CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

jupiter-vrfd

Use when a user mentions Jupiter token verification, VRFD eligibility, paying 1000 JUP to verify a token, submitting a verification request, or updating metadata via the Jupiter express verification flow.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./vendored/jupiter/jupiter-vrfd/SKILL.md

The canonical home for this skill is jupiter-vrfd in jup-ag/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 tight, actionable skill body with excellent token efficiency, concrete endpoints, and a real pre-payment validation gate. Its main defects are a dangling reference to the nonexistent examples/verify.md (the entire execute workflow depends on it) and no inline request-body shape or error-recovery guidance for the POST execute step.

Suggestions

Fix the dangling reference: either create ./examples/verify.md with the execute-request walkthrough (request body shape, signing, error responses) or remove/redirect the link to ./references/api-reference.md, which already exists.

Add a minimal inline example of the POST /tokens/v2/verify/express/execute request body (even 3-4 lines) so the core action is executable without loading the reference.

State the flow order explicitly (1. check eligibility, 2. craft, 3. sign & execute) and add one line on handling a failed execute response (e.g., surface the API error, do not retry payment without user confirmation).

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no explanation of what Solana, API keys, or verification are; every section (router table, decision matrix, rules, resources) carries operational weight. The "Execution Notes" section borders on obvious but is brief and situational, not enough to drop from the score-5 anchor "every token earns its place".

5 / 5

Actionability

Concrete, near-executable guidance: exact endpoint paths with query parameters and HTTP methods ("/tokens/v2/verify/express/check-eligibility?tokenId={TOKEN_ID}") plus an explicit eligibility decision matrix mapping response flags to actions. Not 5 because the POST execute step has no inline request-body shape and the actual request/response construction is deferred to the reference file — minor gaps per the score-4 anchor.

4 / 5

Workflow Clarity

A clear implicit sequence (check-eligibility → craft-txn → sign and execute) with an explicit validation gate: the decision matrix says "**STOP** — show verificationError / metadataError to user" before any payment, and the rule "Do not claim a request was submitted unless you have a real API response" adds a post-execution checkpoint. Not 5 because there is no error-recovery guidance for a failed execute call and the step order is implied by table position rather than stated as an ordered flow.

4 / 5

Progressive Disclosure

Structure is good in intent — on-demand loading instructions, a clearly signaled one-level reference (./references/api-reference.md, which exists and is well-organized) — but the second referenced path "./examples/verify.md" does not exist in the bundle, leaving the execution phase with no supporting content. A dangling reference is a functional navigation failure beyond the score-4 anchor's "minor organization gaps", so it sits between anchors 3 and 4, and closer to 3 given half the loadable material is missing.

3 / 5

Total

16

/

20

Passed

Description

61%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 highly distinctive, well-targeted trigger description with natural keyword coverage, but it omits any statement of what the skill actually does. Adding a leading capability clause (e.g., "Routes agents through Jupiter's public express token-verification flow...") before the "Use when" clause would resolve the completeness gap.

Suggestions

Prefix the description with a concrete 'what' clause in third person, e.g. "Submits Solana tokens through Jupiter's public express verification flow, including eligibility checks, the 1000 JUP payment transaction, and optional metadata updates.", before the existing "Use when..." trigger list.

Add one or two missing natural trigger variations such as "check eligibility" or "get a token verified / verified badge" to broaden keyword coverage.

Keep the description under its current length when adding the 'what' clause — trim the enumerated trigger list if needed rather than padding.

DimensionReasoningScore

Specificity

Names several concrete domain actions — "Jupiter token verification, VRFD eligibility, paying 1000 JUP to verify a token, submitting a verification request, or updating metadata" — which is comparable to the score-4 anchor's "lists several specific actions; minor gaps in coverage". It falls short of 5 because the actions are framed as things a user might mention rather than what the skill itself does, and no implementation capability (routing through the express flow) is stated as a verb.

4 / 5

Completeness

The description is entirely a "Use when..." trigger clause — only 'when' is present with no statement of what the skill does — which matches the score-2 anchor ("only 'when' is present without 'what'") exactly. It is not 3 because that anchor requires a clear 'what', which is absent; the rich trigger list does not substitute for a capability statement.

2 / 5

Trigger Term Quality

Good coverage of natural phrases users would actually say ("token verification", "paying 1000 JUP", "submitting a verification request", "updating metadata") including the VRFD synonym. Not 5 because common variations such as "check eligibility", "verify my token", or "get the verified badge" are absent; not 3 because the terms present are natural user language, not just technical jargon.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Jupiter/Solana token verification) with highly specific triggers ("VRFD eligibility", "1000 JUP", "Jupiter express verification flow") that no other skill would plausibly fire on, matching the score-5 anchor of "clear niche with distinct triggers; minimal conflict risk".

5 / 5

Total

15

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

internet-court/internet-court-skill

Path

vendored/jupiter/jupiter-vrfd/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.