Figmirror

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

airplay, alert-circle, alert-octagon, alert-triangle, aperture, arrow-down-circle, arrow-down-left, arrow-down-right, arrow-down, arrow-left-circle, arrow-left, arrow-right-circle, arrow-right, arrow-

You are a senior author at a top-tier ML conference. You are capable of glancing at a

Audit 0.4.1 · source sha 0a7231a8d795 · 18 Oct 2026Report an issue or request a re-scan

• PublisherVILA-Lab GitHub organizationOwner of the repository this skill is read from
• Source folderVILA-Lab/FigMirror/.claude/skills/figmirrorThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict0a7231a8d795A new audit runs when the source changes
• Repository statusNot archivedLast push 18 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: FigMirror mirrors the visual style of a top-conference paper figure (NeurIPS / ICML / ICLR / Nature family) onto the user's own data. Takes dirty data plus a reference figure screenshot (cropped or uncropped),…

---
name: figmirror
description: >
  FigMirror mirrors the visual style of a top-conference paper figure (NeurIPS /
  ICML / ICLR / Nature family) onto the user's own data. Takes dirty data plus a
  reference figure screenshot (cropped or uncropped), preprocesses the reference
  crop, runs a Drawer/Reviewer loop, and outputs a camera-ready PDF plus a
  self-contained matplotlib script with an inline DATA SECTOR.
---

# FigMirror (`figmirror`)

Use this skill when the user wants to:
- Transfer the visual style of a top-conference paper figure to their own data.
- Produce a camera-ready matplotlib figure matching a reference screenshot in
  style, not in data.
- Mirror 3D paper-figure references such as surfaces, scatter, trajectories,
  bars, layered waterfalls, or plane projections when the reference or data is
  actually 3D.
- Receive a self-contained `.py` script with editable inline data plus PNG/PDF
  outputs.

## Required Inputs

- A reference figure screenshot (`PNG`/`JPG`). It may include margins, captions,
  neighboring panels, or page text; Stage 0 preprocesses it.
- The user's data in any parseable form: pasted table, CSV, TSV, markdown table, or
  dirty terminal text.
- A working directory for iteration artifacts.

## 3D Insert Gate

Enable `references/three-d-prompting.md` only when the user asks for a 3D
figure, the reference is visibly 3D, or the parsed data requires a 3D encoding
such as `x/y/z`, surfaces, trajectories, layered profiles, closed objects, 3D
small multiples, 3D bars, or plane projections. Do not use this insert to turn
an ordinary 2D task into 3D.

## Architecture

- **Python runner** owns UI lifecycle, cancellation, optional
  data-gen, and launching the main `claude` process.
- **The top-level `claude` process is Orchestrator only.** It owns iteration state,
  role dispatch, artifact checks, Reviewer audit-view staging, deterministic
  review-gate invocation, stop decisions, and final selection.
- **Drawer** runs as the named `figmirror-drawer` custom subagent through the
  `Task` tool with `subagent_type="figmirror-drawer"` and
  `run_in_background=false`. It writes each iteration's matplotlib
  script, render, notes, and floor self-check in the staged workdir.
- **Reviewer** runs as the named `figmirror-reviewer` custom subagent through the
  `Task` tool with `subagent_type="figmirror-reviewer"` and
  `run_in_background=false`. It sees only the staged audit view:
  the far-view composite, full-resolution reference/draft near views, the
  Reviewer prompt, the aesthetic library, fixed diagnostics, and optional fixed
  3D audit material. It returns strict
  JSON including `boxes`; `figannot.py review-decision` validates and records the
  result before any Drawer or finalization decision. The `Task` tool carries a
  single text prompt and has no attachment channel, so the Orchestrator gives
  the Reviewer an ordered list of absolute image paths and the Reviewer opens
  each one with `Read`, once, in that order.
- **3D flow** uses the standard Orchestrator plus named Drawer/Reviewer
  subagents, and optional candidate-scoring path for strict reproduction.

## Workflow

1. Read these bundled references from this skill directory:
   - `references/preprocessor.md` for Stage-0 reference crop cleanup.
   - `references/orchestrator-claude.md` for loop wiring and stop conditions.
     `references/orchestrator-codex.md` ships alongside it as the diff baseline
     for the port and must not be followed at runtime.
   - `references/drawer.md` for the Drawer instructions.
   - `references/reviewer.md` for the Reviewer instructions.
   - `references/aesthetic-library.md` for the L2 convention library.
   - `references/three-d-prompting.md` only when the 3D insert gate is enabled.
2. Preserve the uploaded reference as `inputs/reference_raw.png`, then run the
   reference preprocessor to write `inputs/reference_clean.png`,
   `inputs/reference_crop_check.png`, and `inputs/reference_crop_report.md`.
   It is dispatched as a general-purpose subagent — there is no named
   preprocessor role — per the Stage 0 section of
   `references/orchestrator-claude.md`. Skip it only when the runner already
   staged those three files.
3. Echo the parsed data structure before drawing. If the user explicitly asked you
   to make up data or proceed without confirmation, record that in `data_echo.md`
   and continue; otherwise ask for confirmation.
4. When the 3D insert gate is enabled, stage `references/three-d-prompting.md`
   plus `references/three-d/` beside the normal prompts. The router selects
   exactly one mode file: `three-d/style-transfer.md` for ordinary user-data
   figures, or `three-d/strict-reproduction.md` for reproduction, comparison, or
   candidate/control replacement. For strict 3D reproduction runs that need
   quantitative candidate diagnosis, also stage `scripts/score_3d_candidates.py`;
   do not use that scorer for ordinary style transfer. The top-level
   Orchestrator owns final selection and must run the selected mode's
   rendered-image gates before copying any candidate to the final figure.
   Always stage `scripts/figannot.py`; it is the deterministic operator for
   building audit composites and drawing Reviewer boxes.
5. The top-level agent follows `references/orchestrator-claude.md` and
   dispatches `figmirror-drawer` for each iter. Every Drawer prompt includes the
   exact trace line `Iter: <N>` with the current non-negative decimal iteration.
   The Drawer writes
   `figure_iter<N>.py`, `img_iter<N>.png`, `notes_iter<N>.md`, and
   `floor_selfcheck_iter<N>.txt`; the Orchestrator verifies those files before
   any Reviewer handoff.
6. Stage `audit_view_<N>`, run `scripts/figannot.py compose` to create
   `composite.png` and `review_prompt.txt`, fit the staged near views with
   `scripts/fit_images.py`, and dispatch `figmirror-reviewer` as
   described in `references/orchestrator-claude.md`. List `composite.png`,
   `reference_clean.png`, and `draft_fullres.

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-18
   ✓SAFE B 89 / 100

   first audit · source 0a7231a8d795

Questions about Figmirror

• github.com/VILA-Lab/FigMirror/tree/main/.claude/skills/figmirror — the audited source at commit 0a7231a8d795 and every finding aboveObserved · 18 Oct 2026

Spotted something wrong? Report a correction · Methodology