CtrlK
BlogDocsLog inGet started
Tessl Logo

tooluniverse-pharmacovigilance

Drug safety and adverse event analysis — FAERS spontaneous-report mining, FDA black-box warnings, signal detection (PRR, ROR, IC), risk factors by demographic/comorbidity, and label change tracking. Use for post-market safety surveillance, AE signal investigation, drug-AE association strength scoring, and pharmacovigilance reports.

69

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is tooluniverse-pharmacovigilance in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 highly actionable with concrete tool calls, formulas, and parameter corrections, but it is padded with conceptual reasoning material Claude largely already knows and ships broken references to four non-existent files. Tightening the reasoning section and providing the referenced bundle files would materially improve it.

Suggestions

Move the seven 'Clinical Reasoning Strategies' into a separate REASONING.md file and keep only a one-line pointer in SKILL.md, eliminating conceptual padding and the duplicated 'Reasoning Strategy 5'.

Provide the four referenced bundle files (SIGNAL_DETECTION.md, REPORT_TEMPLATES.md, CHECKLIST.md, TOOLS_REFERENCE.md) or remove the dead links, since none currently exist in the bundle.

Add an explicit validate→fix→retry loop (e.g., re-run PRR after excluding confounders flagged in Phase 6) to lift workflow clarity above 4.

DimensionReasoningScore

Conciseness

Mostly efficient tool/parameter guidance, but the seven 'Clinical Reasoning Strategies' re-explain pharmacology concepts Claude already knows (on-target/off-target, Naranjo, dose-dependent vs idiosyncratic), and 'Reasoning Strategy 5' is duplicated, adding padding.

3 / 5

Actionability

Fully executable guidance throughout — exact tool calls with parameters, the PRR formula '(A/B)/(C/D)', signal thresholds, severity weights, a WRONG-vs-CORRECT parameter table, and fallback chains.

5 / 5

Workflow Clarity

Phases 0–7 are clearly sequenced with a mandatory report-first step and a Phase 6 mechanistic cross-check, but explicit validate→fix→retry feedback loops are only weakly present and the completeness checklist is referenced to a missing file.

4 / 5

Progressive Disclosure

References to SIGNAL_DETECTION.md, REPORT_TEMPLATES.md, CHECKLIST.md, and TOOLS_REFERENCE.md are clearly signaled, but none of these files exist in the bundle, and the lengthy reasoning-strategies section is inlined where it belongs in a separate file.

3 / 5

Total

15

/

20

Passed

Description

100%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 exemplary: it names a clear niche, lists concrete capabilities, and provides an explicit 'Use for' trigger clause with natural synonyms. It satisfies all four top anchors without verbosity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'FAERS spontaneous-report mining, FDA black-box warnings, signal detection (PRR, ROR, IC), risk factors by demographic/comorbidity, and label change tracking' — giving comprehensive coverage rather than vague domain naming.

5 / 5

Completeness

Explicitly answers both 'what' (the listed analysis capabilities) and 'when' via a clear 'Use for post-market safety surveillance, AE signal investigation...' trigger clause.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage with synonyms users actually say — 'drug safety', 'adverse event', 'AE', 'pharmacovigilance', 'post-market safety surveillance', 'drug-AE association' — matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

Highly specific niche triggers (FAERS, PRR/ROR/IC, black-box warnings, pharmacovigilance) make conflict with unrelated skills minimal, matching the top anchor.

5 / 5

Total

20

/

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

relative_links

Relative link issues: 4 missing

Warning

Total

15

/

16

Passed

Repository
mims-harvard/ToolUniverse
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.