competitor-trial-monitor
Monitor competitor clinical trial progress and alert on market risks
66
48%
Does it follow best practices?
Impact
98%
1.88xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Evidence insights/competitor-trial-monitor/SKILL.mdQuality
Discovery
32%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 identifies a specific domain (pharmaceutical/biotech competitive intelligence) but is too terse to be effective for skill selection. It lacks explicit trigger guidance, detailed capability descriptions, and natural keyword variations that users would employ when requesting this type of analysis.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when analyzing pharma competitors, tracking drug pipelines, reviewing clinical trial databases, or assessing competitive threats in healthcare/biotech'
Expand specific capabilities: what data sources are monitored, what types of alerts are generated (phase transitions, trial failures, FDA decisions), and what risk assessments are provided
Include natural keyword variations users might say: 'pharma competitors', 'drug pipeline', 'trial phases', 'FDA approval', 'competitive landscape', 'biotech analysis'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (competitor clinical trials, market risks) and two actions (monitor, alert), but lacks detail on what specific monitoring entails or what types of alerts/risks are covered. | 2 / 3 |
Completeness | Describes what the skill does (monitor and alert) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains relevant keywords like 'competitor', 'clinical trial', 'market risks', and 'alert', but misses common variations users might say such as 'pharma competitors', 'drug trials', 'pipeline analysis', or 'competitive intelligence'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'clinical trial' and 'competitor' creates a somewhat specific niche, but 'market risks' is generic and could overlap with financial analysis or general competitive intelligence skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides good actionable command examples with complete parameter documentation, but suffers from significant bloat with generic sections (risk assessment, security checklist, evaluation criteria, lifecycle status) that don't help Claude execute the task. The workflow between commands is implicit rather than explicit, and there's no guidance on error handling or validation.
Suggestions
Remove generic boilerplate sections (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status) that don't provide actionable guidance for using the tool
Add a 'Typical Workflow' section showing the sequence: add trials → periodic scan → review alerts → generate report, with validation checkpoints
Include error handling guidance: what happens if an NCT ID doesn't exist, API is unavailable, or scan finds no updates
Consider splitting detailed configuration and alert rules into separate reference files, keeping SKILL.md as a quick-start overview
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains significant padding including a generic risk assessment table, security checklist, evaluation criteria, and lifecycle status sections that don't add actionable value. The core functionality is reasonably documented but buried in boilerplate. | 2 / 3 |
Actionability | Provides fully executable bash commands with concrete examples including real NCT IDs, company names, and drug names. The command reference tables are complete with parameter types, defaults, and requirements. | 3 / 3 |
Workflow Clarity | Commands are documented individually but there's no clear workflow showing the typical sequence (add → scan → report). Missing validation steps for checking if trials exist, handling API failures, or verifying successful additions to watchlist. | 2 / 3 |
Progressive Disclosure | Content is organized with clear sections and tables, but it's monolithic with no references to external files for detailed documentation. The alert rules, configuration, and data storage sections could be split out for a cleaner overview. | 2 / 3 |
Total | 9 / 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
ca9aaa4
- 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.