paddle-catalog-setup
Create the Paddle products and prices that other Paddle skills depend on — try MCP tools first, fall back to a Node SDK seed script, or dictate dashboard steps as a last resort.
62
72%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/catalog-setup/SKILL.mdQuality
Discovery
67%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 strong on specificity and distinctiveness, clearly articulating a concrete multi-step fallback strategy for creating Paddle products and prices. Its main weaknesses are the lack of an explicit 'Use when...' clause and somewhat technical trigger terms that may not match how users naturally phrase requests. Adding explicit trigger guidance would elevate this from a good to excellent description.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when setting up Paddle for the first time, initializing a product catalog, or when other Paddle skills report missing products or prices.'
Include more natural user-facing trigger terms like 'set up Paddle', 'initialize catalog', 'create billing products', or 'bootstrap Paddle environment'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: creating Paddle products and prices, trying MCP tools first, falling back to a Node SDK seed script, and dictating dashboard steps as a last resort. These are specific, actionable steps. | 3 / 3 |
Completeness | Clearly answers 'what' (create Paddle products and prices with a prioritized fallback strategy), but lacks an explicit 'Use when...' clause. The phrase 'that other Paddle skills depend on' implies when but doesn't explicitly state trigger conditions. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'Paddle products', 'prices', 'MCP tools', 'Node SDK', 'seed script', and 'dashboard', but misses common user-facing variations like 'set up Paddle', 'initialize products', 'catalog setup', or 'billing setup'. The terms are somewhat technical rather than what users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it specifically targets creating Paddle products/prices as a prerequisite for other Paddle skills, with a clear prioritized approach (MCP → SDK → dashboard). The dependency relationship and specific tooling chain make it unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent workflow clarity, clear method prioritization with fallback paths, and fully executable code examples for all three approaches. Its main weakness is verbosity — it repeats key constraints (amount units, casing conventions, trial period rules) across the modeling section, method examples, and common pitfalls, and explains some concepts Claude already understands. The content would benefit from being split across supporting files given its length.
Suggestions
Reduce redundancy by removing repeated explanations of amount units, casing conventions, and trial period constraints from the common pitfalls section — these are already clearly stated in the method sections.
Trim the 'What you're modeling' section to remove explanations of basic concepts (what a product vs price is) and focus only on Paddle-specific gotchas like zero-decimal currencies and environment separation.
Consider extracting the tax category table and common pitfalls into a separate reference file to reduce the main skill's token footprint.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is thorough and well-structured, but it's verbose in places — the 'What you're modeling' section explains product/price relationships Claude already knows, the tax category table could be more compact, and several pitfalls repeat information already stated in the methods (e.g., amount units, trial period constraints, camelCase vs snake_case). The common pitfalls section alone is quite long with significant redundancy. | 2 / 3 |
Actionability | Excellent actionability across all three methods. The MCP execute payloads are copy-paste ready with correct parameter shapes, the Node SDK seed script is fully executable TypeScript with proper imports and error handling, and the dashboard steps are click-by-click specific. Variants for one-time prices and regional overrides are also provided as executable snippets. | 3 / 3 |
Workflow Clarity | The skill has a clear prioritized method selection (MCP → SDK → Dashboard), explicit fallback triggers (e.g., 'if forbidden, fall back to next method'), and a dedicated Verify section with specific validation steps and a suggested next step. The feedback loop for error recovery is well-defined throughout. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a logical flow, and it links to external Paddle docs for deeper reference. However, for a skill this long (~250+ lines), some content like the full common pitfalls list, the tax category table, or the regional pricing examples could be split into separate reference files. As a standalone SKILL.md with no bundle files, it's a monolithic document that could benefit from better content splitting. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- PaddleHQ/paddle-agent-skills
- Commit
62438cd
- 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.