Name: figma-generate-diagram
Rating: 88.2 (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

84%

Does it follow best practices?

Impact

97%

1.51x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

78%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 routing skill with clear step sequencing and effective progressive disclosure via verified reference files. It is slightly verbose in the judgment/guidance prose, and the body lacks a complete end-to-end tool-call example and an explicit post-generation validation step.

Suggestions

Add one complete example generate_diagram call (with name, mermaidSyntax, and a small flowchart) so the body is copy-paste ready end-to-end, not just in fragments.

Tighten Step 4's context-source bullets and Step 5's yes/no signal lists to reduce prose without losing the judgment guidance.

Add an explicit post-generation validation step (e.g., open the returned link and confirm the diagram rendered correctly before iterating) to complement the dissatisfaction feedback loop.

Dimension	Reasoning	Score
Conciseness	Efficient and free of padding about concepts Claude already knows; it assumes competence throughout. Step 4's context-gathering list and Step 5's yes/no signal lists are purposeful but could be trimmed slightly to be leaner.	4 / 5
Actionability	Concrete, executable guidance throughout—Mermaid label examples (A["Process (main)"], -->\|"O(1) lookup"\|), exact tool parameters (name, mermaidSyntax, fileKey, useArchitectureLayoutCode), and a specific figma.createPage error string. Minor gap: no complete end-to-end generate_diagram call example in the body, with full recipes deferred to references.	4 / 5
Workflow Clarity	Steps 1–7 are clearly sequenced with a constraints checklist (Step 3), a context quality gate (Step 4), and a dissatisfaction feedback loop (Step 7, stop after 2 attempts). Minor gap: no explicit post-generation validation step beyond user feedback.	4 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references; the routing table links to per-type reference files (architecture, flowchart, sequence, erd, state, gantt, workflow) that all exist on disk, and per-type detail is appropriately split out of the body.	5 / 5
	Total	17 / 20 Passed

Description

90%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, highly specific description with comprehensive trigger terms, explicit what-and-when guidance, and low conflict risk. The main defect is second-person voice ('tells you', imperative 'load this skill') which the rubric penalizes on specificity, plus the core generation outcome is implied rather than stated.

Suggestions

Convert to third-person voice: replace 'tells you when to use...' with 'advises when to use...' and rephrase the opening imperatives ('load this skill BEFORE every...') as descriptive third-person statements to avoid the specificity penalty.

State the core outcome explicitly as an action (e.g., 'produces editable FigJam diagrams from Mermaid syntax via the generate_diagram tool') so the 'what' is not only implied by the prerequisite framing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (routes to type-specific guidance, sets universal Mermaid constraints, advises on type selection/skipping) but uses second-person voice ('tells you when to use...') and opening imperatives ('load this skill'), which the rubric penalizes by reducing specificity by 1; the core generation outcome is also left implicit rather than stated as an action.	3 / 5
Completeness	Explicitly answers both what (routes to guidance, sets constraints, advises on type/skip) and when (user asks to create/generate/draw a diagram, mentions Mermaid, wants something visualized in FigJam) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms (ERD/entity-relationship, state diagram/state machine) and varied user phrasings (create, generate, draw, render, sketch, build) across many diagram types, plus Mermaid syntax and FigJam.	5 / 5
Distinctiveness Conflict Risk	Tightly scoped to the generate_diagram tool and FigJam/Mermaid with specific diagram-type triggers, giving it a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 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
Path: skills/figma-generate-diagram/SKILL.md
Commit: ae7e5e5

Reviewed: 6 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.