CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-payment-credential

Obtain Link purchase approval and complete checkout with server-side credential entry in the existing browser.

Quality

80%

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 ./apps/templates/bell-stack/agent/extensions/link/skills/create-payment-credential/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplar of dense, safety-conscious instruction writing: named tools, exact parameter specs, explicit stop conditions, and clear error-recovery routing with no wasted tokens. The only meaningful gap is the absence of one worked example showing the structure of a `link__checkout` call's mappings and submit target.

DimensionReasoningScore

Conciseness

The body is a lean, dense set of instructions with no padding and no explanation of concepts Claude already knows; every sentence carries actionable or safety-critical guidance (e.g., the field-mapping enumeration and the stop conditions). It fully assumes the model's competence, matching the top anchor.

5 / 5

Actionability

Guidance is highly concrete: named tools (`link__create_spend_request`, `link__retrieve_spend_request`, `link__checkout`, `link__create_report`), exact parameter names, formats (MM/YY, smallest currency unit, lowercase currency), and CSS selector/frame requirements. It falls just short of fully copy-paste-ready because no complete example invocation shows how the field mappings and submit target are actually structured, leaving a minor gap.

4 / 5

Workflow Clarity

The five numbered steps are clearly sequenced with explicit validation checkpoints ('Stop on denial, cancellation, or expiry', rechecking approval and merchant/amount/currency, checking Link payment status after submission) and explicit error-recovery routing (human handoff for 3DS, never automatically retrying an uncertain purchase). The destructive-operation cap does not apply because validation is thoroughly present.

5 / 5

Progressive Disclosure

The skill is under 50 lines, self-contained with no bundle files, and needs no external references; the numbered workflow plus closing reporting section is well organized. Per the rubric's simple-skill guidance this earns the top score on organization alone.

5 / 5

Total

19

/

20

Passed

Description

57%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 precise, appropriately concise, and highly distinctive, but it only answers 'what' and never 'when'. Adding an explicit trigger clause and a few natural synonyms would substantially improve trigger-term quality and completeness without sacrificing its lean phrasing.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when the operator enables Link sandbox mode and a purchase must be completed with server-side credential entry' — this would lift completeness and trigger-term quality together.

Include natural trigger phrases and synonyms users would actually say, such as 'pay with Link', 'Link checkout', 'approve a Link purchase', or 'sandbox purchase'.

Briefly enumerate one or two more concrete capabilities from the body (e.g., verifying request status, post-checkout payment status checks, or reporting outcomes) to broaden capability coverage.

DimensionReasoningScore

Specificity

The description names two concrete actions ("Obtain Link purchase approval" and "complete checkout with server-side credential entry") with precise qualifiers like "in the existing browser", but coverage stops at those two actions. This matches the anchor for 1-2 concrete actions that are not comprehensive rather than the 'several specific actions' of the level above.

3 / 5

Completeness

The 'what' is clear and specific (obtain Link approval, complete checkout with server-side credential entry), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3. It explicitly answers only half of what the dimension requires.

3 / 5

Trigger Term Quality

Relevant domain keywords are present ("Link", "purchase approval", "checkout", "credential entry", "browser") but there are no synonyms or natural variations such as "pay with Link", "payment", or "sandbox". This is 'some relevant keywords but missing common variations', not the good-with-few-gaps coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

"Link purchase approval" and "server-side credential entry in the existing browser" carve out a clear niche with distinctive trigger phrases that virtually no other skill would match. Conflict risk with generic checkout or browser skills is minimal, matching the highest anchor.

5 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

vercel/eve

Path

apps/templates/bell-stack/agent/extensions/link/skills/create-payment-credential/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.