experiment-forge SKILL.md skillA
experiment-forge from yichen-zju/claude-for-research is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yichen-zju/claude-for-research/experiment-forge@git:20261014.9f2a5e0Pins git:20261014.9f2a5e0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yichen-zju/claude-for-research
- Path
claude/skills/experiment-forge/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261014.9f2a5e0, committed Oct 14, 2026
- Size
- 6,861 bytes
- Repository stars
- 10
- License
- none declared
Forge self-contained experiment packages with code, configs and runbooks from a task description; use when launching or packaging structured autonomous experiments.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Experiment Forge ## 任务包结构 ``` <task-dir>/ ├── prepare.py # 🔒 锁定：数据准备、tokenizer/dataloader、评估函数。agent 禁止修改（评估真实性保护） ├── train.py # 🔓 开放：默认开放文件（模型、优化器、训练循环、超参） ├── program.md # 🧭 人类可迭代：给 agent 的研究组织指令（用 templates/program.md 生成） ├── pyproject.toml # 依赖清单 —— 变更须走任务契约的预授权流程（声明包+版本、隔离环境安装） └── results.tsv # 实验台账（表头由 forge 生成，agent 追加行，不提交 git） ``` 名字按任务实际调整（比如 `evaluate.py`/`model.py`），但 **锁定/开放/指令 三件套不可缺**。可编辑范围按任务定义（r29 A5）：数据选择、增强、表示、tokenizer 等训练方法组件可以纳入开放范围（多个开放文件合法）；锁定范围只保护评估与数据 ground truth——评估完整性需要保护，训练流水线不因评估保护而永久不可改。 ## 任务契约（Forge 时一次确认；被 orchestrator 调用则视为已授权） 逐项确认**一次完成**（一条消息列全），不逐条追问；被 research-orchestrator 调用时视为上游已授权（BOOTSTRAP 双闸门），直接采用 state 里的 scope/预算/环境，只对**新增实质性选择**（预算扩张、权限变化、评估口径改变）提问。 1. **比较口径（按研究问题选择，r29 A4）**：等 wall-clock / 等 updates（步数）/ 等数据量（tokens）/ 训练到约定收敛——Forge 时与研究问题一起选定并写进 program.md。固定时长只是可选协议之一（适合"固定算力下谁更好"的问题），不是普适公平标准；更慢但效果更好的方法不能仅因跑得慢记科学失败。 2. **架构无关指标**：指标必须对架构改动公平（karpathy 用 val_bpb 而非 loss，因为 loss 随 vocab size 变）。问用户："换个架构/分词器/特征，这个指标还可比吗？"不可比就换指标。 3. **评估代码锁定**：评估函数、数据加载、随机种子控制放在锁定文件里，是 ground truth。 …
Read the whole file at its exact version.
How to install
mdr add yichen-zju/claude-for-research/experiment-forge@sha256:4674c69a3b5d35b0The line at the top of this page pins the label git:20261014.9f2a5e0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cqsrburgjsquoivq)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 14, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6861 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yichen-zju/claude-for-research · 10 stars · license none declared · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cqsrburgjsquoivq GET https://markdownregistry.com/api/v1/resolve?ref=yichen-zju/claude-for-research/experiment-forge GET https://markdownregistry.com/api/v1/blob/4674c69a3b5d35b0f93fa1a72db550861f36c0ab83295db8ececc3ce64761a57
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from yichen-zju/claude-for-research
Every file in yichen-zju/claude-for-research