CtrlK
BlogDocsLog inGet started
Tessl Logo

poly-pizza-api

Use this skill whenever an LLM agent needs to search, browse, or download 3D models from Poly Pizza (poly.pizza) using their REST API. Triggers on any task involving: finding free low-poly 3D models, searching the Poly Pizza catalogue, fetching model metadata or download URLs, retrieving popular models, or downloading .glb files from Poly Pizza. Use this skill proactively whenever the agent needs to obtain 3D assets programmatically, even if the user just says "find me a 3D model of X" without mentioning Poly Pizza by name.

73

Quality

90%

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

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and token-efficient for an API reference, with executable examples and clear error-handling guidance. Its main weaknesses are the batch workflow lacking validation checkpoints and the absence of progressive disclosure — all reference material lives inline in one file.

Suggestions

Add explicit validation/retry checkpoints to the 'Batch fetch for a scene' workflow (e.g., check each search response status, handle empty results, retry on 429) so the batch path matches the per-model error handling.

Split the full endpoint reference, response shapes, and parameter tables into a separate REFERENCE.md and keep SKILL.md as an overview + quick-start, linking to it with clearly signaled one-level-deep references.

Consolidate the two overlapping download code blocks (the inline 'Downloading a model' snippet and the 'fetch_model' function) to reduce redundancy.

DimensionReasoningScore

Conciseness

The body is reference-dense API documentation with concrete endpoints, parameter tables, response shapes, and executable code, and avoids explaining concepts Claude already knows; not a 2 because there is no conceptual padding, every section is directly actionable.

3 / 3

Actionability

Provides fully executable Python snippets with exact base URLs, the X-Auth-Token header, query params, and copy-paste-ready functions, matching the anchor for fully executable, copy-paste-ready guidance.

3 / 3

Workflow Clarity

Common patterns are sequenced and the fetch_model function includes raise_for_status checks, but the 'Batch fetch for a scene' batch workflow lacks validation checkpoints, so per the batch-operation guideline workflow clarity is capped at 2 rather than 3.

2 / 3

Progressive Disclosure

The ~250-line skill is well-organized into clear sections but is a single monolithic file with the full endpoint reference and response shapes inline and no external reference files split out, matching the anchor where content that should be separate is inline.

2 / 3

Total

10

/

12

Passed

Description

100%

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 specific, trigger-rich, and complete, clearly stating both capabilities and when to invoke the skill with natural user-facing phrasings. The imperative 'Use this skill whenever an LLM agent needs…' form mirrors accepted good examples and is not penalized.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'search, browse, or download 3D models', 'fetching model metadata or download URLs', 'retrieving popular models', 'downloading .glb files' — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what (search/browse/download 3D models via the Poly Pizza REST API) and when ('Use this skill whenever…', 'Triggers on any task involving…', with an explicit trigger list).

3 / 3

Trigger Term Quality

Covers natural phrasings a user would say, including 'find me a 3D model of X', 'low-poly 3D models', '.glb files', and 'Poly Pizza', giving good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche (Poly Pizza 3D models) with distinct triggers; unlikely to fire for unrelated skills.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jasonkneen/tiny-world-builder
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.