empiricalwiki: Skill for Claude Code

.claude/skills/theory-ingest/SKILL.md

theory-ingest is a skill for Claude Code from Lambenthan/empiricalwiki. It costs 54 tokens per session (1,804 once invoked), scanned A, original, MIT.

A tool that turns a theory paper into reusable research-wiki entries. It records the model's assumptions, solution concept, results, proofs, comparative predictions, and predictions that can be tested with data.

In plain words
What is it for?
Use it with a local PDF or LaTeX source to create paper, assumption, proposition, hypothesis, mechanism, and foundation pages, plus links and a project log.
Why use it?
It breaks a dense mathematical paper into consistent pieces that can be reused across later research. It also links the theory to empirical research in the same knowledge graph.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 →

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/theory-ingest/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 theory-ingest

README.md
[![agentmods](https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/theory-ingest/github.svg)](https://agentmods.dev/skills/lambenthan/empiricalwiki/theory-ingest)
Your own site
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/theory-ingest"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/theory-ingest/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 theory-ingest

Your own site · 80×15
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/theory-ingest"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/theory-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,804 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 $0.00054 $0.01804
Opus 5 $0.00027 $0.00902
Sonnet 5 $0.00011 $0.00361
Haiku 4.5 $0.00005 $0.00180

Measured 11d ago against content hash 620b965c9c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

theory-ingest 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 11d 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/theory-ingest/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/theory-ingest

把一篇理论建模论文拆成可复用的研究资产。对着「理论建模通用骨架」的 6 个固定槽位抽取:环境/原语、解概念、结果、论证、比较静态、可检验推论。形式化陈述逐字引用,禁止释义。

Inputs

  • source: 本地 .pdf.tex,或 /init 预处理后的 raw/tmp/... 路径。
  • --topic 可选:当前项目主题,如“管理者短视与耐心资本”。

Outputs

  • wiki/papers/{slug}.mdpaper_kind: theory
  • 按需新建或更新:
    • wiki/assumptions/*.md
    • wiki/propositions/*.md
    • wiki/hypotheses/*.md(模型导出的可检验推论)
    • wiki/mechanisms/*.md(填 ## Theoretical Logic,与实证层共享)
    • wiki/foundations/*.md(解概念、证明框架等可复用规范知识)
  • wiki/index.mdwiki/log.md
  • wiki/graph/edges.jsonl

Workflow

Step 1: Resolve Source

确认工作目录是项目根目录,包含 wiki/raw/tools/

优先使用 .venv

if [ -x .venv/bin/python ]; then PYTHON_BIN=.venv/bin/python; else PYTHON_BIN=python3; fi

理论论文公式密集,.tex 优先:有 .tex 源码就用源码,公式不会被 PDF 解析毁掉。只有 PDF 时先人工读第一页标题:

"$PYTHON_BIN" - "<source>" <<'PY'
import sys, fitz
doc = fitz.open(sys.argv[1])
print(doc[0].get_text("text")[:2000])
PY

然后运行:

"$PYTHON_BIN" tools/prepare_paper_source.py --raw-root raw --source <source> --title "<confident-title>"

把返回的 prepared_path 作为正文读取入口。

Step 2: Extract Along the 6-Slot Skeleton

先打开 docs/runtime-theory-skeleton.zh.md,对着 6 个固定槽位抽取。没有明确证据写“未报告”,不猜:

  1. 环境 / 原语:参与人、行动/策略空间、偏好/支付函数、信息结构、时序、技术/约束
  2. 解概念:均衡概念(Nash / 子博弈精炼 / 贝叶斯精炼 / 竞争均衡 …)
  3. 结果:每个命题/定理/引理的形式化陈述 + 成立条件
  4. 论证:每个结果的证明技术
  5. 比较静态:内生量随参数怎么动
  6. 可检验推论:模型导出的、可拿去实证的符号关系

理论论文没有 variables/datasets/identification/robustness——这些不是填“未报告”,而是整块不存在。这是与 /empirical-ingest 的根本分流。

Step 3: Write Pages

打开 docs/runtime-page-templates.zh.md,按模板写页面。

papers/{slug}.mdpaper_kind: theory,填 theory block,正文用理论段落:

## 研究问题
## 模型环境
## 核心假设
## 解概念
## 命题与证明
## 比较静态
## 可检验推论
## 对实证的启发
## Related
  • 每条核心假设 → assumptions/formal_statement 逐字引用原文
  • 每个命题/定理 → propositions/formal_statement 逐字引用,conditions 写清成立条件,proof_technique 查不到写“未报告”
  • 每条可检验推论 → hypotheses/status: literature_supported
  • 模型形式化的经济机制 → 查重后更新 mechanisms/## Theoretical Logic 段;不要新造与实证侧重复的机制页
  • 解概念、证明框架等可复用规范知识 → foundations/(终端节点,不写反向链接)

Read the full file on GitHub · 140 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. 11d ago First seen · 140 lines · 54 tokens per session scan A 620b965c9c70

Subscribe to this mod's changes

theory-ingest is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,804 once invoked, about $0.0003 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

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

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

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