products), matching the anchor "Names domain and 1-2 concrete actions, but not comprehensive". It is not a 4 because it does not list several specific concrete actions, and not a 2 because the actions go beyond merely naming the domain.

3 / 5

Completeness

The "what" is clear (corrects outdated Vercel knowledge, introduces new products), but the "when" is absent — "Injected at session start" describes a loading mechanism, not when the skill applies, so the missing-'Use when' cap of 3 applies. It is not a 4 because there is no explicit trigger guidance at all, and not a 2 because the "what" is clear rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords like "Vercel platform", "LLM knowledge", and "new products" are present, but the natural phrases a user would actually say (deploy, Fluid Compute, Next.js, edge runtime, vercel.json) are missing — the same level as "Works with PDF files". Not a 2 because the domain keyword is present; not a 4 because no synonyms, variations, or file/extension triggers appear.

3 / 5

Distinctiveness Conflict Risk

The Vercel-knowledge-correction niche is mostly distinct with only minor overlap risk against other Vercel-specific skills. Not a 5 because the description contains no distinct trigger phrases that would reliably select it over closely related skills.

4 / 5

Total

13

/

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

vercel/vercel-plugin

Path

skills/knowledge-update/SKILL.md

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.