Tessl • The management layer for AI agent skills

An excellent, highly actionable skill body: executable end-to-end examples, explicit verification steps, and dense Paddle-specific knowledge with almost no filler. The only weaknesses are mild redundancy (throttling, successUrl) and monolithic structure where reference files could reduce upfront token load.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and consistently Paddle-specific (frameTarget class rules, absolute successUrl requirement, event-shape discrimination, updateItems replace semantics), but throttling guidance is repeated in three places, the relative-successUrl pitfall appears twice, and the long MCP-conventions blockquote is generic Paddle-MCP material rather than checkout-specific — trimmable per anchor 4. It is not 3 because nearly all content adds non-obvious, domain-specific value Claude could not infer.	4 / 5
Actionability	Two complete, copy-paste-ready App Router client components (with imports and env handling), concrete install commands, working event-discrimination code, pre-fill and updateItems snippets, and a verification checklist with an actual sandbox test card number ("4242 4242 4242 4242") cover the common cases fully — anchor 5.	5 / 5
Workflow Clarity	The sequence runs prerequisites → choose style/variant → minimal overlay → full inline → advanced features → pitfalls → verify, with an explicit 5-step verification checklist with expected outcomes and a pitfalls section that maps errors to fixes (e.g. "'Paddle is not defined' — you forgot to await initializePaddle()"), providing the feedback loops anchor 5 requires.	5 / 5
Progressive Disclosure	No bundle files exist; the single body is well-sectioned with clear headers, clearly signaled sibling-skill pointers ("webhooks", "subscription-sync", "sandbox-testing", "catalog-setup"), and curated external doc links — matching anchor 4. It is not 5 because the full event table and the MCP-conventions note are inline content that could live in reference files so the core workflow loads leaner.	4 / 5
	Total	18 / 20 Passed

Description

70%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 specific, distinct description with concrete capability enumeration, but it lacks an explicit "Use when..." trigger clause, capping completeness and leaving trigger coverage narrower than the natural phrasing users might use. Adding one trigger sentence would raise it to top-tier quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when adding a Paddle (overlay or inline) checkout to a Next.js app, wiring up checkout events, pre-filling customer details, or updating line items dynamically."

Include a few natural payment-side synonyms users might say ("payment page", "buy button", "cart", "Paddle billing") to broaden trigger-term coverage.

Mention initialization and the post-checkout success-URL redirect in the capability list to close the coverage gaps in specificity.

Dimension	Reasoning	Score
Specificity	"overlay or inline, with event handling, customer pre-fill, and dynamic line item updates" lists four concrete capabilities plus the domain, matching anchor 4 (several specific actions, minor gaps). It is not 5 because initialization and the post-checkout redirect/success-URL handling are unstated.	4 / 5
Completeness	The "what" is clear and concrete ("Add a Paddle Checkout to a Next.js web app — overlay or inline, with event handling..."), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by the noun phrase, which caps this dimension at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Paddle Checkout", "Next.js web app", "overlay", "inline", "customer pre-fill", and "line item" are natural terms a user would say, matching anchor 4's good keyword coverage. It falls short of anchor 5 because payment/billing synonyms ("payment", "buy button", "cart", "billing") are missing.	4 / 5
Distinctiveness Conflict Risk	"Paddle Checkout" scoped to "a Next.js web app" carves out a clear niche with distinct triggers and minimal conflict risk with other checkout/payment skills (e.g. Stripe), matching anchor 5.	5 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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: PaddleHQ/paddle-agent-skills
Path: providers/codex/plugin/skills/checkout-web/SKILL.md
Revision: 70cb70d

Reviewed: 4 days ago

Discovery Implementation Validation

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.

paddle-checkout-web

Table of Contents

Is this your skill?