reqwise-figma-mcp: Skill for Claude Code

.claude/skills/figma-erd/SKILL.md

figma-erd is a skill for Claude Code from hoangpm96/reqwise-figma-mcp. It costs 52 tokens per session (2,307 once invoked), scanned A, original, MIT.

A Figma entity-relationship diagram, or ERD, showing database tables, important columns, keys, and how records relate. It also shows how many records on each side of a relationship are allowed.

In plain words
What is it for?
Use it to plan or review tables and relationships before building a database or changing its schema.
Why use it?
It makes a data model reviewable without reading a database migration. It can expose missing keys, incorrect relationships, and links that do not match the real schema.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

This is hoangpm96/reqwise-figma-mcp's own configuration. It tells Claude Code how to work on reqwise-figma-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything reqwise-figma-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hoangpm96/reqwise-figma-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hoangpm96/reqwise-figma-mcp/main/.claude/skills/figma-erd/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hoangpm96/reqwise-figma-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for figma-erd

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-erd/github.svg)](https://agentmods.dev/skills/hoangpm96/reqwise-figma-mcp/figma-erd)
Your own site
<a href="https://agentmods.dev/skills/hoangpm96/reqwise-figma-mcp/figma-erd"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-erd/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for figma-erd

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangpm96/reqwise-figma-mcp/figma-erd"><img src="https://agentmods.dev/badge/skills/hoangpm96/reqwise-figma-mcp/figma-erd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.02307
Opus 5 $0.00026 $0.01154
Sonnet 5 $0.00010 $0.00461
Haiku 4.5 $0.00005 $0.00231

Measured 4d ago against content hash 2eba20b47301, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-22, from the pricing page.

Security

Grade A, and why

figma-erd scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/figma-erd/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/figma-erd — What we store, and how it joins

Read ../reqwise-diagram-rules.md first — connection gate, the four levels of correct, the findings loop, frame placement, verification. This file carries only what is specific to an ERD.

Goal

Make the data model reviewable by people who will not read a migration. Tables, the columns that matter, and — the part that is usually wrong — which column joins to which, and how many of each side.

Output: one Figma frame ERD · <title>, plus the model problems it exposed.

Constraints

Hard rules — never violate

  • Name the columns on every relation. fromField and toField are what make the line attach to the row that actually implements the relationship, and what lets a reader check the picture against the schema. A relation without them is a decorative line.
  • Every table gets a primary key unless it is external: true (a table another system owns). The tool reports the ones that do not.
  • Use the real names. loan_applications, customer_id — the names in the database or the ones the team has agreed to use. A pretty diagram with invented names is worse than no diagram, because someone will code against it.
  • Pick one naming convention and hold it. snake_case or camelCase, not both. Mixing them is reported, and it is reported because it is always a merge of two people's work that nobody reconciled.
  • Never invent a column to make a join work. A relation naming a column that does not exist is a finding about the model, not a typo to paper over.

Write it in the compact form

text is a table, then its indented columns, then the relations. Unlike mermaid's erDiagram, the relation line names the columns on both sides — which is the whole point of an ERD line and the thing that makes it checkable against the schema.

users happy / core.auth          # class, and a detail line after "/"
  id uuid pk!                    # ! = NOT NULL
  email varchar(255)!
  created_at timestamptz
bookings
  id uuid pk!
  user_id uuid fk!
  status varchar(16)!
booking_seats                    # the join table, spelled out
  booking_id uuid pfk!
  seat_id uuid pfk!
psp_transactions ext / owned by the payment gateway
  reference varchar(64)!
  booking_id uuid fk!
users.id 1-* bookings.user_id "books"
bookings.id 1-? psp_transactions.booking_id "paid by"    # ? = zero-one, so it is optional
bookings.id 1=+ booking_seats.booking_id "holds"      # = identifying, + one-many

Read the full file on GitHub · 185 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 185 lines · 52 tokens per session scan A 2eba20b47301

Subscribe to this mod's changes

figma-erd is a skill published in the GitHub repository hoangpm96/reqwise-figma-mcp (65 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,307 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-18.

Related

Other skills, from other repositories

dotcanvas

Author and edit a Grida .canvas board — a .canvas.json manifest plus document files (references, generated images, notes) placed on an infinite canvas. Use when working on a .canvas bundle or arranging visuals/design work spatially. For a linear deck/presentation, use the slides skill instead.

gridaco/grida · 69 tokens

slides

Build a Grida slides deck — a .canvas bundle in slides mode whose pages are SVG documents (16:9, one SVG per slide). Use when creating a presentation, pitch deck, slideshow, or talk.

gridaco/grida · 46 tokens

datamodellm

Create visual data models for database schemas using Nimbalyst's DataModelLM editor. Use when the user wants to design a data model, database schema, entity relationship diagram, or Prisma schema.

nimbalyst/nimbalyst · 45 tokens

svg

Author and edit .svg files in a Grida editor session — live-canvas binding, SVG output style, and parse-error recovery. Use when creating or modifying an SVG document.

gridaco/grida · 39 tokens

er-diagrams

Create animated entity-relationship and database schema diagrams using the Excalimate MCP server. Use when asked to visualize database schemas, data models, table relationships, foreign keys, entity relationships, or any structured data design with tables and their connections.

excalimate/excalimate · 52 tokens

dashboard-design

Design and code a self-contained HTML dashboard for DeepSQL — ground on the schema, verify SQL, then emit it as a shell plus one verified widget block at a time so the canvas builds progressively.

DeepSQLAI/deepsql · 43 tokens