rct-bias-assessment-rob

Automates Risk of Bias 2 (ROB2) assessment for RCT papers by analyzing text against specific domains and synthesizing a report. Use when you need to assess the quality of a clinical trial paper or evaluate risk of bias.

Quality

64%

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/Data Analysis/rct-bias-assessment-rob2/SKILL.md

Quality

Content

46%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 contains a solid, genuine ROB2 assessment workflow with a concrete output schema, but it is diluted by substantial generic boilerplate sections and a few non-executable command examples that do not match the actual scripts.

Suggestions

Remove or collapse the auto-generated boilerplate ('When to Use', 'Key Features', 'Implementation Details') that restates the description and adds generic packaging advice.

Fix command/path inconsistencies: either give assess_rob2.py a real argparse CLI before suggesting `--help`, or document calling its functions directly; invoke extract_pdf.py as scripts/extract_pdf.py consistently.

Add an explicit validation checkpoint (e.g., verify the generated JSON against the output schema before returning the artifact) to strengthen the workflow.

Dimension	Reasoning	Score
Conciseness	Several sections are auto-generated boilerplate padding ('Use this skill when a data analytics task needs a packaged method...', 'Key Features', 'Implementation Details'), and the 'When to Use' list repeats the description verbatim, adding noticeable verbosity without value.	2 / 5
Actionability	Provides concrete commands and a JSON output schema, but the headline `python scripts/assess_rob2.py --help` is not actually runnable since assess_rob2.py has no CLI entry point, and extract_pdf.py is invoked with an inconsistent path.	3 / 5
Workflow Clarity	The assessment workflow (extract study info, assess 5 domains, synthesize overall judgement) is clearly sequenced with explicit synthesis rules, but there are no explicit validation checkpoints or feedback loops for verifying the output.	3 / 5
Progressive Disclosure	Structure is reasonable with a one-level-deep reference to references/rob2_guidelines.md (a real file) and scripts under scripts/, though some domain detail is duplicated inline and the extract_pdf.py path is referenced inconsistently.	4 / 5
	Total	12 / 20 Passed

Description

82%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 cleanly covers both capability and trigger conditions in a specialized niche using third-person voice. Its main weakness is that the described actions are somewhat abstract rather than enumerating concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain (ROB2/RCT papers) and two concrete actions ('analyzing text against specific domains' and 'synthesizing a report'), but the actions are fairly abstract rather than a comprehensive list of specific operations.	3 / 5
Completeness	Explicitly states what it does ('Automates Risk of Bias 2 (ROB2) assessment...') and when to use it ('Use when you need to assess the quality of a clinical trial paper or evaluate risk of bias'), satisfying both halves with concrete triggers.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('risk of bias', 'clinical trial paper', 'RCT', 'ROB2') with both the acronym and its expansion, though a few synonymous phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	ROB2 assessment for RCT papers is a clearly specialized niche with distinct triggers, posing minimal overlap risk against other skills.	5 / 5
	Total	17 / 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/Data Analysis/rct-bias-assessment-rob2/SKILL.md
Commit: 63c61d3

Reviewed: 8 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.