CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

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 viable workflow with input validation and an executable R command, but it is buried in generic template boilerplate and a fully duplicated nested SKILL document, with conflicting Python-vs-R execution guidance and a Dependencies section that omits the actual R requirements.

Suggestions

Delete the nested `````skill` block (lines 99-224); extract its unique content (parameter descriptions, output template, plot color legend) into properly referenced sections or files instead of duplicating the workflow and data-format table inline.

Resolve the dual entry-point confusion: state one authoritative execution path (the R script), move the Python variant to a clearly labeled fallback section, and update Dependencies to list R plus ggplot2/reshape2 rather than only Python 3.10+.

Remove the template boilerplate ("Key Features" that restates the description, "Deterministic Output Rules", "Completion Checklist") and fix the "Quick Validation" expected output to match what validate_skill.py --check actually prints.

DimensionReasoningScore

Conciseness

About half the body is boilerplate ("Key Features" restates the description verbatim; "Output Contract", "Deterministic Output Rules", "Completion Checklist" are generic template filler), and the nested `````skill` block (lines 99-224) duplicates the data-format table, domain definitions, and workflow verbatim (~125 lines). Not 1: the data-format spec and R invocation are genuinely necessary content.

2 / 5

Actionability

The command `Rscript scripts/rob2_plot.R "<csv_path>" "<save_name>" "<output_dir>" and the column table are concrete and executable, but the body presents two conflicting entry points (python scripts/rob2_plot.py --help vs. the R script in Step 2), lists only Python 3.10+ under Dependencies while the real workflow needs R with ggplot2/reshape2, and "Quick Validation" promises an expected output validate_skill.py does not produce. Not 4: the authoritative execution path is ambiguous.

3 / 5

Workflow Clarity

A real sequence exists (validate input values -> prompt user to correct -> execute script -> emit formatted summary) and input validation is present, satisfying the batch-validation cap. However, the sequence is undermined by a duplicated nested workflow, an "Example run plan" that points at the Python script instead of the R script, and a dangling "See `## Workflow` above" cross-reference. Not 4: conflicting duplicate guidance obscures the actual sequence and its checkpoints.

3 / 5

Progressive Disclosure

All referenced bundle paths (scripts/rob2_plot.R, scripts/rob2_plot.py, scripts/validate_skill.py) exist and are one level deep, with clear section headers. But a complete second SKILL document is inlined inside a nested fenced block instead of living in a separate file, duplicating ~125 lines of content. Not 2: structure and script references are present and clearly signaled; not 4: the inlined nested document is a major organization gap.

3 / 5

Total

11

/

20

Passed

Description

75%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, domain-distinct, and clearly states what the skill does with concrete I/O formats, but it omits any "Use when..." trigger guidance and misses some natural synonyms (Cochrane, meta-analysis, .csv).

Suggestions

Append a trigger clause, e.g. "Use when the user has ROB2/risk-of-bias assessment data (e.g., from a Cochrane systematic review) and wants a traffic light or summary bar plot."

Add natural synonyms users would say, such as "risk of bias assessment", "Cochrane review", or "meta-analysis", and the .csv extension.

DimensionReasoningScore

Specificity

"Draw ROB2 risk-of-bias plots, including a Traffic Light Plot and a Summary Bar Plot. Input is a CSV file...; output are two PNG plot files" names multiple concrete actions and pins both input and output formats, comprehensively covering this domain. Not 4: there are no meaningful gaps in action coverage.

5 / 5

Completeness

The "what" is explicit and concrete, but the description contains no "Use when..." clause or equivalent explicit trigger guidance, capping completeness at 3. Not 4: the anchor for 4 requires both what and when to be present.

3 / 5

Trigger Term Quality

Natural user phrases like "ROB2 risk-of-bias", "Traffic Light Plot", "Summary Bar Plot", "CSV", and "PNG" are present, but common synonyms ("risk of bias assessment", "Cochrane", "meta-analysis") and file extensions (.csv) are missing. Not 5: keyword coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

"ROB2" plus the two named plot types define a clear niche with distinct triggers and minimal conflict risk against generic plotting skills. Not 4: no overlap with a closely related skill is apparent.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

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.