ebm-calculator

Evidence-Based Medicine diagnostic test calculator. Computes sensitivity, specificity, PPV, NPV, likelihood ratios, NNT, and pre/post-test probability.

Quality

71%

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/Other/ebm-calculator/SKILL.md

Quality

Content

67%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 body is well-structured and actionable with a clear validated workflow and a real referenced script, but it carries redundant command blocks and generic boilerplate sections, and leaves the references/guidelines.md bundle file unreferenced.

Suggestions

Merge the "Quick Check" and "Audit-Ready Commands" sections into a single validation block to remove the duplicated py_compile command and tighten conciseness.

Either link references/guidelines.md from the body (e.g., under a References section) or remove it, so every bundle file is reachable via clear one-level navigation.

Trim generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) to only what is specific to EBM calculation to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The core sections (Workflow, Parameters, Output Format) are efficient and specific, but redundant command blocks ("Quick Check" and "Audit-Ready Commands" both run py_compile) and generic boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template) add tokens that could be trimmed, fitting the score-3 anchor.	3 / 5
Actionability	Concrete executable commands (py_compile, `python scripts/main.py --help`), a complete parameter table with flags and defaults, and a defined JSON output format give mostly copy-paste-ready guidance, with the full worked examples living in the script's --help epilog rather than inline, matching the score-4 anchor.	4 / 5
Workflow Clarity	The 7-step Workflow is clearly sequenced with an explicit input-validation step, a user-confirmation checkpoint (step 4), and a missing-parameter fallback (step 7), but it lacks a validate→fix→retry feedback loop, fitting the score-4 anchor; this is a calculator rather than a destructive/batch operation so the score-3 cap does not apply.	4 / 5
Progressive Disclosure	The body is well-organized into clear sections and correctly offloads executable logic to scripts/main.py (a real referenced file), but references/guidelines.md exists as an orphaned bundle file never linked from the body, a minor organization gap matching the score-4 anchor.	4 / 5
	Total	15 / 20 Passed

Description

75%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 is specific and distinctive, naming a comprehensive set of computed EBM metrics, but it lacks an explicit "Use when..." trigger clause, which caps its completeness and leaves natural trigger phrases to the body.

Suggestions

Add a "Use when..." sentence to the description with concrete trigger phrases (e.g., "Use when the user asks to calculate sensitivity, specificity, likelihood ratios, NNT, or convert pre/post-test probability") to lift completeness above 3.

Include natural user-spoken synonyms such as "EBM calculator" or "diagnostic accuracy" directly in the description to improve trigger-term quality.

Dimension	Reasoning	Score
Specificity	"Computes sensitivity, specificity, PPV, NPV, likelihood ratios, NNT, and pre/post-test probability" lists multiple concrete computed actions with comprehensive coverage of the calculator's metrics, matching the score-5 anchor.	5 / 5
Completeness	It clearly states the "what" (computes the listed metrics) but provides no "Use when..." trigger guidance in the description itself; per the rubric a missing explicit trigger clause caps completeness at 3, matching the score-3 anchor.	3 / 5
Trigger Term Quality	The description surfaces the relevant technical keywords (sensitivity, specificity, PPV, NPV, likelihood ratios, NNT, pre/post-test probability) giving good keyword coverage, but it omits natural synonyms and user-spoken phrases like "EBM calculator" or "diagnostic accuracy" that appear only in the body, fitting the score-4 anchor.	4 / 5
Distinctiveness Conflict Risk	"Evidence-Based Medicine diagnostic test calculator" with its specific metric list carves out a clear niche with distinct triggers and minimal overlap with other skills, matching the score-5 anchor.	5 / 5
	Total	17 / 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/Other/ebm-calculator/SKILL.md
Commit: 63c61d3

Reviewed: 6 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.