empiricalwiki: Skill for Claude Code

.claude/skills/exp-design/SKILL.md

exp-design is a skill for Claude Code from Lambenthan/empiricalwiki. It costs 45 tokens per session (4,175 once invoked), scanned A, original, MIT.

A planning workflow for designing experiments around explicit claims, with baseline, validation, factor-isolation, and robustness tests.

In plain words
What is it for?
Use it with a research idea or a written hypothesis. It creates planned experiment pages, links them to claims and ideas, records the execution order and budget, and updates the research graph.
Why use it?
It turns an idea into an ordered research plan with dependencies, stopping decisions, optional review, and a stated GPU-hour budget.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is Lambenthan/empiricalwiki's own configuration. It tells Claude Code how to work on empiricalwiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything empiricalwiki configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 tools/research_wiki.py slug "<experiment-title>".

Reuse

Borrowing it

Nothing to install: this file belongs to Lambenthan/empiricalwiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/exp-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/Lambenthan/empiricalwiki

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for exp-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-design/github.svg)](https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-design)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-design"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for exp-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/exp-design"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/exp-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.04175
Opus 5 $0.00023 $0.02087
Sonnet 5 $0.00009 $0.00835
Haiku 4.5 $0.00005 $0.00417

Measured 9d ago against content hash d106f414d4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

exp-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/exp-design/SKILL.md · 360 lines

How it starts

The opening of the file, as written. The whole thing — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/exp-design

根据一个 idea(或自由文本假设),设计完整的实验计划。 以 claims 为核心:从 Target / Decomposition / Threats 三个维度界定要验证的 claims, 设计 baseline(基线复现)、validation(核心验证)、ablation(因素隔离)、robustness(鲁棒性)四种实验块。 实验按依赖关系排序,阶段间设决策门(sanity fail → 提前停止)。 可选 Review LLM review 检查实验完整性。所有实验写入 wiki/experiments/ 并添加 graph edges。

Inputs

  • idea:以下之一:
    • wiki/ideas/ 中的 slug(如 sparse-lora-for-edge-devices
    • 自由文本假设描述(直接提供实验目标)
  • --review(可选):启用 Review LLM review 审查实验计划完整性
  • --budget <gpu-hours>(可选):总计算预算上限(GPU 小时),影响 robustness 实验规模

Outputs

  • wiki/experiments/{slug}.md — 每个实验块一个页面(status: planned)
  • wiki/graph/edges.jsonl — 新增 experiment → claim 的 tested_by 边
  • wiki/ideas/{slug}.md — 更新 linked_experiments 字段
  • wiki/graph/context_brief.md — 重建
  • wiki/graph/open_questions.md — 重建
  • wiki/log.md — 追加日志
  • EXPERIMENT_PLAN_REPORT(输出到终端)— 实验块总览、执行顺序、计算预算

Wiki Interaction

Reads

  • wiki/ideas/{slug}.md — 获取 idea 的 hypothesis、approach、risks、origin_gaps
  • wiki/claims/*.md — 目标 claims 的当前状态、已有 evidence、confidence
  • wiki/experiments/*.md — 已有实验(避免重复设计、参考 setup 配置)
  • wiki/papers/*.md — 相关论文的 baselines 和实验设置
  • wiki/concepts/*.md — 涉及的技术概念(指导实验设计)
  • wiki/graph/context_brief.md — 全局上下文
  • wiki/graph/open_questions.md — 知识缺口(指导实验优先级)

Writes

  • wiki/experiments/{slug}.md — 创建实验页面(每个实验块一个)
  • wiki/ideas/{slug}.md — 更新 linked_experiments 字段
  • wiki/graph/edges.jsonl — 添加 tested_by 边
  • wiki/graph/context_brief.md — 重建
  • wiki/graph/open_questions.md — 重建
  • wiki/log.md — 追加操作日志

Graph edges created

  • tested_by:claim → experiment(claim 被该实验验证)

Workflow

前置:确认工作目录为 wiki 项目根(包含 wiki/raw/tools/ 的目录)。

Step 1: 加载上下文

  1. 解析 idea 输入
    • 若为 slug:读取 wiki/ideas/{slug}.md,提取 ## Motivation## Hypothesis## Approach sketch## Risks,以及 frontmatter 字段 origin_gapstagsdomainpriority(遵循 CLAUDE.md 的 ideas template)
    • 若为自由文本:直接作为假设描述使用
  2. 加载相关 wiki 上下文
    • 读取 wiki/graph/context_brief.md(全局上下文)
    • 读取 wiki/graph/open_questions.md(知识缺口)
    • 从 idea 的 origin_gaps 读取对应的 wiki/claims/*.md(目标 claims)
    • 从每个目标 claim 的 source_papers 字段读取对应的 wiki/papers/*.md,获取 baseline setup 和已有实验协议 —— 这是 idea → claim → paper 的规范路径(ideas 不带 linked_papers 字段,改用 origin_gapssource_papers)
    • 读取已有 wiki/experiments/*.md,检查是否已有类似实验
  3. 若 idea 无 origin_gaps:从假设描述中提取隐含的 claims,在 wiki/claims/ 中查找或标注需要新建

Read the full file on GitHub · 360 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 360 lines · 45 tokens per session scan A d106f414d4b5

Subscribe to this mod's changes

exp-design is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 4,175 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

review-paper

Comprehensive manuscript review with three modes: single-pass (default), --adversarial critic-fixer loop, and --peer [journal] simulated peer-review pipeline (editor + 2 dispositioned referees + editorial decision, calibrated to a target journal). R&R continuation via --peer --r2/--r3; hostile-editor stress test via…

pedrohcgs/claude-code-my-workflow · 114 tokens

audit-reproducibility

Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.

pedrohcgs/claude-code-my-workflow · 54 tokens

capture-environment

Snapshot the computational environment for a replication package — detects the analysis stack (R / Stata / Python) and emits the right lockfiles (renv.lock + sessionInfo.txt, requirements.txt / environment.yml / uv.lock, Stata version + ado package list), records seeds and RNG kind, optionally writes a pinning…

pedrohcgs/claude-code-my-workflow · 139 tokens

data-management-plan

Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…

pedrohcgs/claude-code-my-workflow · 143 tokens

grant-proposal

Scaffold a research grant proposal (NSF, NIH, ERC, or foundation) by composing existing primitives — pulls identification strategy from an /interview-me spec, delegates the data-management plan to /data-management-plan and the facilities statement to /capture-environment, and emits a funder-requirements checklist. Use…

pedrohcgs/claude-code-my-workflow · 131 tokens

power-analysis

Compute statistical power, required sample size, and minimum detectable effect (MDE) for a study design, then write a registry-ready power section. Handles two-arm RCTs (with clustering / ICC and unequal allocation), multiple-arm corrections, and a simulation-based power option for non-standard designs…

pedrohcgs/claude-code-my-workflow · 150 tokens