empiricalwiki: Skill for Claude Code

.claude/skills/prefill/SKILL.md

prefill is a skill for Claude Code from Lambenthan/empiricalwiki. It costs 28 tokens per session (1,721 once invoked), scanned A, original, MIT.

A tool that adds basic, established knowledge about a research field to a wiki's foundations section. These foundations are reference pages for standard methods and concepts.

In plain words
What is it for?
Use it to populate foundations for general research, NLP, computer vision, machine-learning systems, or robotics.
Why use it?
It prevents later paper reviews from creating duplicate pages for textbook material.

Skill for Claude Code

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

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/fetch_wikipedia.py summary "<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/prefill/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 prefill

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/prefill.svg)](https://agentmods.dev/skills/lambenthan/empiricalwiki/prefill)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/prefill"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/prefill.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,721 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 $0.00028 $0.01721
Opus 5 $0.00014 $0.00860
Sonnet 5 $0.00006 $0.00344
Haiku 4.5 $0.00003 $0.00172

Measured 8d ago against content hash 20a3c6395b78, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

prefill 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 8d 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/prefill/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/prefill

将领域基础知识(奠基性方法、common practice、标准架构)作为终端页面沉淀到 wiki/foundations/。 Foundations 设计上单向:其他页面可以链接到 foundation,foundation 不写反向链接。

Trigger

手动:/prefill [domain]/prefill --add "概念名"

Inputs

  • domain(位置参数,可选):研究领域 — general / NLP / CV / ML Systems / Robotics 之一。未指定时从 wiki/topics/ 标签推断;若 topics 为空则提示用户。
  • --add "<概念>":跳过 catalog,直接为单个概念建立 foundation。

Outputs

  • wiki/foundations/{slug}.md — 每个种子一页
  • 更新的 wiki/index.md(由 rebuild-index 重生成 foundations 段落)
  • wiki/log.md 一条记录

Wiki Interaction

读取

  • wiki/topics/*.md — 用于推断 domain(未指定时)
  • wiki/foundations/*.md — 跳过已存在的 foundation(幂等)
  • .claude/skills/prefill/foundations-catalog.yaml — 种子列表

写入

  • wiki/foundations/{slug}.md(仅新建,从不覆盖)
  • wiki/index.md(通过 tools/research_wiki.py rebuild-index
  • wiki/log.md(通过 tools/research_wiki.py log

Workflow

前置条件:当前目录包含 wiki/tools/.claude/WIKI_ROOT=wiki/

Step 1: 确定 domain

  1. 用户传入 domain → 直接使用。
  2. 否则若处于 --add 模式 → 默认 general,除非用户额外指定。
  3. 否则:读取 wiki/topics/*.md 的 frontmatter tags;若能识别出主导 domain 则用之,否则提示用户。

Step 2: 加载种子

  • Catalog 模式:读取 .claude/skills/prefill/foundations-catalog.yaml,取 domains.{domain} 下所有条目,并叠加 domains.general 的全部条目(general foundations 适用所有领域)。
  • --add 模式:构造单一种子 {slug: <slugified concept>, title: <concept>, summary: ""}。Slug 用 python3 tools/research_wiki.py slug "<concept>" 生成。

对每个种子,若 wiki/foundations/{slug}.md 已存在则跳过(不覆盖、不警告)。

Step 3: 从 Wikipedia 拉取背景

对每个剩余种子调用 tools/fetch_wikipedia.py

python3 tools/fetch_wikipedia.py summary "<title>"
python3 tools/fetch_wikipedia.py sections "<title>"
python3 tools/fetch_wikipedia.py section "<title>" --index <N>   # 拉取相关章节
  • summary 调用返回 {title, extract, url}
  • sections 调用返回 [{index, line, level}, ...] — 选取 line 包含 Variants / Types / Architecture / History / Limitations / Applications 的章节(大小写不敏感子串匹配)。
  • 任意调用退出码为 2 表示页面不存在 — 该种子回退到 LLM 知识,生成的 frontmatter 中 source_url: ""

Read the full file on GitHub · 161 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 161 lines · 28 tokens per session scan A 20a3c6395b78

Subscribe to this mod's changes

prefill is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,721 once invoked, about $0.0001 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

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

preregister

Draft a structured preregistration document (OSF, AsPredicted, or AEA RCT Registry style) from a research spec or free-form study description. Output is a Markdown file with hypotheses, design, sampling plan, analysis plan, exclusions, and inference criteria — annotated with MUST / SHOULD / MAY clarity flags. Use when…

pedrohcgs/claude-code-my-workflow · 153 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