meta-forest-continuous-plot

Generate forest plots for meta-analysis of continuous data. Input a CSV file containing study names, means, standard deviations, and sample sizes for experimental and control groups. Output forest plot PNG and data table CSV.

Quality

61%

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-forest-continuous-plot/SKILL.md

Quality

Content

48%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 has a clear, validated workflow and a concrete Rscript path, but it is padded with generic boilerplate and its Python guidance is broken (citing a non-functional --help on a hardcoded converter) while omitting the real CLI script and failing to link the detailed README.

Suggestions

Remove the generic boilerplate sections ('When to Use', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restate safe/reproducible guidance Claude already applies, and keep only skill-specific content.

Fix the Python path: reference `scripts/forest_continuous.py` (the real CLI with csv_path/outcome_name/output_dir args) instead of `scripts/convert_data.py --help`, which does not exist.

Replace the inlined output template and R-package list with a one-level pointer to scripts/README.md so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: large generic boilerplate sections ('When to Use', 'Key Features', 'Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') repeat safe-reproducible-within-scope messaging Claude already knows, and the box-drawing output template duplicates scripts/README.md rather than pointing to it.	2 / 5
Actionability	Concrete Rscript command and data-format table are present, but the documented Python entry point is wrong: 'Quick Validation' and 'Example Usage' point to `scripts/convert_data.py --help`, yet that script has no argparse/--help and uses a hardcoded input path, while the actually usable CLI script `forest_continuous.py` is never mentioned in SKILL.md.	3 / 5
Workflow Clarity	Three clearly sequenced steps with an explicit validation checkpoint in Step 1 (check columns, at least 2 studies, reasonable values) and a correction feedback loop ('If data is problematic, prompt the user to correct and resubmit'); only minor gaps such as the omitted R-vs-Python fallback branch.	4 / 5
Progressive Disclosure	Bundle contains a detailed scripts/README.md plus the real forest_continuous.py, but SKILL.md references only convert_data.py and the R script, never signaling the richer README, while inlining output-template and R-package detail that already lives in README — references present but not clearly signaled to the best resource.	3 / 5
	Total	12 / 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.

A specific, distinctive description with concrete inputs and outputs, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3. Otherwise strong across specificity and distinctiveness.

Suggestions

Add a 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks for a forest plot, meta-analysis of continuous outcomes, or pooled effect sizes from study means/SDs').

Include common synonyms and a file extension cue (e.g., 'forest plot', 'meta-analysis', 'SMD', 'continuous outcomes', '.csv') to lift trigger-term coverage to 5.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate forest plots for meta-analysis', input CSV with named columns (study names, means, SDs, sample sizes for experimental/control groups), and output of 'forest plot PNG and data table CSV' — giving comprehensive coverage of inputs, processing, and outputs.	5 / 5
Completeness	The 'what' is clear and concrete (generate forest plots from continuous-data CSV, output PNG + CSV), but there is no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Strong natural domain keywords a user would say ('forest plots', 'meta-analysis', 'continuous data', 'CSV', 'experimental and control groups', 'PNG') but lacks synonyms/file extensions and does not include the phrase 'meta-analysis' variants like 'systematic review'; a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	'forest plots for meta-analysis of continuous data' is a clear niche with distinct, specialized triggers unlikely to fire for unrelated skills; minimal conflict risk.	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/meta-forest-continuous-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.