Home / terrylica / cc-skills · plugins/arxiv-source-first/skills/arxiv-source-first-paper-ingest/SKILL.md · GitHub

arxiv-source-first-paper-ingest skillA

arxiv-source-first-paper-ingest is agent-read markdown (skill) from terrylica/cc-skills: Read an arXiv paper faithfully by fetching the authors' own LaTeX source instead of OCR-ing the PDF. Extracts every display equation with its label, environment and enclosing proposition, renders each to MathML, and proves usability by compiling each formula with a real TeX engine. Use when you need a paper's formulas exactly — to replicate a method, implement a loss function or custom objective, verify a quoted number, or check a claim against what the authors actually wrote. TRIGGERS - read th.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# arXiv source-first paper ingest

> **Self-Evolving skill.** If a step here fails or the tooling drifts, fix this file in the same
> change. The Post-Execution Reflection at the bottom says what to check.

**The whole idea in one line: for an arXiv paper, the PDF is a rendering of something you can get
losslessly, so do not read the rendering.**

`arxiv.org/e-print/<id>` serves the authors' own LaTeX. It carries the exact formulas, their
`\label`s, and — critically — which formulas are _stated propositions_ rather than intermediate
steps inside a proof. None of that survives into a PDF, so no vision model can recover it.

Measured on one real paper, OCR of the PDF reached **0.958 mean token similarity** to the source and
**only 49 % of its formulas compiled**, against 98 % for the source. Full numbers, including a
systematic model defect that similarity cannot see, in
[`../../references/OCR-VERSUS-AUTHOR-LATEX-GROUND-TRUTH.md`](../../references/OCR-VERSUS-AUTHOR-LATEX-GROUND-TRUTH.md).

---

## Step 1 — fetch the source, not the PDF

Identify yourself; arXiv asks for it and rate-limits anonymous bulk access.

```bash
ID=2605.00501
UA="your-project/1.0 (mailto:you@example.com)"
…

Read the whole file at its exact version.

How to install

Latest version
mdr add terrylica/cc-skills/arxiv-source-first-paper-ingest@git:20260731.1bd7c64
Exact content
mdr add terrylica/cc-skills/arxiv-source-first-paper-ingest@sha256:6bec80e59461fc80

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ic7eo5qlpbxnqd6d.svg)](https://markdownregistry.com/a/art_ic7eo5qlpbxnqd6d)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260731.1bd7c64 latest2026-07-31 1bd7c64 5,832 BA view · diff
git:20260731.46704862026-07-31 4670486 5,833 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5832 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

terrylica/cc-skills · 74 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ic7eo5qlpbxnqd6d
GET https://markdownregistry.com/api/v1/resolve?ref=terrylica/cc-skills/arxiv-source-first-paper-ingest
GET https://markdownregistry.com/api/v1/blob/6bec80e59461fc80523969c6a0baaf87061528a0e37c0bb992dceeaed15b8369

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from terrylica/cc-skills

CLAUDE.md claude
terrylica/cc-skills · CLAUDE.md
git:20260920.d5f6026 · audit A · 74 stars
CLAUDE.md@docs claude
terrylica/cc-skills · docs/CLAUDE.md
git:20260903.abf94c3 · audit A · 74 stars
CLAUDE.md@docs/design claude
terrylica/cc-skills · docs/design/CLAUDE.md
git:20260903.3d243d7 · audit A · 74 stars
CLAUDE.md@plugins claude
terrylica/cc-skills · plugins/CLAUDE.md
git:20260920.d5f6026 · audit A · 74 stars
CLAUDE.md@plugins/agent-reach claude
terrylica/cc-skills · plugins/agent-reach/CLAUDE.md
git:20260722.52c9284 · audit A · 74 stars
agent-reach skill
terrylica/cc-skills · plugins/agent-reach/skills/agent-reach/SKILL.md · Give your AI agent eyes to see the entire internet. 17 platforms via CLI, MCP, curl, and Python scripts. Zero config…
git:20260527.fb73e18 · audit A · 74 stars
CLAUDE.md@plugins/arxiv-source-first claude
terrylica/cc-skills · plugins/arxiv-source-first/CLAUDE.md
git:20260822.291af0a · audit A · 74 stars
CLAUDE.md@plugins/asciinema-tools claude
terrylica/cc-skills · plugins/asciinema-tools/CLAUDE.md
git:20260812.1b1cc81 · audit A · 74 stars
analyze skill
terrylica/cc-skills · plugins/asciinema-tools/skills/analyze/SKILL.md · Semantic analysis of converted recordings. TRIGGERS - analyze cast, keyword extraction, find patterns.
git:20260401.b664eaf · audit A · 74 stars
asciinema-analyzer skill
terrylica/cc-skills · plugins/asciinema-tools/skills/asciinema-analyzer/SKILL.md · Semantic analysis of asciinema recordings. TRIGGERS - analyze cast, keyword extraction, find patterns in recordings.
git:20260401.b664eaf · audit A · 74 stars
asciinema-cast-format skill
terrylica/cc-skills · plugins/asciinema-tools/skills/asciinema-cast-format/SKILL.md · Asciinema v3 .cast file format reference. TRIGGERS - cast format, asciicast spec, event codes, parse cast file.
git:20260401.b664eaf · audit A · 74 stars
asciinema-converter skill
terrylica/cc-skills · plugins/asciinema-tools/skills/asciinema-converter/SKILL.md · Convert .cast recordings to .txt for analysis. TRIGGERS - convert cast, cast to txt, strip ANSI, batch convert.
git:20260401.b664eaf · audit A · 74 stars

Every file in terrylica/cc-skills

Browse by kind, by grade A, or by owner.