AGENT SKILL

szl-uncertainty-lineage

Propagate declared measurement uncertainty through a small arithmetic dependency graph using a first-order delta approximation. Use when a researcher needs to see how corrected inputs or shared-source correlation change a reported standard uncertainty; require unit checks separately.

License 许可
Apache-2.0
最近更新
2026-11-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
szl-uncertainty-lineage
license
Apache-2.0
description
Propagate declared measurement uncertainty through a small arithmetic dependency graph using a first-order delta approximation. Use when a researcher needs to see how corrected inputs or shared-source correlation change a reported standard uncertainty; require unit checks separately.

02 资源文件 3

03 SKILL.md 正文

Uncertainty lineage

Run the offline helper on a bounded, explicitly declared model:

python scripts/run.py assets/example.json

The report retains every declared input dependency, including one whose local derivative cancels to zero. It gives each target's value, Jacobian, propagated variance, standard uncertainty, and signed per-input covariance contributions. Compare those quantities with a separately calculated reference before using the result in research. Read references/contract.md when preparing an input model or interpreting a failure.

The helper uses only the Python standard library. It contacts no external services and requires no credentials. This family supplies a CLI resource; it has no native sidecar kernel or verified application registration. Point and Jacobian operations must be exact at 80-digit decimal precision; nonterminating decimal divisions such as 1/3 fail closed. The standard-uncertainty square root is separately approximated. Read the contract before choosing this bounded tool for an arithmetic graph.

Require the researcher to declare either input independence or the complete correlation matrix. Missing correlations are unknown, never silently treated as zero. Keep the original model and report when a value or correlation is revised; run the revised model as a new version. Verify units with a separate unit check before this numerical step.

This evaluates a first-order local approximation to supplied arithmetic. It does not establish the input uncertainty model, distribution coverage, physical units, causality, or a scientific conclusion. Large uncertainty near a nonlinear boundary may require simulation or an analytic reference.

04 同仓库更多 Skills

szl-holdings
szl-holdings/szl-skills

szl-unit-invariants

Checks declared SI dimensions, allowlisted unit conversions, expected ranges and fixed pointwise invariants (equal, sum, difference, product, ratio) over selected measurement or simulation columns, flagging incompatible quantities, scale errors of 1000x and broken conservation checks. Use when merging instrument exports with different units, validating simulation output against conservation laws, or when a reviewer asks how unit errors were ruled out. Not an uncertainty-propagation or symbolic tool.

★ 0
szl-holdings
szl-holdings/szl-skills

szl-typesafe-ai

TypeSafe/Jev: Choice/Noul/Score in code, not TypeScript types. System One models turn natural language and application state into probabilities that software can compose. Use when building routing, ranking, extraction, verification, or replacing an LLM prompt-and-parse step with structured decisions; also when brainstorming what TypeSafe could make possible. Do not use for TypeScript/Java/Rust static types, Zod/Pydantic/mypy/JSON Schema/protobuf codegen, or asking whether a pipeline is type-safe. At SZL, Jev is an optional second reader only.

★ 0
szl-holdings
szl-holdings/szl-skills

demo

暂无简介

★ 0
szl-holdings
szl-holdings/szl-skills

demo

暂无简介

★ 0
szl-holdings
szl-holdings/szl-skills

szl-skill-update-review

Compare pinned local skill packages using inventories and a retained lock; report changed skills, files, declarations and reruns without approving safety or validity.

★ 0
szl-holdings
szl-holdings/szl-skills

szl-skill-conformance

Checks retained scientific skill-sharing evidence: exact local source and supplied host-export resource bytes, explicit import aliases, task and result digests, positive versus irrelevant-task trigger declarations, and optional artifact-to-trace byte bindings. Use when a shared skill appears imported but invocation is uncertain, when comparing retained trials across hosts, or when an update may invalidate an earlier result. Offline checking never executes the candidate and never certifies real host invocation or scientific correctness.

★ 0