meta-rob-plot

Draw ROB2 risk-of-bias plots, including a Traffic Light Plot and a Summary Bar Plot. Input is a CSV file with ROB2 assessments for each study; output are two PNG plot files.

Quality

56%

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/meta-rob2-plot/SKILL.md

Quality

Content

42%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 concrete, executable workflow with real bundled scripts, but it is heavily padded by an embedded duplicate skill definition, a duplicated data table, generic boilerplate, and a Python/R execution-path contradiction. Removing the embedded block and reconciling the execution path would substantially improve quality.

Suggestions

Delete the embedded ```skill block (lines ~98–224) and its duplicate frontmatter/table; keep a single, canonical workflow and data-format table.

Reconcile the execution path: the Workflow calls the R script while 'Example Usage' and 'Quick Validation' call the Python script — pick one primary path and document the other only if genuinely supported.

Remove the broken `python scripts/rob2_plot.py --help` instruction (the script uses raw argv and has no --help), and fix the 'See ## Workflow above' cross-reference, since Workflow appears below Implementation Details.

Replace the generic boilerplate ('When to Use', 'Output Contract', 'Completion Checklist', etc.) with ROB2-specific guidance, and add an output-verification step confirming the two PNGs were written.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose with several padded/redundant sections: an entire embedded second skill definition (the nested ```skill block with its own frontmatter and re-stated workflow), a duplicated data-format table, and generic boilerplate sections like 'When to Use'/'Output Contract'/'Completion Checklist'.	2 / 5
Actionability	Provides concrete executable commands (`Rscript scripts/rob2_plot.R "<csv_path>" "<save_name>" "<output_dir>"` with documented params) and a real data-format table, but the Python-vs-R execution-path contradiction and the broken `python scripts/rob2_plot.py --help` suggestion leave meaningful gaps.	3 / 5
Workflow Clarity	A clear 3-step sequence (validate input → run script → emit results) with an input-validation/re-submit feedback loop exists, but output verification is absent, the Python/R path contradiction muddies execution, and the batch nature caps the score at 3 without verification checkpoints.	3 / 5
Progressive Disclosure	Has section structure and one-level-deep, clearly signaled references to real bundle scripts (scripts/rob2_plot.R, rob2_plot.py, validate_skill.py), but the inlined embedded second skill document and duplicated table are content that should not live in the overview.	3 / 5
	Total	11 / 20 Passed

Description

70%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, distinct, and uses natural domain keywords, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Adding a 'Use when...' clause would lift it into the top band.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user has ROB2 risk-of-bias assessments and wants a traffic-light or summary bar visualization.'

Add common synonyms/variations users might say, such as 'risk of bias', 'RoB 2', 'Cochrane risk-of-bias', or '.csv', to broaden trigger coverage.

Mention the expected output file extensions explicitly in the trigger phrasing to reinforce the PNG deliverable.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions — 'Draw ROB2 risk-of-bias plots, including a Traffic Light Plot and a Summary Bar Plot' plus explicit CSV input and two PNG outputs — with only minor coverage gaps.	4 / 5
Completeness	It clearly states the 'what' (draw two named plots from CSV to PNG) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms a researcher would say ('ROB2', 'risk-of-bias', 'Traffic Light Plot', 'Summary Bar Plot', 'CSV', 'PNG'), though a few synonyms/extensions are missing.	4 / 5
Distinctiveness Conflict Risk	'ROB2 risk-of-bias plots' is a clear, narrow niche with distinct triggers and minimal conflict risk against other skills.	5 / 5
	Total	16 / 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/meta-rob2-plot/SKILL.md
Commit: f5ef65b

Reviewed: ~4 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.