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.
curl -O https://raw.githubusercontent.com/Lambenthan/empiricalwiki/main/.claude/skills/empirical-ingest/SKILL.mdgit clone --depth 1 https://github.com/Lambenthan/empiricalwikiWrote 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.
[](https://agentmods.dev/skills/lambenthan/empiricalwiki/empirical-ingest)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/empirical-ingest"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/empirical-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.
<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/empirical-ingest"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/empirical-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00049 | $0.01336 |
| Opus 5 | $0.00024 | $0.00668 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
empirical-ingest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/empirical-ingest
把一篇实证论文拆成可复用的研究设计资产。它不是普通摘要工具;优先抽取变量、数据、模型、机制、识别和稳健性,再写通用概念。
Inputs
source: 本地.pdf、.tex,或/init预处理后的raw/tmp/...路径。--topic可选:当前项目主题,如“耐心资本与 ESG”。
Outputs
wiki/papers/{slug}.md- 按需新建或更新:
wiki/variables/*.mdwiki/datasets/*.mdwiki/models/*.mdwiki/mechanisms/*.mdwiki/hypotheses/*.mdwiki/identification/*.mdwiki/robustness/*.mdwiki/heterogeneity/*.mdwiki/tables/*.md(仅当用户明确要求逐表复现时创建;默认把关键表格及结论写进论文卡,不单独建页)
wiki/index.md、wiki/log.mdwiki/graph/edges.jsonl
Workflow
Step 1: Resolve Source
确认工作目录是项目根目录,包含 wiki/、raw/、tools/。
优先使用 .venv:
if [ -x .venv/bin/python ]; then PYTHON_BIN=.venv/bin/python; else PYTHON_BIN=python3; fi
如果输入是 PDF,先人工读取第一页标题。中文 PDF 可以用 PyMuPDF 快速抽取:
"$PYTHON_BIN" - "<source>" <<'PY'
import sys, fitz
path = sys.argv[1]
doc = fitz.open(path)
print(doc[0].get_text("text")[:2000])
PY
然后运行:
"$PYTHON_BIN" tools/prepare_paper_source.py --raw-root raw --source <source> --title "<confident-title>"
把返回的 prepared_path 作为正文读取入口。若标题不确定,不传 --title。
Step 2: Extract Empirical Facts
从论文中抽取以下字段。没有明确证据时写“未报告”,不要猜:
- 研究问题
- 理论机制
- 研究假设
- 样本区间、样本范围、样本筛选规则
- 数据来源和数据库表
- 被解释变量、核心解释变量、中介变量、调节变量、控制变量、工具变量
- 变量测算公式、分组规则、缩尾规则
- 主模型、固定效应、标准误聚类方式
- 内生性处理
- 机制检验、异质性检验、稳健性检验
- 关键表格及结论
- 可复现线索:变量名、数据库、Stata 处理步骤
Step 3: Write Pages
打开 docs/runtime-page-templates.zh.md,按模板写页面。
写 papers/{slug}.md 时,正文必须包含:
## 研究问题
## 理论机制
## 研究假设
## 数据与样本
## 变量设定
## 模型设定
## 主要结果
## 机制检验
## 异质性检验
## 稳健性检验
## 内生性处理
## 可复现线索
## 对我当前选题的启发
## Related
对每个核心变量、数据源、模型、机制和检验方法,先查重再创建新页面:
"$PYTHON_BIN" tools/research_wiki.py slug "<title>"
已有等价页面时更新,不重复造近义页面。
Step 4: Add Graph Edges
用工具写图谱关系,不手动编辑 wiki/graph/edges.jsonl:
"$PYTHON_BIN" tools/research_wiki.py add-edge wiki --from papers/<paper> --to variables/<variable> --type operationalizes --confidence high --evidence "<evidence>"
"$PYTHON_BIN" tools/research_wiki.py add-edge wiki --from papers/<paper> --to datasets/<dataset> --type uses_dataset --confidence high --evidence "<evidence>"
"$PYTHON_BIN" tools/research_wiki.py add-edge wiki --from papers/<paper> --to models/<model> --type estimates_model --confidence high --evidence "<evidence>"
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.
- 12d ago First seen · 143 lines · 49 tokens per session scan A 12e4c8302a59
empirical-ingest is a skill published in the GitHub repository Lambenthan/empiricalwiki (84 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 1,336 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.
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…
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.
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…
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…
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…
simulation-study
Scaffold and run a reproducible Monte Carlo simulation study in R — a declared assumption regime, a parameterized DGP, an estimator grid, a seeded replication loop, and a summary of bias, RMSE, empirical SE, coverage, size/power with Monte Carlo standard errors. Use when the user says "run a Monte Carlo simulation"…