CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paddle-sandbox-testing

Test a Paddle integration end-to-end using the sandbox environment, test cards, the webhook simulator, and local tunnels — without taking real money.

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 paddle-sandbox-testing in PaddleHQ/paddle-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 exceptionally actionable, with executable code, exact values, and a validated end-to-end workflow that includes error-recovery loops. Its weaknesses are moderate redundancy between the two sandbox-vs-live tables and a complete absence of progressive disclosure — generic MCP/CLI usage guides and reference tables are inlined rather than split into referenced files.

Suggestions

Move the generic Paddle MCP and Paddle CLI usage blockquotes (and the simulator scenario table) into files under references/ and link to them, keeping SKILL.md as a lean overview.

Deduplicate the "Sandbox vs production at a glance" table against the later "differences that may catch you out" table — domain approval and refund timing appear in both with overlapping detail.

Split the long Step 1 paragraph about the default payment link into a short numbered sub-procedure with the MCP, CLI, and dashboard options as clearly separated alternatives.

DimensionReasoningScore

Conciseness

Almost every passage is non-inferable Paddle specifics (key prefixes, retry counts, test cards, scenario event sequences) rather than concepts Claude already knows, but the "at a glance" table duplicates domain-approval and refund-timing rows covered more fully in the later differences table, and Step 1 item 3 is an overlong paragraph that could be trimmed.

4 / 5

Actionability

Fully executable throughout: exact test card numbers, a copy-paste MCP execute function, complete CLI commands with JSON bodies, a runnable CI polling script, env-var examples, and concrete replay/debug calls covering the common cases.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced, and Step 5's end-to-end loop has explicit Confirm checkpoints (successUrl, server logs, DB rows, dashboard transaction) plus feedback loops for error recovery (checkout_url_domain_not_approved retry, verification-secret mismatch diagnosis, aborted-event causes).

5 / 5

Progressive Disclosure

Sections are well organized, but this 230-line skill has no reference files at all, and substantial content that belongs in separate files is inlined — the two large generic blockquotes on Paddle MCP and CLI usage conventions are family-wide boilerplate, and the simulator scenario table is reference material.

3 / 5

Total

17

/

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.

The description gives a concrete, distinctive picture of what the skill does and which tools it uses, with genuinely natural trigger terms. Its main weakness is the absence of any explicit "use when" guidance, which caps completeness and leaves triggering to inference.

Suggestions

Add an explicit trigger clause, e.g. "Use when verifying a Paddle integration before going live, testing checkout or webhook flows, or when the user mentions sandbox, test cards, or the webhook simulator."

Consider naming one or two more user-facing actions (e.g. "trigger webhook events", "exercise subscription state changes") to broaden action coverage beyond the single verb "Test".

DimensionReasoningScore

Specificity

Names the domain and four concrete mechanisms ("sandbox environment, test cards, the webhook simulator, and local tunnels") but rests on a single action verb ("Test"), leaving minor gaps in coverage rather than the multiple distinct actions of a 5.

4 / 5

Completeness

The "what" is clear and concrete (test a Paddle integration end-to-end without real money, using named tools), but there is no "Use when..." clause or equivalent trigger guidance, so "when" is only weakly implied — capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural terms users would say — "Paddle", "sandbox", "test cards", "webhook simulator", "local tunnels" — but misses common variations like "test payments", "webhook testing", or "go live", so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

"Paddle" combined with sandbox-specific triggers ("test cards", "webhook simulator", "local tunnels") carves out a clear niche with minimal conflict risk; these phrases would not naturally fire a different skill.

5 / 5

Total

16

/

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

PaddleHQ/paddle-agent-skills

Path

providers/cursor/plugin/skills/sandbox-testing/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.