JiamingShi-JsPhysJiamingShi-JsPhys/chelate-shell/skills/capstone-labmate/SKILL.md

capstone-labmate

Skill10 starsChanged 6 days agoMITView on GitHub

Parses PASCO Capstone `.cap` files into down-sampled CSV/JSON, pre-configures a Capstone run from a lab manual PDF, and drafts a watermarked lab report. It is an interoperability helper for teaching; it never fabricates data and never claims the experiment was performed by the tool.

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
- 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
- sci-visualizerSkill
- security-guardSkill
- task-organizerSkill
- video-trackerSkill

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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:
Run this exact form — do not read the source tree:
line 26
Distinctive:
No data was collected — the tool never invents measurements.
line 45
Distinctive:
Never fabricate data: Every number comes from the parsed file.
line 59

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

capstone-labmate

Turns Capstone's binary .cap output into analysis-ready tables and helps with the pre-lab and post-lab paperwork. All parsing runs locally.

Stage: ingest · Sandbox: no · Dependencies: stdlib only (numpy/matplotlib/pypdf add optional paths)

Quick Execution

Run this exact form — do not read the source tree:

python run.py --root <WS> --action ingest -- <file.cap>

ingest and process both map to the .cap parser; preconfigure reads a PDF lab manual; draft writes the watermarked report.
Outputs land in <WS>/process/stage_a|stage_c|stage_d — never in the skill directory.

When to use

A .cap file must become CSV/JSON for analysis.
A lab manual PDF must be turned into a preconfigured Capstone run.
A draft lab report must be generated from already-collected data.

When NOT to use

No data was collected — the tool never invents measurements.
The user wants the AI to run the experiment; it is physically isolated from that stage.

Actions

`--action`	Does	Extra arguments
`ingest`	`.cap` → down-sampled CSV/JSON	`<file.cap>`
`process`	Alias of `ingest`	`<file.cap>`
`preconfigure`	Lab manual PDF → preconfigured `.cap`	`<file.pdf>`
`draft`	Summary → watermarked draft report	`<summary>`

Hard constraints

Never fabricate data. Every number comes from the parsed file.
Reports are drafts. They carry a watermark; academic responsibility stays with the user.

Outputs

<WS>/process/stage_c/ — converted JSON/CSV.
<WS>/process/stage_a/ — the preconfigured run.
<WS>/process/stage_d/draft.md — the watermarked draft.
<WS>/process/gates/capstone-labmate_<ts>.json — the gate result.

Failure handling

An unreadable or truncated .cap fails the gate with the parser's message.
A PDF without a recognisable procedure is reported, never guessed.

Limitations

"PASCO" and "Capstone" are trademarks of PASCO Scientific; this skill is independent.
Conversion down-samples: the full native resolution is not preserved.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free