plotting-agent skillA
plotting-agent is agent-read markdown (skill) from ar9av/paperorchestra: Step 2 of the PaperOrchestra pipeline (arXiv:2604.05018). Execute the visualization plan from outline.json — render plots and conceptual diagrams from experimental_log.md and idea.md, optionally refine via VLM critique loop, and produce context-aware captions. Runs in parallel with the literature-review-agent. TRIGGER when the orchestrator delegates Step 2 or when the user asks to "generate the figures for my paper" or "render the plots from this experiment log"..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Plotting Agent (Step 2)
Faithful implementation of the Plotting Agent from PaperOrchestra
(Song et al., 2026, arXiv:2604.05018, §4 Step 2 and App. F.1 p.45).
**Cost: ~20–30 LLM calls.** The paper uses PaperBanana (Zhu et al., 2026) as
the default backbone with a closed-loop VLM-critique refinement. This skill
expresses that loop in host-agent terms: you (the host agent) generate
matplotlib code with your own LLM, render via your Bash/Python tool,
optionally critique the rendered PNG with your vision model, redraw, and
finally caption.
## Inputs
- `workspace/outline.json` — specifically the `plotting_plan` array
- `workspace/inputs/idea.md` and `workspace/inputs/experimental_log.md` —
the source data
- `workspace/inputs/figures/` — optional pre-existing figures (`PlotOn` mode)
## Outputs
- `workspace/figures/<figure_id>.png` — one PNG per `plotting_plan` entry
(300 DPI, sized to the requested aspect ratio)
- `workspace/figures/captions.json` — `{figure_id: caption_text}` map
## Workflow
### Per figure (executed independently per `figure_id`)
1. **Read the figure spec** from `outline.json`:
```json
{
"figure_id": "fig_main_results",
…Read the whole file at its exact version.
How to install
mdr add ar9av/paperorchestra/plotting-agent@git:20260921.8d6fd97mdr add ar9av/paperorchestra/plotting-agent@sha256:34c5fae63a611892Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_iyv5vcdolrj6ascd)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260921.8d6fd97 latest | 2026-09-21 | 8d6fd97 | 9,395 B | A | view · diff |
| git:20260410.39484d9 | 2026-04-10 | 39484d9 | 7,940 B | A | view · diff |
| git:20260410.2b73c0a | 2026-04-10 | 2b73c0a | 8,915 B | A | view · diff |
| git:20260409.c2de31b | 2026-04-09 | c2de31b | 7,134 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9395 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ar9av/paperorchestra · 664 stars · license NOASSERTION · pushed 2026-09-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_iyv5vcdolrj6ascd GET https://markdownregistry.com/api/v1/resolve?ref=ar9av/paperorchestra/plotting-agent GET https://markdownregistry.com/api/v1/blob/34c5fae63a611892eb9e7d49aba93be2a706667525e4d0d00d9bb3109805c3b9
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.