graph-interpretation
Use when interpreting scientific graphs and charts, explaining data visualizations for research presentations, writing figure captions for publications, or analyzing trends in clinical research data. Converts complex visual data into clear, accurate explanations for academic papers, clinical reports, and public presentations.
53
59%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/graph-interpretation/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific capabilities and includes an explicit 'Use when' clause with natural trigger terms. The description effectively combines the what and when, using domain-specific language that researchers would naturally use. The only minor weakness is potential overlap with broader data analysis or scientific writing skills, though the focus on visual data interpretation for scientific/clinical contexts provides reasonable distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: interpreting scientific graphs/charts, explaining data visualizations, writing figure captions, analyzing trends in clinical research data, and converting visual data into explanations for academic papers/clinical reports/presentations. | 3 / 3 |
Completeness | Clearly answers both what (interpreting graphs, explaining visualizations, writing figure captions, analyzing trends, converting visual data into explanations) and when (explicit 'Use when' clause at the beginning with specific trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'scientific graphs', 'charts', 'data visualizations', 'figure captions', 'publications', 'clinical research data', 'academic papers', 'clinical reports', 'research presentations'. These cover a good range of terms a researcher would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | While it carves out a niche in scientific/clinical data visualization interpretation, there could be overlap with general data analysis skills, scientific writing skills, or chart interpretation skills. The clinical research focus helps but doesn't fully eliminate conflict risk. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from extreme verbosity, with the description copy-pasted into multiple sections and large amounts of generic boilerplate that Claude already knows. While it contains some useful domain-specific content (graph type tables, audience-specific explanation templates, statistical reporting standards, common pitfalls), this is buried under repetitive scaffolding. The code examples reference non-existent modules with no bundle support, making them illustrative rather than executable.
Suggestions
Remove all generic boilerplate sections (Output Requirements, Error Handling, Input Validation, Response Template, Input Validation) that teach Claude things it already knows, and eliminate the repeated description copy-pasted into 'When to Use' and 'Key Features'.
Either provide actual bundle files (scripts/graph_interpreter.py, references/) or remove references to them and restructure as a pure instruction skill with concrete guidance rather than fake API examples.
Split the domain-specific reference content (graph type tables, audience templates, statistical reporting standards) into separate reference files and keep SKILL.md as a concise overview with navigation links.
Replace the generic 5-step workflow with graph-interpretation-specific steps, e.g.: 1) Identify graph type, 2) Extract key statistical measures, 3) Assess visual integrity (axis scaling, error bars), 4) Generate audience-appropriate explanation, 5) Validate statistical claims against visible data.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. The description is copy-pasted into multiple sections (When to Use, Key Features). Massive amounts of boilerplate (Output Requirements, Error Handling, Input Validation, Response Template) that Claude already knows. The 'Implementation Details' section says 'See Workflow above' then repeats generic guidance. Many sections explain obvious concepts and the skill is far longer than needed for its purpose. | 1 / 3 |
Actionability | Contains code examples that look executable (Python API calls, CLI commands), but they reference modules (scripts/graph_interpreter.py, GraphInterpreter class) that don't exist in any bundle. The code is essentially pseudocode dressed as real code—none of it is verifiable or copy-paste ready. The CLI examples and Python API are illustrative but not grounded in actual implementations. There's a syntax error in Pattern 3 ('clinical Utility=True'). | 2 / 3 |
Workflow Clarity | The Workflow section provides a 5-step sequence and the Quality Checklist provides before/during/after checkpoints, which is decent. However, the workflow steps are generic and abstract ('Confirm the user objective', 'Validate that the request matches the documented scope') rather than specific to graph interpretation. There are no concrete validation commands specific to the domain, and the error recovery is generic boilerplate. | 2 / 3 |
Progressive Disclosure | The skill is a monolithic wall of text with no bundle files to support it. It references 'references/' directory and 'scripts/main.py' but no bundle files exist. Everything is inlined in one massive document (~300+ lines) with no actual external references. The content that could be split (graph type tables, audience templates, common patterns) is all crammed into the single file. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aipoch/medical-research-skills
- Commit
73f6514
- 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.