CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paddle-onboarding

Check a Paddle account's onboarding status in sandbox or live — audit settings, credentials, notification destinations, catalog, domains, and verification, report what's done and missing against the go-live checklist, then fix the gaps the API allows with the user's approval.

Quality

82%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

Exceptionally actionable and well-sequenced: complete executable audit and fix code across three access methods with thorough error handling and validation loops. The weaknesses are moderate repetition of guardrail and permission guidance across sections and inlining of general MCP/CLI tooling reference that could live in a shared file.

Suggestions

Consolidate the permission-handling guidance repeated in 'Before you start', Step 3, 'Permissions and forbidden', and 'Guardrails' into a single section and cross-reference it from the other spots.

Move the general Paddle MCP server and CLI usage blockquotes (camelCase method paths, pagination, exit codes, login flows) into a shared reference file such as references/paddle-tooling.md, keeping only onboarding-relevant details inline.

DimensionReasoningScore

Conciseness

The body is dense and Paddle-specific throughout, but permission and 'ask first' guidance repeats across 'Before you start', Step 3, 'Permissions and forbidden', and 'Guardrails', and the localhost/domain-approval pitfalls restate the Step 3 table — more than minor trimming would be needed.

3 / 5

Actionability

Fully executable across all three access methods: a complete MCP execute audit script, a copy-paste CLI command block with jq secret-stripping, a curl loop for direct API use, and a before/after fix example covering the common cases.

5 / 5

Workflow Clarity

Steps 1–4 are explicitly sequenced with validation checkpoints: each read is individually error-wrapped, each write is re-read and reported, verification statuses each get an interpretation, and forbidden errors have permission-then-dashboard fallback loops.

5 / 5

Progressive Disclosure

Well-organized single file with clear section headers, tables, and easy navigation, but the two general Paddle MCP and CLI tooling blockquotes (~40 lines not specific to onboarding) are inlined rather than split into a shared reference file.

4 / 5

Total

17

/

20

Passed

Description

75%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 specific, well-scoped description with concrete audit, report, and fix actions and a clearly protected niche. Its main weakness is the missing explicit "Use when…" trigger clause — when to invoke the skill is only implied — along with a few natural user phrasings users would say being absent.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks if their Paddle account is ready to go live, what's left to set up, or before switching an integration from sandbox to live."

Include the natural user phrasings that appear in the body — "ready to go live", "take live payments" — as trigger terms in the description.

DimensionReasoningScore

Specificity

"audit settings, credentials, notification destinations, catalog, domains, and verification, report what's done and missing … then fix the gaps the API allows" lists multiple concrete actions with comprehensive coverage of the audit domain.

5 / 5

Completeness

The 'what' is clear (audit, report, fix), but there is no "Use when…" clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by "go-live checklist", which caps completeness at 3.

3 / 5

Trigger Term Quality

Good natural keywords ("Paddle account", "onboarding", "sandbox or live", "go-live checklist") but a few natural phrases users would actually say — "ready to go live", "take live payments" — are missing.

4 / 5

Distinctiveness Conflict Risk

"Check a Paddle account's onboarding status in sandbox or live … against the go-live checklist" names a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

17

/

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/codex/plugin/skills/onboarding/SKILL.md

Revision

f2e0af8

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill