clinicaltrials-gov-parser

Monitor and summarize competitor clinical trial status changes from ClinicalTrials.gov.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/clinicaltrials-gov-parser/SKILL.md

Quality

Content

60%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 content is highly actionable with real, executable code and CLI examples backed by a verified bundle, and its workflow and reference structure are solid. Its main weakness is verbosity from redundant sections that re-cover error handling, output contracts, and input scope.

Suggestions

Merge the redundant sections — Error Handling with Failure Handling, and Output Requirements with Output Contract and Response Template — to remove padding and respect token budget.

Consolidate the overlapping scope/input sections (When to Use, Input Validation, Required Inputs, When Not to Use) into a single clear input-and-scope section.

Tighten the Workflow so the technical validation step (python -m py_compile scripts/main.py) appears as an explicit checkpoint inside the numbered sequence rather than only in a separate Quick Check section.

Dimension	Reasoning	Score
Conciseness	The 256-line body is noticeably verbose with several duplicate/padded sections — Error Handling vs Failure Handling, Output Requirements vs Output Contract vs Response Template, and When to Use vs Input Validation vs When Not to Use — rather than merely having a few trimmable lines, though it avoids explaining basic concepts.	2 / 5
Actionability	Provides mostly executable guidance: concrete Python import and method calls that map to real script methods, real CLI commands, plus parameter and API-method tables, with only minor gaps (no concrete sample output of what the code produces).	4 / 5
Workflow Clarity	The Workflow section lays out a clear 5-step sequence with validation/fallback checkpoints (stop early on unsupported scope, switch to fallback on failure) plus separate User Checkpoints for batch operations, leaving only minor gaps in integrating the technical py_compile validation into the numbered flow.	4 / 5
Progressive Disclosure	A References section clearly signals one-level-deep pointers to real files (api-docs.md, status-codes.md, examples.md), and the bundle structure matches, but the body itself is long and fairly monolithic with substantial inlined content rather than a lean overview, so it falls short of the score-5 lean-overview anchor.	4 / 5
	Total	14 / 20 Passed

Description

57%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 clearly distinct within a well-defined niche, but it omits any explicit 'when to use it' trigger guidance, which caps completeness and limits trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when monitoring competitor trial recruitment, completion, or status changes on ClinicalTrials.gov').

Include natural synonyms and identifiers users say, such as NCT numbers, recruitment/enrollment status, and ClinicalTrials.gov, to broaden trigger-term coverage.

Enumerate a couple more concrete actions (e.g., 'track recruitment status' or 'generate competitor summary reports') to lift specificity toward the comprehensive anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('competitor clinical trial status changes from ClinicalTrials.gov') and two concrete actions ('Monitor and summarize'), but does not enumerate multiple specific actions like the score-5 anchor (extract/fill/merge/convert), so it sits at the 1-2 concrete actions anchor.	3 / 5
Completeness	The description gives a clear 'what' but lacks any 'Use when...' trigger clause or equivalent explicit 'when' guidance, which per the judging guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant natural terms ('clinical trial', 'status changes', 'ClinicalTrials.gov', 'competitor') a user might say, but misses common variations and synonyms such as 'recruitment', 'enrollment', or 'NCT', matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'competitor clinical trial status changes from ClinicalTrials.gov' carves out a clear, narrow niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	14 / 20 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/Evidence Insight/clinicaltrials-gov-parser/SKILL.md
Commit: 63c61d3

Reviewed: 3 hours 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.