d-molecule-ray-tracer
Generate photorealistic rendering scripts for PyMOL and UCSF ChimeraX.
32
27%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data Analysis/3d-molecule-ray-tracer/SKILL.mdQuality
Discovery
40%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 identifies a clear and distinctive niche (photorealistic rendering for PyMOL and ChimeraX) but is incomplete due to the absence of a 'Use when...' clause. It would benefit from additional trigger terms covering common user language around molecular visualization and structural biology, as well as explicit guidance on when Claude should select this skill.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks for molecular visualization, protein rendering, publication-quality figures, or mentions PyMOL or ChimeraX.'
Include additional natural trigger terms users might say, such as 'molecular visualization', 'protein structure rendering', '3D molecular graphics', 'ray tracing', '.pml', '.cxc'.
List more specific actions beyond 'generate scripts', such as 'set up lighting, materials, and camera angles for publication-quality molecular images'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (molecular visualization) and a specific action (generate rendering scripts), and mentions two specific tools (PyMOL, UCSF ChimeraX), but doesn't list multiple concrete actions beyond 'generate scripts'. | 2 / 3 |
Completeness | It answers 'what' (generate rendering scripts) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'when' is entirely absent, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes good specific terms like 'PyMOL', 'ChimeraX', 'photorealistic rendering', and 'scripts', but misses common user variations like 'molecular visualization', 'protein structure', '3D rendering', 'ray tracing', or file extensions like '.pml', '.cxc'. | 2 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche — photorealistic rendering scripts for two named molecular visualization tools. It is highly unlikely to conflict with other skills. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity and structural disorganization. It contains extensive boilerplate sections (security checklists, risk assessments, lifecycle status, response templates) that don't help Claude generate rendering scripts. The core actionable content — CLI usage and parameter tables — is buried among redundant and generic workflow descriptions, and the document references bundle files that don't exist.
Suggestions
Remove all boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Requirements, Input Validation, Error Handling) and consolidate into a lean document focused on: what the tool does, how to invoke it, key parameters, and example outputs.
Eliminate duplicate/self-referential sections — merge 'Example Usage' and 'Usage' into one section, remove 'Quick Check' (redundant with 'Audit-Ready Commands'), and remove all 'See ## X above' lines.
Add a validation step in the workflow for checking generated script syntax (e.g., verifying PyMOL .pml files parse correctly) and include a feedback loop for handling invalid PDB IDs or malformed output.
Either provide the referenced bundle files (references/, scripts/main.py, requirements.txt) or remove references to them; currently the skill references paths that don't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose and repetitive. It contains multiple redundant sections (e.g., 'Quick Check' and 'Audit-Ready Commands' repeat the same py_compile command, 'Example Usage' and 'Usage' overlap heavily). Sections like 'Risk Assessment', 'Security Checklist', 'Evaluation Criteria', 'Lifecycle Status', 'Response Template', 'Output Requirements', and 'Input Validation' are boilerplate that don't add actionable value for Claude. Self-referential lines like 'See `## Features` above for related details' waste tokens. The document is well over 200 lines when it could be under 80. | 1 / 3 |
Actionability | The skill provides concrete CLI commands with specific parameters and a detailed parameter table, which is good. However, the actual rendering script generation logic is entirely delegated to `scripts/main.py` which is not provided in the bundle, making it impossible to verify executability. The commands themselves are concrete and copy-paste ready, but the workflow steps are generic and not specific to molecular rendering. | 2 / 3 |
Workflow Clarity | There are two separate 'Workflow' sections — one generic 5-step process and one 4-step 'Example run plan' — neither of which includes validation checkpoints specific to the rendering task. There's no feedback loop for checking whether generated scripts are valid PyMOL/ChimeraX syntax, no verification that PDB IDs resolve correctly, and no guidance on what to do if rendering fails. The workflow steps are abstract and could apply to any script-running task. | 1 / 3 |
Progressive Disclosure | The document is a monolithic wall of text with no bundle files provided to support the many references (e.g., 'See `references/` for...', 'See `## Features` above'). Self-referential pointers like 'See `## Usage` above for related details' are confusing and circular. Content that should be in separate files (parameter tables, preset tables, security checklists) is all inline, making the document bloated. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
73f6514
- 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.