Name: figma-generate-diagram
Rating: 98.6 (1 reviews)
Author: figma

figma-generate-diagram

MANDATORY prerequisite — load this skill BEFORE every `generate_diagram` tool call. NEVER call `generate_diagram` directly without loading this skill first. Trigger whenever the user asks to create, generate, draw, render, sketch, or build a diagram — flowchart, architecture diagram, sequence diagram, ERD or entity-relationship diagram, state diagram or state machine, gantt chart, or timeline. Also trigger when the user mentions Mermaid syntax or wants a system architecture, decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline visualized in FigJam. Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely (mindmaps, pie charts, class diagrams, etc.).

1.51x

Quality

—

Does it follow best practices?

Impact

97%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

100%

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

The body is well-structured, actionable, and concise: a numbered workflow with decision gates, concrete Mermaid constraints, and clean progressive disclosure to per-type reference files that all exist. It avoids teaching concepts Claude already knows and provides explicit error-recovery guidance.

Dimension	Reasoning	Score
Conciseness	Lean and operational throughout: it assumes Claude knows what Mermaid and diagram types are and spends its tokens on constraints, routing, and decision rules rather than concept explanation, so every section earns its place.	3 / 3
Actionability	Gives concrete, executable guidance — specific Mermaid constraints (no emojis, no \n, camelCase IDs, quoted special chars, reserved words), an explicit routing table, and exact tool parameters with copy-ready values like `figma.com/board/{fileKey}/...`.	3 / 3
Workflow Clarity	A clear 7-step sequence with explicit gating checkpoints (Step 1 "Is generate_diagram the right tool?", Step 5 hybrid decision) and a feedback loop in Step 7 (stop after 2 failed attempts and ask what is wrong), satisfying the anchor for clear sequencing with error-recovery guidance.	3 / 3
Progressive Disclosure	The body is an overview that routes to one-level-deep, clearly signaled references (architecture.md, flowchart.md, sequence.md, erd.md, state.md, gantt.md, workflow.md), all of which exist in ./references/; content is appropriately split with easy navigation.	3 / 3
	Total	12 / 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 high-quality description: it states concrete actions, gives broad and natural trigger terms, answers both what and when explicitly, and is tightly scoped to one tool. It uses imperative rather than first/second-person voice, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Routes to type-specific guidance, sets universal Mermaid constraints, and tells you when to use a different diagram type or skip the tool entirely" — alongside named diagram types, matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ("Routes to type-specific guidance, sets universal Mermaid constraints...") and when ("Trigger whenever the user asks to create, generate, draw...") with an explicit trigger clause equivalent to "Use when...".	3 / 3
Trigger Term Quality	Covers natural user phrasing broadly: "create, generate, draw, render, sketch, or build a diagram," plus "flowchart, architecture diagram, sequence diagram, ERD... gantt chart, or timeline," "Mermaid syntax," "decision tree, dependency graph, API call flow, auth handshake, schema, or pipeline" — strong coverage of terms users would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche tied to the `generate_diagram`/FigJam tool with a "MANDATORY prerequisite... load this skill BEFORE every generate_diagram tool call," making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: figma/mcp-server-guide
Commit: c7c92a1

Reviewed: 2 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.