adverse-event-narrative

Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.

Quality

72%

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/Academic Writing/adverse-event-narrative/SKILL.md

Quality

Content

62%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body has a well-sequenced workflow with checkpoints and validation, but is undermined by non-executable code examples (referencing missing modules) and reference/script listings that don't match the actual bundle files, plus some redundant inline content.

Suggestions

Reconcile the Scripts and References listings with the actual bundle—only main.py exists, so either add the referenced modules or rewrite examples to use the real CIOMSNarrativeGenerator API in main.py.

Trim the redundant "Overview" (it restates the description) and move the inline WHO-UMC category list into the existing references/ files to reduce token weight.

Remove the duplicated "python scripts/main.py --help" line and ensure every listed reference filename maps to a real file in references/.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with actionable code and checklists, but padded with an "Overview" that repeats the frontmatter, inline WHO-UMC category reference material that belongs in references/, and a duplicated verbatim "--help" command.	2 / 3
Actionability	Provides concrete commands and Python code, but the showcased "from scripts.narrative_generator import NarrativeGenerator" references modules absent from the bundle (only main.py exists, with a different CIOMSNarrativeGenerator API), so the examples are not executable as written.	2 / 3
Workflow Clarity	An 8-step Workflow with explicit "Checkpoint" steps (3 and 6), a Fallback branch, pre/post-generation checklists, and validation/error-handling guidance gives clear sequencing with validation feedback loops.	3 / 3
Progressive Disclosure	A real references/ and scripts/ structure exists with one-level-deep signaled references, but the body's file listings do not match the actual bundle (e.g., cioms_i_guidelines.pdf, narrative_generator.py, who_umc_causality.md do not exist), so navigation would break.	2 / 3
	Total	9 / 12 Passed

Description

82%Weight 40%Scale 1-3

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 concrete regulatory-narrative capabilities with strong domain trigger terms. Its main gap is the absence of an explicit "when to use" trigger clause in the description itself, which lives in the body instead.

Suggestions

Add an explicit "Use when..." trigger clause to the description (e.g., "Use when generating AE/ICSR narratives for FDA, EMA, or CIOMS I submission, or when the user says 'AE narrative', 'CIOMS narrative', or 'safety report'.") to lift completeness to 3.

Move everyday trigger phrasings currently only in the body ("AE narrative", "ICSR", "CIOMS narrative", "safety report", "MedWatch narrative") into the description so the trigger terms surface at the top level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—"Generates CIOMS I-compliant ICSR narratives", "temporal analysis", "MedDRA coding", "causality assessment using WHO-UMC or Naranjo criteria", and "multi-format output"—naming specific methods rather than vague language.	3 / 3
Completeness	Clearly answers "what" but lacks an explicit "Use when..." trigger clause in the description; the "when" guidance lives only in the body's "When to Use" section, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Covers natural domain terms a pharmacovigilance user would say—"ICSR narratives", "adverse event", "regulatory submission", "FDA and EMA", "MedDRA coding"—with good breadth of phrasings.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche—CIOMS/ICSR adverse event narrative generation anchored to FDA, EMA, WHO-UMC, and Naranjo—making it unlikely to trigger for an unrelated skill.	3 / 3
	Total	11 / 12 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/Academic Writing/adverse-event-narrative/SKILL.md
Commit: f5ef65b

Reviewed: 6 days 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.