light-experiment-coding
Light 科研主线 stage 6：把冻结的 question/estimand、experiment matrix、pre-registration 与 data lineage 落成最小可运行、测试先行、无泄漏、可复现且能交给 result-analysis 的实验代码。用于实现或复现训练/预处理/评测， 设计 gold/property/metamorphic 测试，控制 Python/NumPy/框架/CUDA/DataLoader 随机性，审查 train/test 或 CV fit 穿越，记录 config/code/environment/input hashes、stdout/stderr、raw metrics、patient/entity predictions 与 failure artifacts，以及运行 stage-6 checkpoint。数据泄漏或不可复现是 critical；静态扫描和同 seed 两次一致都不证明跨硬件 绝对复现。
npx skills add Light0305/Light-skills --skill light-experiment-coding --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 实验编码（stage 6） 任务不是“写出能跑的 notebook”，而是把上游冻结计划逐行实现成**可证伪、可复跑、可审计**的实验。优先级： 1. 不改研究问题； 2. 不让评估信息进入训练； 3. 能用固定环境与 seed 真复跑； 4. 保留足够 raw evidence，让 result-analysis 自己重算； 5. 代码整洁和速度服从以上约束。 先完整阅读 [`references/experiment-coding-resource-map.md`](references/experiment-coding-resource-map.md)。工具机制见 [`references/tools.md`](references/tools.md)，TDD/调试红旗见 [`references/tdd_redflags.md`](references/tdd_redflags.md) 与 [`references/debug_protocol.md`](references/debug_protocol.md)。 ## 入口：冻结输入 开始写码前读取并 hash： - question / estimand； - experiment matrix 每一行和 fair-comparison 常量； - pre-registration 及 provenance； - failure-tree report：每条 hypothesis 的 success/failure/inconclusive 分支、guardrail/counter-metric、kill criterion 与 amendment policy； - data fixed revision、raw/curated SHA256、lineage、split ID、`split_leakage` evidence； - result-analysis 对 raw run、predictions、metrics、failures、provenance 的消费契约； - 当前 git commit 与 dirty state。 primary outcome、comparison family、exclusion、stopping 已冻结。若实现证明计划不可行，带最小复现和影响返回 research-plan，停下让人决策；不得改 config 默认值静默漂移。 ## 实现顺序 ### 1. 建立最小可运行项目 优先复制 [`assets/project-scaffold/`](assets/project-scaffold/)： - `uv.lock` + `pyproject.toml`：`uv sync --locked --extra dev`； - `configs/e
- 入口：冻结输入
- 实现顺序
- 1. 建立最小可运行项目
- 2. 测试先行
- 3. 防泄漏实现
- 4. 控制随机性与数值边界
- 5. 每个 run 保留 raw bundle
- 门控与 checkpoint
- 交 result-analysis 与 7→6
- 不可协商
- 完成判据
- 名实对齐
python scripts/experiment_execution_contract.py --spec experiment_execution_contract.json \ python scripts/review_gate.py src/ --json python scripts/seed_audit.py src/train.py src/reproducibility.py python scripts/repro_gate.py --spec repro_spec.json --report repro_findings.json python scripts/run_artifact_check.py --manifest runs/EXP-01/run-a/manifest.json python scripts/run_artifact_check.py --compare \ runs/EXP-01/run-a/manifest.json runs/EXP-01/run-b/manifest.json python ../light-orchestrator/scripts/run_checkpoint.py \ python ../light-orchestrator/scripts/reroute.py \
What does the light-experiment-coding skill do?
Light 科研主线 stage 6：把冻结的 question/estimand、experiment matrix、pre-registration 与 data lineage 落成最小可运行、测试先行、无泄漏、可复现且能交给 result-analysis 的实验代码。用于实现或复现训练/预处理/评测， 设计 gold/property/metamorphic 测试，控制 Python/NumPy/框架/CUDA/DataLoader 随机性，审查 train/test 或 CV fit 穿越，记录 config/code/environment/input hashes、stdout/stderr、raw metrics、patient/entity predictions 与 failure artifacts，以及运行 stage-6 checkpoint。数据泄漏或不可复现是 critical；静态扫描和同 seed 两次一致都不证明跨硬件 绝对复现。
How do I install it?
Run `npx skills add Light0305/Light-skills --skill light-experiment-coding --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Light0305/Light-skills, a repository with 505 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.