Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Figma Slop Check

    1

    Gate for Figma frames after a write: slop and rigor checks, then PASS or a numbered punch list by node id.

    Free

    2 usesSecurity scanned

    About this skill

    Quality gate for a Figma file, run after a write and before figma-handoff-gate. No frame is called done while a check fails. It reads the file and reports PASS, or a numbered punch list by node id where each finding carries a severity and an action (swap, snap or ask). Rigor findings stay read-only until the user approves them.

    What it checks:

    • Slop, 8 checks (S1 to S8): overlap and spacing, AI-stuffed cards, status marker creep, names and canvas notes that read as generated, decorative excess, mechanical repetition, hype copy, and the closing reply.
    • Rigor, 11 checks in 5 groups: bound or loose (color, text style, scale), components intact, auto layout sized right, words (glossary wording, layer names), and screenshot proof.
    • The 5 auto-fails and the 0-10 score of the figma-canon quality rubric, 8/10 minimum.

    Requires the figma-canon skill installed next to it (it links to ../figma-canon/references/). Written for figma-console-mcp with the Desktop Bridge plugin in Figma Desktop; not validated on the official Figma MCP server.

    Part of figma-maxxing, free and MIT on GitHub: https://github.com/thiagoxikota/figma-maxxing

    Not validated on the official Figma MCP server; the checks are written for figma-console-mcp and its Desktop Bridge plugin. The repo README reports one demo run on that server, made with the rigor lens from before 1.2.0, which rewrote it as the current 11 checks. Depends on figma-canon for the slop catalog, quality rubric, naming, state and handoff canon. Scales, glossary and naming rules come from the project's variables, styles and figma-map.md; the numbers in references/checks.md are placeholders, and a case no source covers is reported as ask. With two or more variable modes, values are read in the current mode only. Accessibility beyond the catalog's auto-fails and layout strategy are out of scope. If the Bridge is disconnected it stops and hands off to figma-bridge-doctor, a separate skill. After 3 fix and re-check cycles on the same failing check it stops and surfaces the problem.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    2 uses

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Requires

    Figma
    Figma Console MCP

    Permissions

    Read Files
    Write Files

    Allowed Hosts

    api.figma.com

    File Scopes

    docs/figma-map.md
    .figma-slop-check/decisions.json
    .figma-slop-check/runs/*.json
    ../figma-canon/references/*.md

    The skill folder holds Markdown only (SKILL.md, references/checks.md, references/punch-list.md) and ships no scripts. It makes no network calls and reads no environment variables itself; Figma is reached through the agent's figma-console-mcp tools. It reads the project map (default docs/figma-map.md) and the figma-canon references. It writes one run record per screen to .figma-slop-check/runs/<YYYY-MM-DD>-<screen-slug>.json and keeps accepted deviations in .figma-slop-check/decisions.json. Canvas changes happen only for fixes the user approves, each routed through figma-preflight, plus slop failures on work the agent just made, which it is told to fix before answering.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Rigor findings stay read-only until you approve them by number, for example "fix 2" or "fix all high", and only those items are applied, each one through figma-preflight. The exception is a slop failure on work the agent just made: the skill tells the agent to fix it before answering.

    An agent connected to Figma through figma-console-mcp, with the Desktop Bridge plugin running in Figma Desktop, and the figma-canon skill next to this one. The slop catalog, the quality rubric and the naming canon live in figma-canon's references.

    Tell the agent it is intentional. It records an entry in .figma-slop-check/decisions.json with a reason and a node scope, and the next run leaves that finding out of the punch list. Saying "later" records it as debt instead, and it comes back with its distance until it is fixed.

    New in Branding & Design

    Free