Skills for Real Engineers. Straight from my .agents directory.
science-experiment-runbook
Agent skill fromyzlin286-wq/Deepscient
Use when turning an approved plan into an actual run — when the design and sample size are settled and someone needs to produce data, execute code, or reproduce a result; when a run must be recordable (inputs, outputs, environment, seed) so that six months later the numbers in the paper can be traced back; when a result cannot be reproduced and the difference has to be explained rather than waved away; also use when deciding where raw data, analysis code and generated artifacts belong.
How to install science-experiment-runbook
npx skills add yzlin286-wq/Deepscient# or add only this skill to Claude Code: copy the folder
dsh-science/skills/science/science-experiment-runbook/
# into
~/.claude/skills/science-experiment-runbook/ (all projects)
.claude/skills/science-experiment-runbook/ (one project)
1# 从方案到一次可复现的执行23## 这一层要守住的三件事451. **原始数据只进 `data/`,只读。**6 清洗结果放 `data/clean/`,分析产物放 `experiments/<slug>/<runId>/`。7 一旦在原始文件上直接改,你永远回不到采集当天的状态——而审稿人问的第一个问题往往就是那个状态。82. **每次执行都要能被别人重跑。**9 `science_exp_run` 记的是:脚本内容指纹、输入文件 sha256、输出文件 sha256、10 Python 与关键库版本、seed、是否允许网络。缺任何一项,这次执行就只是"你跑过一次"。113. **Python 层默认无网。**12 数据下载在采集阶段做完,分析阶段不该联网。要联网就显式 `network: true`,13 记录里会写明——这是给自己留的证据,不是给别人看的仪式。1415## 顺序1617```18science_study_coach { projectId } ← 先确认 S2/S3 的门过了19science_exp_plan { projectId, effect: … } ← 样本量与前置条件(若还没做)20把数据放进 data/21写 code/run.py ← 一个脚本一件事,参数从 argv 进来22science_exp_run { projectId, slug, script: 'code/run.py', inputs: ['data/raw.csv'], seed: 42 }23science_exp_query { projectId, what: 'runs' } ← 确认状态、产物、耗时24```2526## `science_exp_run` 的字段怎么填2728| 字段 | 什么时候用 | 坑 |29| --- | --- | --- |30| `script` | 已有脚本 | 路径必须在课题目录内;`../../x.py` 会被拒 |31| `code` | 一次性验证 / 小实验 | 会写成 run 目录里的 `run.py`,同样留痕 |32| `inputs` | 有输入文件 | 相对课题根;文件不存在直接报错,不静默跳过 |33| `seed` | 任何有随机性的分析 | 写进 `seed.txt` 并导出 `DSH_SEED`;不传就用默认值并记录下来 |34| `network` | 需要下载/调用 API | 默认 `false`。Python 层会被 hook 拦住;`curl` 子进程拦不住,这一点要在记录里自己注意 |35| `timeoutMs` | 长任务 | 超时按失败记,不会假装成功 |3637## 失败了怎么办3839失败的执行**也进溯源链**,这是刻意的:一份只记录成功的历史没有诊断价值。40411. 先读 `stderrTail` 和 run 目录里的 `stderr.log`。422. 分类:代码错(改脚本重跑)/数据错(回去看采集)/环境错(`probeEnv` 对比版本)/超时(拆任务)。433. **不要**为了让结果出来而降低检验标准、删样本、换主结局。那一步一旦迈出去,后面所有数字都要重做。4445## 复现性检查(交给别人之前)4647- 同一 seed 跑两次,输出文件的 sha256 应完全一致。不一致就说明有未受控的随机源(时间、字典序、并行度、浮点归约顺序)。48…
Excerpt shown under the repository's MIT license.
More skills in Deepscient
- ▸science-agent-scheduling
- ▸science-campaign-design
- ▸science-consensus-report
- ▸science-discipline-methods
- ▸science-figure-for-journal
- ▸science-frontier-to-paper
- ▸science-fulltext-hunting
- ▸science-journal-intel
- ▸science-journal-selection
- ▸science-literature-search
- ▸science-manuscript-formatting
- ▸science-org-roles
Similar skill repositories
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
