CtrlK
BlogDocsLog inGet started
Tessl Logo

active-comparator-single-soc-faers-safety-comparison

Generates complete FAERS pharmacovigilance study designs for multi-drug or class-level safety comparison inside one predefined SOC or AE family using active comparators, disproportionality analysis, subgroup characterization, and reviewer-facing evidence control.

55

Quality

63%

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 ./awesome-med-research-skills/Protocol Design/active-comparator-single-soc-faers-safety-comparison/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 skill body is a clearly sequenced, actionable research-design planner with strong progressive disclosure via real reference files and explicit validation checkpoints. Its main weakness is verbosity, with hard rules and rationale restating guidance already implied by the workflow steps.

Suggestions

Collapse the 'Hard Rules' section by removing rules that merely restate constraints already enforced by Steps 5–6 and the output sections, keeping only genuinely additive guardrails.

Promote a few explicitly inlined reference summaries (e.g., the full config comparison table in Step 3) into the corresponding reference files to reduce body length.

Make the validation feedback loop in Section F fully explicit (validate → if errors, fix and re-validate → only proceed when valid) to lift workflow clarity toward the top anchor.

DimensionReasoningScore

Conciseness

The body is well-structured but runs long and restates some guidance the model already understands (e.g., extensive hard-rules restating workflow constraints already covered in the steps), so it is mostly efficient but could be tightened.

3 / 5

Actionability

It gives concrete, executable direction — explicit step sequencing, named output sections (A–J), required fields, table formats, and explicit redirect text for out-of-scope requests — with only minor gaps where detail is delegated to references.

4 / 5

Workflow Clarity

The 7-step execution sequence is clearly ordered with mandatory dependency and consistency checkpoints (Step 5) and validation/robustness separation (Section F), though some validation feedback loops are described at a structural rather than fully explicit validate-fix-retry level.

4 / 5

Progressive Disclosure

SKILL.md acts as an overview with well-signaled, one-level-deep references to eight real bundle files (study-patterns.md, workload-configurations.md, etc.), each linked inline at the relevant step; minor gaps are that some detail is still inlined rather than pushed to references.

4 / 5

Total

15

/

20

Passed

Description

58%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 occupies a clear niche, but it is missing an explicit 'Use when...' trigger clause and leans on technical jargon rather than natural user language, which caps completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases users would naturally say (e.g., 'Use when planning a FAERS comparison of a drug class against active comparators within a single SOC or AE family').

Introduce natural-language synonyms alongside the jargon (e.g., 'adverse-event reporting', 'safety-signal comparison') so trigger terms match how users actually phrase the request.

Tighten the long clause into a tighter action list to push specificity from several actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Generates complete FAERS pharmacovigilance study designs', 'multi-drug or class-level safety comparison', 'disproportionality analysis', 'subgroup characterization', 'reviewer-facing evidence control' — giving solid but not exhaustive coverage of the skill's operations.

4 / 5

Completeness

The 'what' is clearly stated (generates comparative FAERS safety study designs), but there is no explicit 'Use when...' clause or concrete trigger guidance stating when Claude should invoke the skill.

3 / 5

Trigger Term Quality

It includes domain keywords ('FAERS', 'pharmacovigilance', 'SOC', 'AE family', 'disproportionality') but these are technical jargon rather than the natural phrases a user would say, and lacks synonyms or common variations.

3 / 5

Distinctiveness Conflict Risk

The niche is narrow and specific — active-comparator single-SOC FAERS comparison — making it mostly distinct from other skills, with only minor overlap risk against related pharmacovigilance skills.

4 / 5

Total

14

/

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.