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

89%

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

Quality

Content

88%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 highly actionable, well-structured skill body with concrete templates, schema reference, and a validated multi-step workflow. The main weakness is verbosity in the tool-location resolver and references to out-of-bundle shared files.

Suggestions

Trim the "Tool Location" history (e.g. "Phase 3.1 (Arch C) move") and collapse the 4-layer resolver into a shorter chain with the fallback detail moved to a referenced doc.

Make the two ../shared-references/ links (integration-contract.md, review-tracing.md) clearly external/optional, or inline the minimal needed contract so the skill is self-contained.

Move the full Nodes/Edges/Groups schema table into a separate REFERENCE.md, leaving only the most-used fields inline to reduce SKILL.md token load.

Dimension	Reasoning	Score
Conciseness	Mostly lean and assumes Claude's competence (no padding about what SVG/JSON is), but the "Tool Location" section carries implementation-history noise ("Phase 3.1 (Arch C) move") and a lengthy 4-layer resolver chain that could be trimmed.	4 / 5
Actionability	Copy-paste ready commands ("python3 \"$FIGURE_RENDERER\" render/validate/schema"), concrete JSON templates for each diagram type, and a full schema table with defaults and notes cover the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced steps with an explicit "Validate first" checkpoint, a fix-and-re-render feedback loop, a visual-review checklist, and a Codex iterate-until-≥7 recovery loop.	5 / 5
Progressive Disclosure	Well-organized sections with a confirmed bundle file (scripts/figure_renderer.py) and mostly one-level-deep references; two references point to ../shared-references/ outside the bundle, slightly muddying navigation.	4 / 5
	Total	18 / 20 Passed

Description

91%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, third-person description that clearly states capability and trigger conditions with rich bilingual keywords. It is comprehensive on triggers and completeness, with only minor room to sharpen the distinctiveness framing relative to sibling diagram skills.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete outputs ("Generate ... architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG") but is essentially one verb applied to several diagram kinds rather than multiple distinct actions, so it sits below the comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both "what" (generate deterministic publication-quality diagrams from JSON into SVG) and "when" ("Use when user says ..."), with concrete trigger phrases matching the anchor 5 example.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including bilingual synonyms ("架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture") that a user would plausibly say.	5 / 5
Distinctiveness Conflict Risk	Clear niche (deterministic JSON→SVG architecture/workflow figures) reinforced by "Preferred over AI illustration for formal architecture/workflow figures"; minor overlap risk with related diagram skills not named in the description itself.	4 / 5
	Total	18 / 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: 0472e53

Reviewed: 5 days 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.