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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./providers/claude/plugin/skills/sandbox-testing/SKILL.md

The canonical home for this skill is paddle-sandbox-testing in PaddleHQ/paddle-agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

An exceptionally actionable, well-sequenced guide whose Paddle-specific knowledge is genuinely non-obvious and earns its place. Its weaknesses are structural: a 26KB single file carrying reference tables and shared tooling guides that belong in separate reference files, plus a couple of sections that could be tightened.

Suggestions

Move the test-card table and the full simulator scenario-event table into a references/ file (e.g. TEST-CARDS.md, SIMULATIONS.md), keeping only the standard card and one example scenario inline.

Extract the long MCP and CLI tooling blockquotes into a shared reference file and inline only the sandbox-relevant excerpts, which would also remove the version pin ("v0.2.0 or later") from the main body.

Trim Step 1's default-payment-link paragraph and Step 5's cancellation confirmations to their essential commands and expected events to reduce token load.

DimensionReasoningScore

Conciseness

Mostly dense, non-obvious Paddle facts (test cards, retry limits, sandbox/live behavioral differences), but the two long MCP/CLI tooling blockquotes, the exhaustive scenario-event table listing every default event of every scenario, and a version pin ("v0.2.0 or later") outside any deprecation section are inlined material that could be tightened or moved out.

3 / 5

Actionability

Fully executable throughout: exact test card numbers, a concrete .env block, an MCP execute code sample, copy-paste paddle CLI commands with --jq filters, Hookdeck tunnel commands, and a complete CI verification script with an explicit failure exit.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with explicit confirmation checkpoints (successUrl, server logs, DB rows, dashboard transaction), error-recovery feedback loops (domain-not-approved → add domain → retry; signature mismatch → wrong secret), and a CI loop that fails the build on undelivered events.

5 / 5

Progressive Disclosure

Sections are well-organized with clear headers and easy navigation, but this ~230-line single file inlines reference material (test-card table, full scenario-event table, MCP/CLI tooling guides, CI script) that belongs in one-level-deep reference files — none of which exist.

3 / 5

Total

16

/

20

Passed

Description

66%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, tool-rich description that clearly conveys the domain and the safety framing ("without taking real money"), held back by the complete absence of explicit trigger guidance. Adding a "Use when..." clause naming the situations that call for this skill would lift it substantially.

Suggestions

Append an explicit trigger clause, e.g. "Use when verifying a Paddle integration before going live, testing webhooks without real money, or debugging sandbox-vs-live differences."

Name the concrete actions users seek — running test checkouts, firing simulated webhook events, and exercising subscription state changes (cancellation, dunning, past_due) — not just the instruments.

Add natural trigger variations users would actually say, such as "go live", "pre-launch checklist", or "test payments", to improve keyword coverage.

DimensionReasoningScore

Specificity

Names the domain and concrete instruments ("sandbox environment, test cards, the webhook simulator, and local tunnels"), but the action is a single verb ("Test a Paddle integration end-to-end") with those instruments as means, leaving minor gaps in coverage of what testing actually involves (checkouts, subscription state changes).

4 / 5

Completeness

The "what" is clear and concrete, but the description contains no "Use when..." clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes natural terms users would say when needing this skill — "Paddle", "sandbox", "test cards", "webhook simulator", "end-to-end" — but misses common variations such as "go live", "pre-launch", or "test payments".

4 / 5

Distinctiveness Conflict Risk

"Paddle integration" plus "sandbox" is a clear niche with minimal conflict risk, but webhook-simulator and general testing terminology creates minor overlap risk with closely related sibling skills (webhooks, subscription-sync).

4 / 5

Total

15

/

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/claude/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.