CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

paddle-catalog-setup

Create the Paddle products and prices that other Paddle skills depend on — try MCP tools first, then the Paddle CLI, fall back to a Node SDK seed script, or dictate dashboard steps as a last resort.

Quality

81%

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

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.

A highly actionable, well-sequenced skill with excellent validation and fallback handling across four execution methods. Its weaknesses are modest duplication between the modeling sections and "Common pitfalls", and a monolithic single-file layout that inlines reference material a leaner SKILL.md would delegate to per-method reference files.

Suggestions

Move method-specific reference material (MCP tool conventions, the CLI reference paragraph, the tax-category table) into one-level-deep files like references/mcp.md, references/cli.md, and references/tax-categories.md, linked from each method section.

De-duplicate the currency-units and casing rules between "What you're modeling" / method sections and "Common pitfalls" — keep the pitfalls entry to a one-line pointer.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious Paddle specifics (zero-decimal currencies, MCP casing conventions, exit codes, trial validation errors) and assumes competence, but the currency-units rule and camelCase/snake_case convention are each restated in "Common pitfalls", and the CLI blockquote bundles tangential material — minor trims available.

4 / 5

Actionability

Every method ships copy-paste-ready material: a complete MCP `execute` payload, exact CLI commands with `--jq`, a full TypeScript seed template, per-variant snippets (one-time, paid trial, regional overrides), and specific error remediation paths.

5 / 5

Workflow Clarity

A ranked method-selection ladder, per-method numbered steps, explicit mid-failure fallback, and a dedicated Verify section (confirm entities exist, confirm reported IDs match, suggest next skill) provide clear sequencing with explicit validation and error-recovery feedback loops.

5 / 5

Progressive Disclosure

Section structure is clear, but the skill is a monolithic ~290-line file with no bundle: the MCP conventions blockquote, the CLI reference paragraph, and the tax-category table are path-specific reference material only one execution route needs, and would be better split into one-level-deep reference files.

3 / 5

Total

17

/

20

Passed

Description

71%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, action-dense description that clearly communicates what the skill does and its method preferences. Its main gaps are the absent explicit "Use when..." trigger clause and missing natural synonyms like "catalog" or "subscriptions", which cap completeness and trigger coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when starting a Paddle integration and the account has no products/prices yet, or when the user asks to set up their Paddle catalog."

Include natural synonyms users would say such as "catalog", "subscriptions", "billing", or "plans" alongside "products and prices".

Briefly signal when NOT to use it (catalog already exists) to sharpen distinctiveness against sibling Paddle skills that also involve prices.

DimensionReasoningScore

Specificity

"Create the Paddle products and prices" plus the full ladder "try MCP tools first, then the Paddle CLI, fall back to a Node SDK seed script, or dictate dashboard steps" lists multiple concrete, comprehensive actions with no coverage gaps in what the skill does.

5 / 5

Completeness

The "what" is clear (create products and prices via a four-method fallback ladder), but there is no "Use when..." clause or equivalent explicit trigger guidance — the "when" is only weakly implied by "that other Paddle skills depend on", which caps this dimension at 3.

3 / 5

Trigger Term Quality

Good natural keywords ("Paddle", "products", "prices", "MCP tools", "Paddle CLI", "dashboard") but misses common user variations like "catalog", "subscriptions", "billing", or "plans", so it falls short of comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

"Create the Paddle products and prices" carves a mostly distinct catalog-setup niche, but closely related Paddle skills also trade in "prices" and the description articulates no distinct triggers, leaving minor overlap risk rather than minimal.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

PaddleHQ/paddle-agent-skills

Path

skills/catalog-setup/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.