ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
57
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/ectd-xml-compiler/SKILL.mdQuality
Discovery
82%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 highly specific and domain-focused, clearly naming the input formats, output format, and regulatory standards. Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The niche domain (pharmaceutical eCTD submissions) makes it very distinctive.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user uploads drug application documents and needs eCTD-compliant XML output, or mentions eCTD, regulatory submissions, or CTD module structure.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists concrete actions: 'convert uploaded drug application documents (Word/PDF) into XML skeleton structure' and specifies compliance with 'eCTD 4.0/3.2.2 specifications'. Multiple specific capabilities are named. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (convert drug application documents to eCTD-compliant XML), but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the description of the action. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'drug application documents', 'Word/PDF', 'XML', 'eCTD', '4.0/3.2.2', 'skeleton structure'. Users in the pharmaceutical regulatory domain would naturally use terms like 'eCTD', 'drug application', and 'XML skeleton'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: eCTD 4.0/3.2.2 compliance, drug application documents, XML skeleton generation. This is unlikely to conflict with any other skill due to its very specific pharmaceutical regulatory domain. | 3 / 3 |
Total | 11 / 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 is heavily padded with boilerplate, redundant descriptions, and generic template sections that are not specific to eCTD XML compilation. While the Usage section with CLI arguments and the eCTD structure overview provide some useful domain-specific content, the majority of the file consists of generic workflow instructions, security checklists, and response templates that waste context window space. The multiple competing workflow sections create confusion rather than clarity, and critical validation steps for regulatory-compliant XML generation are inadequately addressed.
Suggestions
Remove all boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Requirements) and generic workflow descriptions—keep only eCTD-specific content.
Consolidate the three competing workflow descriptions into a single, concrete workflow with explicit validation checkpoints: parse document → classify module → generate XML → validate against DTD → fix errors → output.
Move detailed CLI options, module recognition rules, and eCTD structure diagrams into separate reference files and link to them from a concise overview in the main SKILL.md.
Add a concrete code example or command sequence showing the validate-fix-retry loop for generated XML, since regulatory compliance is the core value proposition.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with massive redundancy. The 'When to Use' section repeats the description verbatim, 'Key Features' restates the purpose again, there are self-referential links ('See ## Usage above'), duplicate sections (two '## References'), contradictory statements ('## Prerequisites: No additional Python packages required' vs '## Dependencies' listing three packages), boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that waste tokens without adding actionable value for Claude. | 1 / 3 |
Actionability | The Usage section with CLI arguments/options and examples is reasonably concrete and actionable. However, there's no actual executable code shown for the core conversion logic—just CLI invocations of a script whose implementation isn't visible. The module auto-recognition rules table and document parsing logic are descriptive rather than executable. The 'Example run plan' is generic and not specific to eCTD conversion. | 2 / 3 |
Workflow Clarity | There are multiple competing workflow descriptions (the 'Example Usage' run plan, the 'Workflow' section, the 'Implementation Details' section) that are all generic and not specific to eCTD XML compilation. None include explicit validation checkpoints for the generated XML beyond mentioning the --validate flag. For a task involving XML generation that must comply with regulatory specifications, the absence of concrete validation-then-fix feedback loops is a critical gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with many sections that could be separated. There are self-referential broken links ('See ## Usage above', 'See ## Workflow above'), duplicate References sections, and boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) that bloat the main file. The eCTD structure diagram, detailed CLI options, and module recognition rules could all be in separate reference files. | 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
8277276
- 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.