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/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/ingest)<a href="https://agentmods.dev/skills/lambenthan/empiricalwiki/ingest"><img src="https://agentmods.dev/badge/skills/lambenthan/empiricalwiki/ingest.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.04544 |
| Opus 5 | $0.00036 | $0.02272 |
| Sonnet 5 | $0.00015 | $0.00909 |
| Haiku 4.5 | $0.00007 | $0.00454 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ingest
把一篇论文转化成一组正确链接的 wiki 页面。/ingest 的职责是写出 well-shaped 的实体与正确的双向链接；语义层面的审计（反向链接对称性、dangling node、字段取值合规）留给 /check。
按需打开下列本地参考文件：
references/pdf-preprocessing.md—— 直接 PDF 输入时的 arXiv-ID 恢复、tex 抓取、prepare-paper 交接流程references/dedup-policy.md—— concept / claim 的合并与新建决策规则，以及/ingest形状检查与/check语义审计的边界references/cross-references.md—— 正向/反向链接矩阵与 paper-to-paper edge 类型选择references/init-mode.md——/init的 manifest 交接与并行安全约束references/error-handling.md—— 来源解析、API 与 slug 冲突的 fallback
在撰写任何 wiki 页面 frontmatter 或正文章节前，先打开 docs/runtime-page-templates.zh.md；需要 index.md、log.md 或 graph/ 格式时，打开 docs/runtime-support-files.zh.md。
Inputs
source：四种之一 —— arXiv URL（例如https://arxiv.org/abs/2106.09685）、本地.tex、本地.pdf、或/init通过.checkpoints/init-sources.json交接的canonical_ingest_path（见references/init-mode.md）--discover（可选，默认 关闭）：在最终 report 之后调用/discover --anchor <this-paper's-arxiv-id>，把 shortlist 作为 "接下来可能想 ingest 的相关论文" 附在 report 里。从不自动 ingest 推荐结果。INIT MODE 下自动跳过。视为用户可见参数：不得仅根据仓库状态擅自开启。
Outputs
- 一篇完整链接的论文页面及其关联实体（concepts、claims、people）
- 通过
tools/research_wiki.py追加的 graph edges 与 citations - 终端汇总报告（新增页面数、建议后续 ingest 的论文）
Wiki Interaction
Reads
wiki/index.md，用于获取所有已存在 slug 与 tagwiki/papers/*.md，用于识别已 ingest 过的论文wiki/concepts/*.md、wiki/foundations/*.md，用于 dedup 匹配wiki/claims/*.md，用于 dedup 匹配wiki/people/*.md，用于识别已有作者wiki/topics/*.md，用于将论文归入已有 topicwiki/graph/open_questions.md，用于识别论文是否填补了已知 gap
Writes
wiki/papers/{slug}.md—— CREATEwiki/concepts/{slug}.md—— CREATE（新建）或 EDIT（追加key_papers、aliases、variants）wiki/claims/{slug}.md—— CREATE（新建）或 EDIT（追加evidence条目）wiki/people/{slug}.md—— CREATE（仅当 importance ≥ 4）或 EDIT（追加Key papers）wiki/topics/{slug}.md—— 只允许 EDIT，/ingest不得 CREATE 新 topicwiki/graph/edges.jsonl—— 通过工具 APPENDwiki/graph/citations.jsonl—— 通过工具 APPENDwiki/graph/context_brief.md—— REBUILD（INIT MODE 下跳过）wiki/graph/open_questions.md—— REBUILD（INIT MODE 下跳过）wiki/index.md—— APPENDwiki/log.md—— 通过工具 APPEND
What ships with it
5 files 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.
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.
- 8d ago First seen · 268 lines · 73 tokens per session scan A d4908c9bbf5f
ingest is a skill published in the GitHub repository Lambenthan/empiricalwiki (82 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 4,544 once invoked, about $0.0004 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
patent-reader
A plain-language reader for Chinese patents that turns a publication number or PDF into notes, diagrams, and an Obsidian entry. Obsidian is a note-taking app that stores linked Markdown files.
compile-latex
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when user says "compile", "build the slides", "rebuild the PDF", "run latex", "render the tex", or asks why a .tex file isn't producing a PDF. Operates on Slides/.tex.
wechat-article-ingest
A tool that converts public WeChat Official Account articles, or PDF copies of them, into Markdown notes. It can also extract the article's main viewpoints and create linked questions for further thinking.
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
jangbu-import
A data-import workflow for turning bank files, card records, spreadsheets, receipts, tax invoices, and statement PDFs into a standard set of 13 transaction fields. OCR, or optical character recognition, is used to read information from document images and PDFs.
markdown-to-pdf
Convert Markdown (.md) files to a polished PDF with ALL images preserved and scaled to the page. Use whenever the user asks to "save this markdown as a PDF", "convert README.md to pdf", "export the .md as a pdf", "turn these notes/docs into a PDF", or wants a PDF deliverable of any GitHub-flavored Markdown document…