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

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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-sequenced skill body with strong validation feedback loops, but it is somewhat verbose in the tool-resolution/legacy sections and leans on dangling shared-references paths plus inline schema material that would benefit from separation.

Suggestions

Tighten or move the multi-layer Tool Location resolution chain and Review Tracing narrative to a reference file, keeping only the canonical $CLAUDE_SKILL_DIR path inline; this would lift conciseness toward 3.

Resolve the dangling references — `../shared-references/integration-contract.md` and `shared-references/review-tracing.md` do not exist in the bundle; either create them, point to real files under references/, or remove the citations.

Split the inline Schema Quick Reference (Nodes/Edges/Groups tables) and Design Patterns into a `references/` file (e.g. SCHEMA.md / PATTERNS.md) linked from the body, improving progressive disclosure toward the score-3 one-level-deep pattern.

Dimension	Reasoning	Score
Conciseness	Most of the body is efficient (templates, schema tables, patterns), but the four-layer "Tool Location" legacy-compatibility resolution chain and the Review Tracing narrative carry detail that could be tightened, matching the score-2 anchor of mostly efficient with some unnecessary explanation. It is not score 3 because not every token earns its place, and not score 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	It provides copy-paste-ready commands ("python3 \"$FIGURE_RENDERER\" render <spec.json> --output <out.svg>", validate, schema), complete JSON templates per diagram type, and a field/defaults schema table, matching the score-3 anchor of fully executable guidance.	3 / 3
Workflow Clarity	A clear 5-step sequence includes an explicit validate-first checkpoint in Step 3 ("If validation fails, inspect the error...and fix the JSON") and a visual-review feedback loop in Step 4, matching the score-3 anchor of explicit validation steps with error-recovery feedback.	3 / 3
Progressive Disclosure	The body is well-sectioned and fetches the authoritative schema on demand via command, but it inlines a large Schema Quick Reference table plus Design Patterns/Anti-Patterns that could be split out, and cites `../shared-references/integration-contract.md` and `shared-references/review-tracing.md` which do not exist as bundle files — matching the score-2 anchor of some structure with content that should be separate inline and unclear signaling.	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.

A strong, third-person description that states concrete capabilities, supplies natural bilingual trigger terms, and gives explicit use-when guidance with a distinctiveness aid. It satisfies the what/when/specificity/trigger criteria cleanly.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Generate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG" — matching the score-3 anchor of naming several specific actions rather than vague language.	3 / 3
Completeness	It answers both 'what' (JSON→SVG diagram generation) and 'when' via an explicit "Use when user says..." clause, matching the score-3 anchor for explicit triggers; the 'when' is not merely implied.	3 / 3
Trigger Term Quality	It supplies natural terms a user would actually say ("架构图", "workflow 图", "pipeline 图", "figure spec", "draw architecture"), with good bilingual coverage matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (deterministic editable SVG diagrams) and adds "Preferred over AI illustration for formal architecture/workflow figures", making conflict with adjacent skills unlikely — matching the score-3 anchor.	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
Commit: 82076e5

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.