table-1-generator

Automated generation of baseline characteristics tables (Table 1) for clinical research papers.

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/table-1-generator/SKILL.md

Quality

Content

60%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.

The core operational content — usage command, parameters, features, validation checks — is solid and executable, but it is buried under a large mass of generic policy boilerplate that pads token cost without adding Table-1-specific value. Trimming the boilerplate and concretizing the undefined fallback path would substantially lift the body.

Suggestions

Cut the generic compliance sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Contract, User Checkpoints) or compress them to a few lines — they contribute no skill-specific knowledge.

Define the 'fallback path' concretely: what should Claude do when scripts/main.py fails (e.g., manual pandas recipe or a specific error-reporting format), instead of only naming it.

Add a short example invocation using --vars and a sample of the expected Table 1 output so the common case is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Roughly half of the ~200-line body is generic compliance boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Contract, User Checkpoints) that adds no skill-specific knowledge Claude doesn't already have — squarely 'noticeably verbose; several unnecessary explanations or padded sections'. Not score 1 because the core sections (Usage, Parameters, Features) are tight and no basic concepts are re-explained.	2 / 5
Actionability	The body gives copy-paste-ready commands ('python scripts/main.py --data patients.csv --group treatment --output table1.csv', 'python -m py_compile scripts/main.py'), a concrete parameter table, and install instructions — mostly executable guidance with minor gaps. Not score 5 because the 'documented reasoning path' and 'manual fallback' are referenced but never defined, --vars usage is not exemplified, and there is no example of the expected output.	4 / 5
Workflow Clarity	The Workflow section sequences five steps, Quick Check/Audit-Ready Commands provide runnable validation up front, and Quick Validation plus User Checkpoints cover output verification and overwrite confirmation — clear sequence with most checkpoints present. Not score 5 because the fallback path is invoked ('switch to the fallback path') without ever being defined, and there is no explicit validate-the-generated-table step with a fix-and-retry loop.	4 / 5
Progressive Disclosure	The bundle is SKILL.md plus one script (scripts/main.py), which exists and is clearly referenced in Quick Check, Audit-Ready Commands, Usage, and Prerequisites — appropriately one level deep with clean section headers. Not score 5 because everything lives inline in a single ~200-line file; the boilerplate sections inflate the overview, and there is no well-signaled separation of quick-start material from extended policy content.	4 / 5
	Total	14 / 20 Passed

Description

48%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.

The description identifies a precise, distinctive niche but undersells it: one generic action, no usage triggers, and no synonyms beyond 'Table 1'/'baseline characteristics'. Adding a 'Use when...' clause and 2-3 concrete actions would move it firmly into good-example territory.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Table 1, baseline characteristics, demographics, or summary statistics for a clinical research paper.'

Enumerate the concrete actions the skill performs, e.g. 'Detects variable types, computes mean±SD / median[IQR / n(%), runs group comparisons (t-test, chi-square), and formats APA-style Table 1 output.'

Include natural synonyms and file triggers users would say — 'demographics table', 'descriptive statistics', 'patient CSV' — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names a precise domain — "baseline characteristics tables (Table 1) for clinical research papers" — but offers only a single generic action, "Automated generation", paralleling the score-2 anchor 'Processes PDF files'. It does not list the 1-2 distinct concrete actions (e.g., computing descriptive statistics, group comparisons, APA formatting) needed for score 3.	2 / 5
Completeness	The 'what' is clear (automated generation of Table 1 for clinical papers) but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'when' is entirely absent, capping completeness at 3 per the judging guideline. Not score 4 because nothing implies the usage context, and not score 2 because the 'what' is concrete rather than vague.	3 / 5
Trigger Term Quality	Relevant natural terms are present ("Table 1", "baseline characteristics", "clinical research papers") but common variations users would say are missing: "demographics table", "summary/descriptive statistics", "patient data", and file-extension triggers like .csv. This matches the anchor 'Some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	"Table 1" and "baseline characteristics" for clinical research form a clear, niche trigger that is mostly distinct, with only minor overlap risk against general statistics/data-analysis skills. Not score 5 because the single generic action gives related data-analysis skills some room to compete for ambiguous requests like 'summarize my patient data'.	4 / 5
	Total	12 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/table-1-generator/SKILL.md
Commit: 686e09d

Reviewed: 13 hours 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.