AGENT SKILL

challenge-sciml-model

Challenge SciML evidence for leakage, physical constraints, extrapolation, uncertainty, baselines, and cost.

License 许可
MIT
所属仓库
dasobral/skills
最近更新
2026-08-15
Stars
★ 0
Forks
0

01 前言 Front Matter

name
challenge-sciml-model
license
MIT
metadata
{ "plugin": "scientific-claim-ledger", "version": "0.1.0" }
description
Challenge SciML evidence for leakage, physical constraints, extrapolation, uncertainty, baselines, and cost.

02 资源文件 2

03 SKILL.md 正文

Challenge SciML Model

Use references/sciml-challenge-result.schema.json to record every check.

Required challenges

  • Grouped, temporal, spatial, and regime-aware splits
  • Preprocessing and calibration leakage
  • Extrapolation beyond observed regimes
  • Conservation, invariance, positivity, and boundary conditions
  • Residual error versus solution and quantity-of-interest error
  • Uncertainty coverage and sharpness
  • Seed and initialization sensitivity
  • Strong baselines compared at matched error
  • End-to-end training, inference, hardware, memory, and energy cost

Workflow

  1. Pin datasets, split identities, preprocessing state, model revision, seeds, hardware, and evaluation commands.
  2. Record each evidence check as pass, fail, unknown, not-applicable, or evidence-gap, with evidence and rationale. Keep these evidence states separate from block, review-required, and other workflow decisions.
  3. Keep objective contract failures distinct from model-adequacy findings.
  4. Run python3 scripts/check_sciml_challenge.py <challenge-result.json>.
  5. Block only forbidden calibration/validation overlap or declared objective constraint failures. Escalate model adequacy as review-required.

Rules

  • Never hide failed seeds or regimes in aggregate metrics.
  • Never compare cost or accuracy at unmatched error targets.
  • Agents may challenge and summarize evidence but cannot make the final pass decision.

04 同仓库更多 Skills

dasobral
dasobral/skills

fixture-skill

Fixture skill used to prove trust inventory coverage.

Skill与智能体开发
★ 0
dasobral
dasobral/skills

write-conformant-code

Write code in any language that matches project conventions exactly. Reads CODING_REQUIREMENTS.md, prior review output, or built-in defaults before writing. Part of Codecraft pipeline: analyze → write → review → audit. Use when implementing features, functions, or any code that should fit seamlessly into an existing codebase.

开发工程师内容创作者写作与文案
★ 0
dasobral
dasobral/skills

test-crypto-interoperability

Record reproducible cryptographic interoperability cases, including negotiation, fallback, sizes, latency, fragmentation, and negative tests.

测试与质量
★ 0
dasobral
dasobral/skills

scientific-platform-architect

Design scientific computing platforms combining HPC kernels with modern infrastructure. Enforces compute-layer separation (Rust/PyTorch/Python), emulator-first thinking, and right-sized infrastructure. Use for MCMC pipelines, neural emulators, platform design, or scientific code review.

设计师代码审查视觉设计
★ 0
dasobral
dasobral/skills

rust-systems

Rust systems engineering for daemons, HTTP APIs, and AOS components. Enforces Tokio/Axum async-first, LiteLLM-compatible OpenAI APIs, workspace layouts, tracing, and systemd-compatible daemon design. Part of AOS Stack plugin. Use for .rs files, Cargo.toml, daemons, or Rust orchestrator services.

视觉设计
★ 0
dasobral
dasobral/skills

run-agent-attack-replay

Aggregate isolated agent attack trials with deterministic side-effect assertions, Wilson intervals, and preserved trace evidence.

Skill与智能体开发
★ 0