CtrlK
BlogDocsLog inGet started
Tessl Logo

single-drug-faers-safety-profile-research-planner

Generates complete FAERS pharmacovigilance study designs for one-drug whole-profile safety mapping using signal detection, subgroup analysis, onset/seriousness characterization, and conservative label-gap interpretation.

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 ./awesome-med-research-skills/Protocol Design/single-drug-faers-safety-profile-research-planner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a well-structured, highly actionable research-planning skill with a clear sequenced workflow, validation checkpoints, and excellent progressive disclosure into eight real reference files. Its main weakness is redundancy between the trigger examples and between the Hard Rules and the step bodies.

Suggestions

Remove the duplicate trigger examples: keep them in one place (Input Validation or Sample Triggers) rather than repeating the same four lines in both.

De-duplicate the Hard Rules: merge rules 3 and 14 (both forbid presenting signals as incidence/risk) and rules 10 and 13 (both forbid silent scope-switching).

Tighten Step 4.5 against Section I, which both cover the reference-literature pack, to avoid restating the same citation rules twice.

DimensionReasoningScore

Conciseness

Mostly substantive domain guidance, but includes noticeable redundancy: the Sample Triggers section duplicates the Input Validation examples, and Hard Rules 3/14 and 10/13 restate body content already covered in the steps.

3 / 5

Actionability

Highly concrete instruction-only guidance: a fixed 7-step sequence, 5 labeled study patterns with use-conditions, 4 workload configs with key additions, and 10 mandatory output sections each with explicit required fields and checklists.

5 / 5

Workflow Clarity

Steps are explicitly ordered ("always run in order"), with a mandatory Dependency Consistency Check before output and a feedback loop ("If any dependency inconsistency is found, revise the plan before outputting").

5 / 5

Progressive Disclosure

SKILL.md is a clear overview with eight well-signaled one-level-deep reference links (study-patterns, workload-configurations, literature-retrieval, workflow-step-template, analysis-modules, method-library, figure-deliverable-plan, validation-evidence-hierarchy), all of which exist as real files.

5 / 5

Total

18

/

20

Passed

Description

66%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 distinct, naming concrete pharmacovigilance methods and a clear niche, but it omits an explicit "Use when..." trigger clause, capping completeness. Slightly more natural-language trigger phrasing would round it out.

Suggestions

Add an explicit "Use when..." clause stating when Claude should invoke this skill, e.g. "Use when planning a single-drug FAERS whole-profile safety study or atlas paper."

Include a couple of plainer user-facing trigger phrases (e.g. "FAERS safety profile", "single-drug adverse-event signal scan") alongside the technical terms.

Clarify the deliverable form ("structured research design / study plan") in the opening verb phrase to round out the "what".

DimensionReasoningScore

Specificity

Lists several concrete actions — "signal detection, subgroup analysis, onset/seriousness characterization, and conservative label-gap interpretation" — giving comprehensive method coverage, with only minor gaps around the deliverable format.

4 / 5

Completeness

The "what" is clearly stated ("Generates complete FAERS pharmacovigilance study designs...") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Good keyword coverage of domain terms a target user would say ("FAERS pharmacovigilance", "one-drug whole-profile safety", "signal detection", "label-gap"), though the language leans technical and omits a few plainer synonyms.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (single-drug whole-profile FAERS safety atlas) with distinct triggers, but has minor overlap risk with a sibling comparative-FAERS skill referenced in the hard rules.

4 / 5

Total

15

/

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.