adverse-event-narrative
1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work. 2. Validate that the request matches the documented scope and stop early if the task would require unsupported as.
33
Quality
17%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/adverse-event-narrative/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is severely deficient across all dimensions. It reads like generic process instructions rather than a skill description, lacks any domain specificity, contains no natural trigger terms, and appears to be truncated ('unsupported as.'). It would be impossible for Claude to distinguish when to use this skill versus any other.
Suggestions
Identify and state the specific domain or task this skill handles (e.g., 'Validates API requests', 'Reviews code submissions', 'Processes form data').
Add a 'Use when...' clause with concrete trigger terms that users would naturally say when they need this skill.
Replace abstract process language with specific, concrete actions the skill performs (e.g., 'checks input formats', 'validates JSON schemas', 'verifies required fields').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'user objective', 'required inputs', 'non-negotiable constraints', and 'detailed work' without specifying any concrete actions or domain. No specific capabilities are listed. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' in any meaningful way and completely lacks a 'when should Claude use it' clause. It describes a generic validation process without context. | 1 / 3 |
Trigger Term Quality | Contains no natural keywords users would say. Terms like 'non-negotiable constraints', 'documented scope', and 'unsupported as' (appears truncated) are technical jargon that users wouldn't naturally use when requesting help. | 1 / 3 |
Distinctiveness Conflict Risk | Extremely generic description that could apply to virtually any skill. 'Confirm user objective' and 'validate request' are universal behaviors, not distinctive triggers for a specific skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity and redundancy, with the description text repeated three times and excessive boilerplate sections that don't add value. While it contains useful domain-specific content about CIOMS narratives and causality assessment with code examples, the actionability is undermined by potentially non-existent module imports and incomplete implementations. The structure is reasonable but the content-to-value ratio is poor.
Suggestions
Remove duplicate content: the description text appears in 'When to Use', 'Key Features', and 'Workflow' sections - consolidate to one location
Delete or move boilerplate sections (Output Requirements, Error Handling, Input Validation, Response Template) to a separate reference file - these are generic and inflate the skill unnecessarily
Verify that code examples reference actual existing modules, or provide complete inline implementations rather than imports from potentially non-existent files
Fix the 'Implementation Details' section that references '## Workflow above' when Workflow actually appears below it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with significant redundancy. The description text is repeated multiple times (in 'When to Use', 'Key Features', and 'Workflow'). Contains unnecessary boilerplate sections like 'Output Requirements', 'Error Handling', 'Input Validation', and 'Response Template' that add little value. The skill explains concepts Claude already knows (what CIOMS is, what adverse events are). | 1 / 3 |
Actionability | Contains executable Python code examples and bash commands, but many are incomplete or reference modules that may not exist (e.g., 'from scripts.narrative_generator import NarrativeGenerator'). The code examples show API usage but lack complete working implementations. Some commands are duplicated (--help appears multiple times in Audit-Ready Commands). | 2 / 3 |
Workflow Clarity | The workflow section provides a clear 5-step sequence, and the Quality Checklist provides validation checkpoints. However, the workflow is generic and doesn't integrate well with the specific adverse event narrative generation process. Missing explicit validation steps between code execution stages. The 'Implementation Details' section references '## Workflow above' but Workflow appears below it. | 2 / 3 |
Progressive Disclosure | References external files appropriately (references/, scripts/) and has clear section headers. However, the document is monolithic with excessive inline content that could be split. The boilerplate sections at the end (Output Requirements, Error Handling, Input Validation, Response Template) bloat the main file unnecessarily. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
4a48721
- 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.