figure-spec
Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that hits all the key criteria. It provides specific concrete actions, comprehensive bilingual trigger terms, explicit 'Use when' guidance, and clear differentiation from related skills like AI illustration. The description is concise yet information-dense, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG.' This clearly describes the input format (JSON/FigureSpec), output format (editable SVG), and the types of diagrams supported. | 3 / 3 |
Completeness | Clearly answers both 'what' (generate deterministic publication-quality diagrams from FigureSpec JSON into editable SVG) and 'when' (explicit 'Use when' clause with specific trigger phrases, plus a differentiation note about when to prefer this over AI illustration). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including bilingual keywords: '架构图', 'workflow 图', 'pipeline 图', '确定性矢量图', 'figure spec', 'draw architecture', plus descriptive phrases like 'publication-ready vector diagrams' and 'editable'. Covers both Chinese and English user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: deterministic diagrams from structured JSON (FigureSpec) into SVG. The explicit contrast 'Preferred over AI illustration for formal architecture/workflow figures' further disambiguates it from general drawing or illustration skills. | 3 / 3 |
Total | 12 / 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, actionable skill with excellent workflow clarity and concrete executable examples. Its main weakness is moderate verbosity—the 'When to Use' negative list, 'Core Properties' section, and inline schema reference could be trimmed or split into separate files. The design patterns and anti-patterns sections add genuine value but contribute to a lengthy single file that would benefit from progressive disclosure.
Suggestions
Move the schema quick reference table and design patterns/anti-patterns into a separate REFERENCE.md file, linking from the main skill with a one-line summary.
Trim the 'Core Properties' section—Claude doesn't need to be told the renderer is deterministic and validated; these are implicit from the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary sections like 'When to Use This Skill' with negative examples that could be trimmed, and the 'Core Properties' section explains things Claude can infer. The anti-patterns and design patterns sections add value but could be more compact. | 2 / 3 |
Actionability | Provides fully executable bash commands, concrete JSON templates for multiple diagram types, a complete schema reference table, and specific file paths. The workflow steps include copy-paste ready code blocks and clear validation commands. | 3 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced with explicit validation checkpoints (Step 3: validate first, then render; Step 4: visual review checklist; Step 5: iterative review with scoring thresholds). There's a clear feedback loop: if validation fails, fix JSON and re-render; if visual issues found, edit spec (never SVG) and re-render. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a long monolithic file (~200 lines) with inline schema reference tables and design patterns that could be split into separate reference files. References to external files (shared-references/review-tracing.md, tools/) exist but no bundle files are provided to verify them. | 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
2028ac4
- 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.