CtrlK
BlogDocsLog inGet started
Tessl Logo

epidemiology

Performs epidemiological analyses including disease modeling (SIR/SEIR), outbreak investigation, risk factor identification, incidence/prevalence estimation, and causal inference from observational data; trigger when users discuss disease spread, public health data, or populat...

63

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/epidemiology/SKILL.md
SKILL.md
Quality
Evals
Security

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 content is a lean, well-structured instruction-only skill with a clear 7-step methodology and a validation checklist. Its weakest point is actionability: it names tools and methods but provides no executable code or commands, and feedback loops for verification are implicit rather than explicit.

Suggestions

Add at least one concrete executable example (e.g., a short EpiEstim or R0-package snippet, or a DAGitty DAG definition) so the guidance is copy-paste ready rather than purely descriptive.

Insert an explicit validate-and-remediate checkpoint in the methodology (e.g., 'After fitting the model, check residuals and re-estimate R0 if assumptions are violated') to turn the checklist into a feedback loop.

Specify which database/tool to use per workflow step so the guidance is unambiguous about execution.

DimensionReasoningScore

Conciseness

The body is mostly efficient — sectioned checklists and short step descriptions assume Claude's knowledge of epidemiology — with only minor instances (e.g., restating 'case-fatality ratio' definitions inline) that could be trimmed; not a 5 because a few bullets restate concepts Claude already knows.

4 / 5

Actionability

The methodology names tools (EpiEstim, DAGitty) and methods but provides no executable code, commands, or concrete parameter examples — it describes rather than instructs, matching the 'some concrete guidance but incomplete' anchor.

3 / 5

Workflow Clarity

The 7-step methodology is clearly sequenced and the Quality Checklist acts as a validation checkpoint, but there is no explicit validate-and-remediate feedback loop for the analytic/modeling operations, leaving minor validation gaps short of a 5.

4 / 5

Progressive Disclosure

Content is well-organized into clearly labeled sections (When to Trigger, Methodology, Databases, Output Format, Quality Checklist) appropriate for an instruction-only skill under 50 lines with no bundle files; minor gaps (e.g., database list could live in a reference file if expanded) keep it from a 5.

4 / 5

Total

15

/

20

Passed

Description

83%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 highly specific and distinct, clearly stating the skill's capabilities and including an explicit trigger clause. Its main weakness is the truncated 'trigger when' phrase ('populat...'), which cuts off natural trigger terms and slightly weakens completeness and trigger term quality.

Suggestions

Complete the truncated trigger clause ('populat...') so the full set of natural trigger phrases is present rather than cut off.

Add a few common synonyms/extensions (e.g., 'epidemic curves', 'herd immunity', 'cohort/case-control') to the trigger list to maximize keyword coverage.

Ensure the trigger phrase reads as third-person ('trigger when users discuss...') consistently and is not left mid-word.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'disease modeling (SIR/SEIR)', 'outbreak investigation', 'risk factor identification', 'incidence/prevalence estimation', 'causal inference' — covering the domain comprehensively.

5 / 5

Completeness

It clearly states 'what' (the epidemiological analyses) and includes an explicit 'trigger when...' clause for 'when', but the truncated trigger phrase prevents the fully explicit, concrete trigger phrases needed for a 5.

4 / 5

Trigger Term Quality

The 'trigger when users discuss disease spread, public health data, or populat...' clause gives good natural keyword coverage, but the trigger list is truncated mid-word ('populat...'), losing common synonyms and variations that would warrant a 5.

4 / 5

Distinctiveness Conflict Risk

A clear epidemiology niche with distinct triggers (SIR/SEIR, R0, attack rate, DAGs) unlikely to collide with other skills; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
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.