SoFarSoGoodyaSoFarSoGoodya/mathmodel-weave/skills/execution/SKILL.md

execution

Skill2 starsChanged 41 days agoMITView on GitHub

Run a local mathematical experiment through the MathModel runtime and package traceable observations, metrics, checks, and figures. Use for numerical experiment requests, not for scheduling or publication-only restyling.

10 other projects use a version of this.

Adopted by

Most recently taken up by

jircdev/crew-plugintheir own version, first seen Nov 1, 2026
ceeinbeta/pm-skillstheir own version, first seen Nov 1, 2026
CrowdStrike/fusion-skillstheir own version, first seen Oct 30, 2026
mcveloria/pm-skillstheir own version, first seen Oct 25, 2026
nuncaeslupus/literary-critictheir own version, first seen Oct 13, 2026
dynos-fit/dynos-worktheir own version, first seen Oct 13, 2026

Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
Towow-ai/Flowness★ 107same name
CrowdStrike/fusion-skills★ 29same name
metraton/gaia★ 4same name
ceeinbeta/pm-skills★ 3same name
mcveloria/pm-skills★ 3same name
dynos-fit/dynos-work★ 2same name
jircdev/crew-plugin★ 1same name
luisabwk/kraken★ 1same name
Leostruka/devin-bundle★ 0same name
nuncaeslupus/literary-critic★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- coordinatorSkill
- evidenceSkill
- explorationSkill
- publicationSkill
- reviewSkill

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 3 are distinctive, and 5 are very specific to this project.

0
Common
Most of the 9 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Use the runtime-backed execution API in mathmodel_agent.execution.
line 6
Very specific:
Use formal only after supplying a stable comparison-contract JSON.
line 11
Very specific:
Treat a fresh algorithm launch as a new experiment_run_id.
line 14
Very specific:
Write complete JSONL observations and figure provenance files before finalization.
line 16
Very specific:
Do not infer not_run from missing output: only a task with no runtime attempt is not_run.
line 17
Distinctive:
Use metric recomputation and independent checks only where their method matches the recorded check type.
line 19
Distinctive:
Keep raw input data read-only.
line 22
Distinctive:
Read the execution contract before preparing a formal run.
line 25

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Use the runtime-backed execution API in mathmodel_agent.execution; do not start a private subprocess, task queue, or per-seed worker system.

Make every command argv explicit and case-relative inputs explicit. Use only the documented command placeholders from docs/modules/execution.md.
Use formal only after supplying a stable comparison-contract JSON. Preserve every planned instance, including failed or timed-out ones. Deterministic algorithms have seed: null.
Treat a fresh algorithm launch as a new experiment_run_id. Do not call a receipt replay a scientific rerun.
Write complete JSONL observations and figure provenance files before finalization. Do not infer not_run from missing output: only a task with no runtime attempt is not_run; otherwise preserve unknown or partial facts.
Use metric recomputation and independent checks only where their method matches the recorded check type. A process rerun and an independent implementation are different claims.
Keep raw input data read-only. A visual redraw does not modify a metric; a change to samples, aggregation, units, or numerical values needs a new experiment package.

Read the execution contract before preparing a formal run.

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.

Reviews can't be read right now.

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