table-1-generator
Automated baseline characteristics table generation for clinical papers
57
Quality
35%
Does it follow best practices?
Impact
99%
3.66xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Data analysis/table-1-generator-advanced/SKILL.mdQuality
Discovery
32%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 specific niche (clinical paper table generation) but is too terse to be effective for skill selection. It lacks explicit trigger guidance, detailed actions, and natural keyword variations that users would employ when requesting this functionality.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when creating Table 1, demographics tables, patient baseline summaries, or when working with clinical trial data for publication'
Expand the capability description to list specific actions such as 'Generates summary statistics, formats demographic data, calculates p-values, creates publication-ready baseline tables'
Include natural keyword variations users might say: 'Table 1', 'demographics', 'patient characteristics', 'study population', 'clinical trial baseline'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (clinical papers) and a specific action (baseline characteristics table generation), but doesn't list multiple concrete actions or detail what 'generation' entails (e.g., statistical summaries, formatting, data extraction). | 2 / 3 |
Completeness | Only describes what the skill does at a high level; completely missing a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'baseline characteristics table', 'clinical papers', but misses common variations users might say such as 'Table 1', 'demographics table', 'patient characteristics', 'clinical trial', or 'study population'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'baseline characteristics table' and 'clinical papers' is fairly specific to a niche domain, but could overlap with general table generation or clinical writing skills without clearer boundaries. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a basic CLI interface description but lacks the depth needed for reliable Table 1 generation. It's padded with generic boilerplate (security checklists, lifecycle status, evaluation criteria) while missing critical actionable content like example input data formats, expected output examples, and validation workflows for statistical correctness.
Suggestions
Add a concrete workflow with validation steps: 1) inspect data, 2) run generation, 3) verify statistical test appropriateness, 4) review output formatting
Include an example showing input CSV structure and corresponding Table 1 output format
Remove generic boilerplate sections (Evaluation Criteria, Lifecycle Status, Security Checklist) that don't provide Table 1-specific guidance
Add guidance on validating statistical test selection (e.g., when t-test vs Mann-Whitney is appropriate based on data distribution)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like the generic evaluation criteria, lifecycle status, and security checklist that add bulk without providing actionable guidance specific to Table 1 generation. The core content is reasonably efficient but padded with boilerplate. | 2 / 3 |
Actionability | Provides a concrete CLI command and parameter table, but lacks executable code examples showing how the script actually works internally. The 'Features' section describes capabilities abstractly rather than showing how to use them. | 2 / 3 |
Workflow Clarity | No workflow sequence is provided - just a single command with no validation steps, no guidance on what to do if output is incorrect, and no feedback loop for verifying statistical appropriateness of the generated table. | 1 / 3 |
Progressive Disclosure | Content is organized into sections but everything is in one file with no references to detailed documentation. The requirements.txt reference exists but no link to actual script documentation or examples of input/output formats. | 2 / 3 |
Total | 7 / 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
ca9aaa4
- 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.