sci-visualizer
Skill10 starsChanged 6 days agoMITView on GitHub
Generation meta-skill: renders static scientific charts from tabular data and scans gif/animation frame sequences. Successor to `figure-generator`, adding the gif path and four chart types.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/chelate-shell.mdcCursor rule
- 3d-modelerSkill
- ai-trace-removerSkill
- bibtex-normalizerSkill
- capstone-labmateSkill
- conflict-detectorSkill
- data-profilerSkill
- document-evolution-trackerSkill
- formula-validatorSkill
- fulltext-extractorSkill
- latex-exporterSkill
- literature-retrieverSkill
- longitudinal-analysisSkill
- ml-auditorSkill
- multi-dim-managerSkill
- quantitative-validatorSkill
- reference-auditorSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Run this exact form — do not read the source tree:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
sci-visualizer
Produces figures and inspects frame sequences. It renders what the data says and never invents points.
- Stage:
generation· Sandbox: no · Dependencies:matplotlib,seaborn,pandas(Pillowoptional for gif frames)
Quick Execution
Run this exact form — do not read the source tree:
python run.py --root <WS> --action process --input data.csv --chart bar--type {static,gif,animation}selects the mode;--charttakesbar|line|scatter|box.--x,--y,--hue,--titleshape the figure.- Output lands in
<WS>/process/figures/; the gate in<WS>/process/gates/.
When to use
- A dataset needs a publication-quality chart.
- A gif or frame sequence must be inspected frame by frame.
When NOT to use
- An interactive or 3D visualisation — out of scope (
3d-modelermakes meshes, not plots). - The figure must be hand-composed.
Actions
--action | Does | Extra arguments |
process | Render the figure or scan frames | --input <csv|json|gif> [--type ...] [--chart ...] [--x --y --hue --title] |
Hard constraints
- Never fabricate data points.
- Never drop rows silently — report what was plotted.
Outputs
<WS>/process/figures/<name>.png— the rendered figure.<WS>/process/gates/sci-visualizer_<ts>.json— the gate result.
Failure handling
- A missing column fails the gate naming that column.
matplotlib/seaborn/pandasmissing →UNVERIFIED.
Limitations
- Static output; gif support is a frame scan, not video rendering.
- Four chart types plus the SEM renderer.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.