rct-bias-assessment-rob2

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

71%

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/Evidence Insight/rct-bias-assessment-rob2/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 body delivers a clear ROB2 workflow, an actionable output schema, and well-signaled references to real bundle files, but it is padded with generic boilerplate sections that inflate the token budget without adding ROB2-specific value.

Suggestions

Remove or condense the generic template sections (When to Use / When Not to Use / Output Contract / Input Validation / Quick Validation) and keep only ROB2-specific guidance, since these add tokens without skill-specific signal.

Fix the extract_pdf.py usage example to include its required argument, e.g. 'python extract_pdf.py <input.pdf>', so the guidance is copy-paste executable.

Replace the generic validation checkpoints with ROB2-specific feedback loops, e.g. verify each domain rating is supported by quoted paper text before synthesizing the overall judgement.

Dimension	Reasoning	Score
Conciseness	Large boilerplate template sections ('When to Use', 'When Not to Use', 'Output Contract', 'Input Validation', etc.) are generic and do not earn their tokens, with some circular phrasing ('Use this skill when the current task can be completed using this skill's bundled scripts').	2 / 5
Actionability	Provides a concrete copy-ready JSON output schema, sequenced domain assessment steps, and a working clean_text import example, with the minor gap that 'python extract_pdf.py' is shown without its required <input PDF file> argument.	4 / 5
Workflow Clarity	The ROB2 workflow is clearly sequenced (extract study info, assess 5 domains, synthesize via explicit High/Some concerns/Low rules, output JSON) with validation/failure-handling sections present, though those checkpoints are generic template text rather than ROB2-specific feedback loops.	4 / 5
Progressive Disclosure	The body is an overview that references one-level-deep real bundle files (references/rob2_guidelines.md and two scripts) with clear signaling, though several non-skill-specific template sections are inlined rather than separated.	4 / 5
	Total	14 / 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 is concise, third-person, and clearly specifies both the task and the trigger conditions, making it highly actionable and distinct. Its only minor weakness is that the listed capabilities stay at a domain level rather than enumerating concrete sub-actions.

Dimension	Reasoning	Score
Specificity	Names the ROB2/RCT domain and two concrete actions ('analyzing text against specific domains and synthesizing a report') but does not enumerate the specific domain-level actions, fitting the anchor for 1-2 concrete actions.	3 / 5
Completeness	Explicitly answers both 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') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user terms ('RCT papers', 'clinical trial paper', 'risk of bias', 'quality of a clinical trial') with good coverage, though a few common synonyms/extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (ROB2 risk-of-bias for RCTs) with distinct triggers and minimal overlap with 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/Evidence Insight/rct-bias-assessment-rob2/SKILL.md
Commit: 63c61d3

Reviewed: 7 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.