paper-figure
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 solid description with strong trigger terms (including bilingual coverage) and a clear 'Use when' clause that explicitly defines activation conditions. The main weakness is that the 'what' portion could be more specific about the types of figures and tables it can generate. Overall, it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions, e.g., 'Generate bar charts, line plots, heatmaps, scatter plots, and formatted statistical tables from experiment results' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (publication-quality figures and tables from experiment results) and a general action (generate), but doesn't list multiple specific concrete actions like 'create bar charts, scatter plots, heatmaps, format tables with statistical annotations'. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate publication-quality figures and tables from experiment results) and 'when' (explicit 'Use when' clause with specific trigger phrases and a contextual condition). | 3 / 3 |
Trigger Term Quality | Includes both Chinese ('画图', '作图') and English ('generate figures', 'paper figures') natural trigger terms, plus the contextual trigger 'plots for a paper'. Good coverage of terms users would actually say. | 3 / 3 |
Distinctiveness Conflict Risk | The focus on publication-quality figures from experiment results, combined with bilingual trigger terms and the academic paper context, creates a clear niche that is unlikely to conflict with general plotting or data visualization skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with executable code examples, a clear multi-step workflow, and thorough quality validation. Its main weaknesses are moderate verbosity (duplicate reference tables, some unnecessary explanations) and a monolithic structure that could benefit from splitting detailed examples into separate referenced files. The fictional REVIEWER_MODEL (gpt-5.4) is a minor concern but doesn't significantly impact usability.
Suggestions
Remove the duplicate Figure Type Reference table at the bottom since it largely repeats the Auto-Select table in Step 3
Consider splitting detailed code templates (bar chart, line plot, table examples) into a separate TEMPLATES.md file referenced from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy — the Figure Type Reference table at the bottom largely duplicates the Auto-Select Figure Type table in Step 3. The Scope table, while useful, is somewhat verbose with explanations Claude doesn't need (e.g., explaining what GAN outputs are). The Constants section includes a fictional 'gpt-5.4' model. Overall moderately efficient but could be tightened. | 2 / 3 |
Actionability | Excellent actionability with fully executable Python code for line plots, bar charts, and style configuration. LaTeX snippets are copy-paste ready. The bash script for running all generators is concrete. Data loading patterns, save utilities, and complete matplotlib rcParams are all provided as working code. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced from reading the figure plan through generation, LaTeX inclusion, review, and quality checklist. Step 5 includes verification that outputs exist. Step 7 provides a review/feedback loop. Step 8 is an explicit quality checklist with validation criteria. The workflow handles both auto-generated and manual figures with clear branching. | 3 / 3 |
Progressive Disclosure | The content is entirely self-contained in one file with no references to supplementary documents for advanced topics. At ~200+ lines, some content (like the full code examples for each figure type, or the detailed LaTeX table template) could be split into referenced files. The structure within the file is well-organized with clear headers, but it's a long monolithic document. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Commit
dc00dfb
- 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.