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.

Quality

76%

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 ./skills/figure-spec/SKILL.md

Quality

Content

73%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.

A well-structured, actionable skill body with a clear validated workflow and good delegation of detail to the bundled renderer script. The main drag on conciseness is the verbose tool-resolution bash block inlined in the body.

Suggestions

Move the multi-layer $FIGURE_RENDERER resolution bash block into a small helper script or a reference file, keeping only the canonical $CLAUDE_SKILL_DIR path and a one-line fallback pointer inline.

Make the architecture JSON template fully copy-paste-ready (replace the '...' ellipses with concrete node fields) so all three templates are executable as-is.

Tighten repeated reminders that $FIGURE_RENDERER 'was resolved in Tool Location above' to a single note, since the variable is already established.

Dimension	Reasoning	Score
Conciseness	The body largely assumes Claude's competence (no basic-concept padding) and uses tight tables, but the ~40-line $FIGURE_RENDERER resolver bash block and its long inline error message are verbose operational detail that could be tightened or moved to a reference, so it is 'mostly efficient but could be tightened'.	3 / 5
Actionability	Provides concrete executable commands (render/validate/schema), rsvg-convert, and complete JSON templates plus a schema table; the architecture template uses '...' ellipses rather than a fully copy-paste-ready example, leaving a minor gap.	4 / 5
Workflow Clarity	Five sequenced steps with an explicit 'Validate first' checkpoint, feedback loops ('If validation fails ... fix the JSON', 'edit the JSON spec ... and re-render'), and a visual-review checklist match the 'clear sequence with explicit validation and feedback loops' anchor.	5 / 5
Progressive Disclosure	Well-organized sections and the authoritative schema is delegated to the script via `python3 "$FIGURE_RENDERER" schema`, with one-level-deep signaled references; the inlined resolver block and references to external shared-references not present in this skill's own bundle are minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

78%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 strong description that clearly states what the skill does and when to use it, with comprehensive bilingual trigger terms and explicit distinctiveness guidance. The only weakness is that it frames a single core action rather than enumerating several concrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain (architecture/workflow/pipeline diagrams) and one concrete action ('Generate ... diagrams from structured JSON (FigureSpec) into editable SVG'), but does not list several distinct actions, so it stops at '1-2 concrete actions' rather than comprehensive coverage.	3 / 5
Completeness	Explicitly answers both 'what' ('Generate deterministic ... diagrams from structured JSON into editable SVG') and 'when' ('Use when user says ...') with concrete trigger phrases, matching the 'clearly and explicitly answers both' anchor.	5 / 5
Trigger Term Quality	Includes a rich, bilingual set of natural triggers ('架构图', 'workflow 图', 'pipeline 图', 'draw architecture', 'figure spec', '确定性矢量图') with synonyms, giving good keyword coverage; a few common natural terms (e.g. 'flowchart', 'block diagram', 'system diagram') are absent so it is not fully comprehensive.	4 / 5
Distinctiveness Conflict Risk	The clause 'Preferred over AI illustration for formal architecture/workflow figures' carves out a clear niche and lowers conflict risk; minor overlap remains with lighter flowchart skills (e.g. mermaid), keeping it just below the 'minimal conflict risk' anchor.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/figure-spec/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.