forest-plot-styler

Analyze data with `forest-plot-styler` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.

Quality

35%

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/forest-plot-styler/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 content pairs genuinely actionable reference material (parameter table, sample data, executable examples) with heavy generic process boilerplate and broken cross-references. Bundle paths are advertised but absent, and navigation cues point to later sections, weakening structure.

Suggestions

Trim duplicated compile/help checks and remove generic boilerplate (Response Template, Output Requirements, Validation rules) that Claude already knows; keep only forest-plot-specific guidance.

Fix the backward "See ## Features/Usage/Workflow above" pointers and remove or create the referenced bundle files (references/, scripts/main.py, requirements.txt).

Add a concrete validation checkpoint in the Workflow tied to the plotting output (e.g. confirm the PNG/PDF is generated and opens, check the pooled-effect diamond and reference line render).

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: duplicated compile/help checks across Quick Check, Audit-Ready Commands, Usage, and Examples, plus generic process boilerplate (Output Requirements, Response Template, Input Validation, Validation and Safety Rules) that Claude already knows. It is above a 1 because concrete executable content is mixed in, but the padding and repetition keep it below a 3.	2 / 5
Actionability	Executable guidance is strong: a full parameter table with defaults and required flags, an input-column table, a sample CSV, and copy-paste invocations covering basic, custom-style, subgroup, and PDF output. It is not a 5 because one audit example passes prose text to --input (contradicting the CSV/Excel requirement) and a few flags are only loosely specified.	4 / 5
Workflow Clarity	A 5-step Workflow with a fallback step is present, but the steps are generic ("confirm objective", "validate scope") rather than tied to the plotting operation, and there is no executable validation checkpoint on the generated artifact (e.g. verify the output file opens). The checkpoints are implicit, matching the anchor for a 3.	3 / 5
Progressive Disclosure	The body references bundle paths (scripts/main.py, references/, requirements.txt) that do not exist on disk, and navigation is broken ("See ## Features above", "See ## Usage above", "See ## Workflow above" point to sections appearing later). Reference-style content (preset styles, parameter docs) is inlined rather than split out, matching the anchor for minimal structure with buried/non-resolving references.	2 / 5
	Total	11 / 20 Passed

Description

25%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 generic data-analysis boilerplate that omits the skill's actual forest-plot purpose and trigger terms, creating high overlap risk with unrelated skills. It lacks an explicit "Use when" clause, so completeness is also weak.

Suggestions

Rewrite the description around the real purpose: beautifying meta-analysis forest plots, customizing odds-ratio point sizes/shapes and confidence-interval line styles, and producing subgroup analysis plots.

Add natural trigger terms a user would say, e.g. "forest plot", "meta-analysis", "odds ratio", "confidence interval", "subgroup analysis".

Append an explicit "Use when..." clause naming the concrete trigger situations (e.g. styling or beautifying a meta-analysis forest plot).

Dimension	Reasoning	Score
Specificity	Phrases like "Analyze data", "reproducible workflow", "explicit validation", and "structured outputs" name a generic domain but offer only abstract actions; none of the actual forest-plot capabilities (OR points, CI line styles, subgroup analysis) are described. It is above a 1 because it does name a domain, but below a 3 because no concrete domain-specific actions are listed.	2 / 5
Completeness	There is a vague "what" ("Analyze data with forest-plot-styler using a reproducible workflow...") but no "when" / "Use when..." trigger clause at all. This matches the anchor for a vague what with no when, and the missing explicit trigger guidance caps the score.	2 / 5
Trigger Term Quality	Only generic keywords ("data", "validation", "structured outputs", "review-ready") appear; the natural terms a user would say ("forest plot", "meta-analysis", "odds ratio", "confidence interval", "subgroup") are entirely missing. Matches the anchor of one or two generic keywords missing the natural phrases.	2 / 5
Distinctiveness Conflict Risk	"Analyze data ... reproducible workflow, explicit validation, structured outputs" applies to virtually any data-analysis skill and would trigger for many unrelated ones. It is very broad with high overlap risk, matching the anchor for a 2.	2 / 5
	Total	8 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 16 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/forest-plot-styler/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.