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

88%

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

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a well-sequenced, validated workflow, but is somewhat verbose and keeps reference-grade material inline rather than splitting it into separate files. Tightening the resolver and moving patterns to references would raise conciseness and progressive disclosure.

Suggestions

Move the multi-layer `$FIGURE_RENDERER` resolution bash into a `scripts/resolve_renderer.sh` helper (or a short reference) and drop the internal migration notes ("Phase 3.1 (Arch C) move", shim details) from the user-facing body to improve conciseness.

Extract Design Patterns, Anti-Patterns, and the Schema Quick Reference tables into a `references/` file (e.g. `references/patterns.md`) linked from SKILL.md, keeping the body an overview to strengthen progressive disclosure.

Clarify or remove references to bundle-absent shared files (`shared-references/integration-contract.md`, `shared-references/review-tracing.md`) so referenced paths resolve within this skill's own bundle.

Dimension	Reasoning	Score
Conciseness	The body is mostly action-oriented and avoids explaining basics Claude knows, but carries unnecessary migration context ("Phase 3.1 (Arch C) move", "backwards-compatible shim ... os.execv") and a dense ~25-line resolver chain that could live in a referenced script; not quite lean enough for a 3.	2 / 3
Actionability	It provides copy-paste-ready commands (`python3 "$FIGURE_RENDERER" render/validate/schema`), complete JSON templates for architecture/workflow/decision diagrams, and schema field tables — fully executable guidance.	3 / 3
Workflow Clarity	A clear 5-step sequence (Understand → Draft → Render/Validate → Visual Review → Iterate) with an explicit "Validate first" checkpoint, error-recovery guidance, a visual-review checklist, and a convergence criterion (≥7/10) for the review loop.	3 / 3
Progressive Disclosure	The real bundle `scripts/figure_renderer.py` is referenced and the authoritative schema is delegated to a command, but the ~250-line body keeps design patterns, anti-patterns, and the full resolver inline, and references shared files (`shared-references/integration-contract.md`, `review-tracing.md`) absent from this skill's bundle.	2 / 3
	Total	10 / 12 Passed

Description

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.

The description is specific, trigger-rich in both English and CJK, and explicitly answers both what and when, with a clear niche statement. It is a strong, well-scoped skill description.

Dimension	Reasoning	Score
Specificity	"Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG" lists multiple concrete actions (generate, render JSON→SVG, support architecture/workflow/pipeline) with a specific input format and output, matching the score-3 anchor.	3 / 3
Completeness	It states what the skill does (generate diagrams from FigureSpec JSON into SVG) and an explicit "Use when user says ..." clause covering when to invoke it, clearly answering both what AND when.	3 / 3
Trigger Term Quality	Explicit triggers "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture" cover natural CJK and English phrasing a user would actually say, satisfying the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	"Preferred over AI illustration for formal architecture/workflow figures" plus diagram-type-specific triggers carve a clear niche unlikely to fire for plotting or qualitative-illustration skills.	3 / 3
	Total	12 / 12 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: c5f3d5b

Reviewed: 11 minutes 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.