Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xuzhougeng/figure-composer
Compose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an existing image.
Passed 12 of 18 test cases with the skill, and 7 of 18 without it.
and 6 more in the full report
9 fixed6 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
When invoking composite figure review sub-agent tasks, which capability permissions should be assigned to the reviewer sub-agent if capability advertising is active?
| Checked | Without skill | With skill |
|---|---|---|
| The reviewer task is granted image_inspection, project_read, and reasoning capabilities. | Missed | Passed |
The instructions your model reads when the skill loads.
Load figure-style with this skill. The sidecar provides pure geometry,
composition, task-building, and review-schema helpers. It does not call models,
delegate Agents, resolve artifacts, or inspect images from Python.
Require a one-sentence claim, target width in millimetres, and concrete
project-relative or absolute data paths. Never use artifact ids as paths. For an
existing figure, inspect the real image with view_image and write the outline
yourself; pixels cannot reveal the source data path.
figure_outline_schema(). Put real paths in
data_path; use null for schematics.a the conceptual hook and panel b the primary evidence. Use a
12-column grid and one row per sub-claim.panel_task(...).delegate_tasks is advertised, submit the independent panel tasks as one
batch. Grant each task the minimum advertised capabilities needed, normally
visualization plus project_read. Require a concrete PNG filename in each
output schema. If delegation is unavailable, render the panels sequentially
with python.compose_figure(...). Do not pass placeholder
markers to the composer.compose_crops(...) with Pillow to save temporary crop files, then call
view_image on the composite and every crop. Fix seams, clipped labels,
aliases, empty space, and misplaced panel letters before review.composite_review_task(...). Delegate it
with image_inspection, project_read, and reasoning when those capability
ids are advertised; otherwise perform the review in the current Agent.{
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.