git:20260916.e88c124 to git:20260916.82e9975

---

name: academic-figure-figma

description: >-

Use when the user wants a paper figure (framework, pipeline, architecture,

method overview) drawn, rebuilt, or refined as an editable vector in Figma

via Claude Code — including reproducing a candidate/reference image

(e.g. studio-pro C01-C04) at exact print size. Also use when the user needs

to set up or fix the Claude Code-Figma connection: installing the Figma MCP

plugin, OAuth/authentication (incl. remote sessions), seat or quota problems,

"figma 连不上/怎么配置", or a first-run guided setup.

---

# Academic Figure in Figma (Claude Code)

Land a sketch, candidate image, or text description as an **editable, paper-exact

vector figure in Figma**, drawn directly through the Figma MCP server.

**Draw from this skill alone.** `references/figma-api-cheatsheet.md` +

`scripts/figma_lib.js` contain the complete verified API subset — do NOT load the

official figma-use skill, the Plugin API typings, or explore the API by trial: that

is the slow path this skill replaces. Icons come from the local cache first

(`scripts/assets/icons/icons.json`, pre-cleaned, injection-ready).

## Hard rules

1. **Correctness before aesthetics.** Grep the paper for every number, term, metric

name, and section reference the figure will carry; show the audit table before

drawing. Fix the reference image's errors, never reproduce them. Terminology must

match the paper canon verbatim; when the paper is inconsistent, ask the user to

pick. Never hard-code section numbers into a figure.

x/y, plus the component-reuse subset (createComponentFromNode / createInstance).

Auto Layout, variant sets, Variables, Styles are banned (cheatsheet §Allowed).

and shrink — fonts fall below the 6pt floor.

false relays, variables on edges not boxes, operation chains not just outcomes,

repeated entities compressed, mainline centred, restrained palette.

a brand mark on the proposed-model block. Screenshot every fetched logo before use

— CDNs mislabel (cache manifest records which marks are already verified).

loop, cheatsheet §Look, then say what changed). Before a mutating call, one line of

expected outcome in the `description`. Inside the call: `const before = snapshot(art)`

first, `diffLayout(before, snapshot(art))` in the return value, and

`await inspect(art, question, region?)` — a print-scale (8×) view of the artboard or

of one region, with the visual question it must answer. `get_screenshot` never

upscales, and a 1× render of a 236 pt figure hides every collision and padding defect

the reader will see (cheatsheet §Core facts). Check: text overflow, single-headed

arrows pointing with the flow, whitespace balance, terminology.

vectorNetwork nodes (never line+polygon fragments). Same-kind elements are

generated from one data table with STYLE tokens; end every session with

`auditFigure()` — structured lint for font floor, ink overflow, block

overlap, arrow-through-block, buried heads and style drift — and fix every

ERROR before asking the user to review.

**Chip heights are outputs, not inputs.** Size every chip from its text ink

via `fitChipToInk()` / `packBox()` (lib) so text can never overflow or be

occluded; hand-guessed fixed heights are banned, and any text change means

re-running `packBox` on that box before re-laying arrows — **in a fresh

call**: text metrics are stale within the call that edited the text, so

same-call packing and linting silently pass on real overlaps

(cheatsheet §Text fitting, stale-metrics trap).

Every symbol — `x_t`, a fraction, a norm, a tick numeral — goes through

`latex2svg.py` (fontset `cm`, the body's maths font) and is placed with `symbol()`

or cloned from the `masters-cm` frame, never rescaled (cheatsheet §Formulas,

style-contract §Type: measured on MoCo, MAE, iMF, JiT, BNF). `mathText()` only for

plain sub/superscripts inside a prose label. User-made formula components are

reused via `findAll` + `createInstance`, never redrawn.

figure is an image, put the real one there: `use_figma` cannot create a bitmap,

so the panels are frames whose fills arrive through the `upload_assets` MCP tool

(cheatsheet §Raster panels). Render each panel natively from the source script,

crop to the frame's aspect before upload, and upsample to `4.2 × pt` pixels —

NEAREST for masks, LANCZOS for everything else.

layer, so park the uploads once in a `masters-typeset` frame and place `master.clone()`

every time — `appendChild` on the master moves it, which silently strips the label from

whichever figure held it before.

read component colours with `scripts/extract_palette.py` (cheatsheet

§Reference colours): crop mode returns one component's fill/stroke/text trio,

probe mode the exact colour at a point. Override the lib `PAL` with the

measured hexes before drawing; same-role components share one measured colour.

write `guideTable(art)` (lib) into `figs/<figure>/GUIDE.md` — ids, names, coordinates,

fonts, fills — together with the decisions taken (why a label sits where it sits,

what the user rejected), and save every render as `renders/<figure>_v<NN>.png`,

never overwriting. A compacted context, or tomorrow's session, resumes from that

file in one read instead of re-deriving the layout from the canvas.

## Workflow

**First run / connection problems — guided setup.** If Figma MCP tools are missing,

auth fails, or whoami shows a View seat, switch to the five-step tutorial in

references/figma-mcp-setup.md (§Tutorial): Claude leads, verifies each step, and

returns here when drawing-ready.

**Step 0 — Preflight.** `whoami` (quota-exempt) → seat must be Full with a paid or

education plan, else run the setup tutorial first (references/figma-mcp-setup.md). Pick canvas width

from the venue (references/paper-canvas-specs.md). Produce the Step-0 correctness

`scripts/figma_lib.js` and the icon cache manifest now — every later call pastes the

lib verbatim at the top of its code.

**Step 1 — Skeleton (1 call).** Artboard at print width + all stage/panel containers

via `stageColumn()`; panel titles, dashed divider. Return every container id.

**Step 2 — Parallel fill (N calls, one message).** One call per container, following

references/parallel-drawing.md: paste lib, `await FONTS()`, fill chips/text/icons for

that container only (`chip()`, `txt()`, `placeSvg()` with cached icons). Fan out all

containers simultaneously; never touch siblings or globals.

**Step 3 — Assembly (1 call).** Arrows between stages (`arrowH`/`arrowV`, colour per

flow type), legend (`legendRow`), per-column balance (`balanceColumn`), artboard trim.

Keep the returned arrow ids for later adjustments — never re-find arrows by type.

**Step 4 — Review loop.** Screenshot at 2.5-3x AND re-read the reference image

side-by-side (structure being right is not enough — compare density, spacing,

error vocabulary at the end of references/figure-grammar.md. Independent fixes may fan out again.

Stop when clean; ask the user to review in Figma at 100% zoom; user exports PDF — run the

font-compliance check (references/build-workflow.md §Venue font compliance) before handing it over.

## References

| File | Load when |

|---|---|

| references/figma-api-cheatsheet.md | before writing the first use_figma call (always) |

| references/parallel-drawing.md | at Step 2 |

| references/paper-canvas-specs.md | at Step 0 (canvas + fonts + palette numbers) |

| references/figure-grammar.md | at Step 0 planning and Step 4 review |

| references/figure-styles.md | picking or switching a figure's style/palette: named presets, construction rules, sampler-board + hex-map workflow |

| references/style-contract.md | at Step 0 for the numbers (palette, type, strokes, spacing, banned tells) and at Step 4 as the checklist; measured from five He Kaiming figures and three flagship inverse-problem papers |

| references/icon-sourcing.md | only when an icon is NOT in the local cache |

| references/figma-mcp-setup.md | connection/quota problems only |

| references/build-workflow.md | deep dives: balancing math, pitfalls, export + venue font compliance |