i4h-catheter-navigation-render-drr

Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

90%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 tight, executable skill body with concrete bash workflows and validation checkpoints, well-organized into clear sections. The main improvement space is strengthening the verify step into an explicit render-failure feedback loop.

Suggestions

Turn the Verify step into a feedback loop: if `test -f ${OUTPUT}` fails or `file` reports an unexpected type, surface the render log tail and re-run with `--local` removed (Docker) per the troubleshooting guidance.

Add an explicit checkpoint after Step 2 confirming the log contains no slangpy/CUDA errors before declaring success, so validation is not just file existence.

Consider moving the Troubleshooting/Limitations detail into a short reference file linked from the body to deepen the progressive-disclosure structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: short Purpose, executable bash blocks, and tight bullet sections with no concept exposition or padding, so every token earns its place.	5 / 5
Actionability	Step 1 and Step 2 provide fully executable, copy-paste-ready bash including a real `i4h run` invocation and two concrete variants (synthetic phantom, cache), plus an executable Verify block covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (resolve run dir → render → verify) with a cache-existence guard and a verify checkpoint, plus a troubleshooting section for recovery; the inline verify is light with no explicit render-failure retry loop, leaving a minor gap versus the top anchor.	4 / 5
Progressive Disclosure	Content is well-organized into clear sections with appropriately placed inline material for a skill this size and clearly signaled sibling-skill links; with no bundle files to split out it is well-structured but not the maximal one-level-deep reference pattern of a 5.	4 / 5
	Total	18 / 20 Passed

Description

87%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 concise, third-person description that clearly states both the capability and concrete trigger conditions with domain-specific keywords. It is distinctive and actionable, with only minor room to add synonyms or extensions for trigger terms.

Dimension	Reasoning	Score
Specificity	Names the concrete action ("Render a single DRR fluoroscopy frame") with specific inputs ("CT cache or synthetic phantom") and trigger actions (render DRR, generate a fluoro image, smoke-test), giving several specific actions rather than the comprehensive multi-action set of a 5.	4 / 5
Completeness	It explicitly states what ("Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom") and when ("Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang renderer") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"render DRR", "generate a fluoro image", and "smoke-test the Slang renderer" are natural phrases a user in this domain would say, with good coverage; a few common synonyms or file extensions are missing, so not a 5.	4 / 5
Distinctiveness Conflict Risk	The DRR/fluoroscopy/Slang-renderer niche with CT-cache-specific triggers is highly specific and unlikely to conflict with other skills, fitting the clear-niche anchor.	5 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NVIDIA/skills
Path: skills/i4h-catheter-navigation-render-drr/SKILL.md
Commit: 994b870

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.