AG

agent-survey-corpus

Collects and extracts agent-focused academic surveys for style learning.

Install

mkdir -p .claude/skills/agent-survey-corpus && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13008" && unzip -o skill.zip -d .claude/skills/agent-survey-corpus && rm skill.zip

Installs to .claude/skills/agent-survey-corpus

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning. **Trigger**: agent survey corpus, ref corpus, download surveys, 学习综述写法, 下载 survey. **Use when**: you want to study how real agent surveys structure sections (6–8 H2), size subsections, and write evidence-backed comparisons. **Skip if**: you cannot download PDFs (no network) or you don't want local PDF files. **Network**: required. **Guardrail**: only download arXiv PDFs; store under `ref/` and keep large files out of git.
548 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Download open-access arXiv survey PDFs related to agentic systems
  • Extract text from downloaded PDFs
  • Generate a `STYLE_REPORT.md` summary
  • Support learning from real agent surveys for documentation structure
  • Allow specification of maximum pages to extract from PDFs

How it works

The skill reads arXiv IDs from a text file, then downloads the corresponding PDFs and extracts text from a specified number of pages.

Inputs & outputs

You give it
`ref/agent-surveys/arxiv_ids.txt` with arXiv IDs
You get back
PDFs in `ref/agent-surveys/pdfs/`, text extracts in `ref/agent-surveys/text/`, and `ref/agent-surveys/STYLE_REPORT.md`

When to use agent-survey-corpus

  • Studying survey structure
  • Improving documentation writing style
  • Researching academic writing patterns
  • Building a reference library

About this skill

Agent Survey Corpus (arXiv PDFs → text extracts)

Goal: create a small, local reference library so you can learn from real agent surveys when refining:

  • C2 outline structure (paper-like sectioning)
  • C4 tables/claims organization
  • C5 writing style and density

This is intentionally not part of the pipeline; it is an optional, repo-level toolkit.

Inputs

  • ref/agent-surveys/arxiv_ids.txt

Outputs

  • ref/agent-surveys/pdfs/
  • ref/agent-surveys/text/
  • ref/agent-surveys/STYLE_REPORT.md (tracked; auto-generated summary)

Workflow

  1. Edit ref/agent-surveys/arxiv_ids.txt (one arXiv id per line).
  2. Run the downloader to fetch PDFs and extract the first N pages to text.
  3. Skim the extracted text under ref/agent-surveys/text/:
    • look at section counts (H2), subsection granularity (H3), and how they transition between chapters.
    • identify repeated rhetorical patterns you want the pipeline writer to imitate.

Script

Quick Start

  • uv run python .codex/skills/agent-survey-corpus/scripts/run.py --help
  • uv run python .codex/skills/agent-survey-corpus/scripts/run.py --workspace . --max-pages 20

All Options

  • --workspace <dir> (use . to write into repo root)
  • --inputs <semicolon-separated> (default: ref/agent-surveys/arxiv_ids.txt)
  • --max-pages <N> (default: 20)
  • --sleep <seconds> (default: 1.0)
  • --overwrite (re-download + re-extract)

Examples

  • Download/extract into repo root ref/:
    • uv run python .codex/skills/agent-survey-corpus/scripts/run.py --workspace . --max-pages 20
  • Download/extract into a specific folder (treated as workspace root):
    • uv run python .codex/skills/agent-survey-corpus/scripts/run.py --workspace /tmp/surveys --max-pages 30

Troubleshooting

  • Download fails / timeout: rerun with a larger --sleep, or try fewer ids.
  • Text extract is empty: the PDF may be scanned; try another survey or increase --max-pages.
  • Files showing up in git status: PDFs/text are ignored via .gitignore (ref/**/pdfs/, ref/**/text/).

When not to use it

  • When network access is unavailable to download PDFs
  • When local PDF files are not desired

Limitations

  • Only downloads arXiv PDFs
  • Requires network access
  • Text extraction may be empty if the PDF is scanned

How it compares

This skill automates the process of collecting and preparing academic survey data for analysis, unlike manual downloading and text extraction.

Compared to similar skills

agent-survey-corpus side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
agent-survey-corpus (this skill)02moReviewBeginner
citation-management237moReviewBeginner
microsoft-docs105moReviewBeginner
peer-review117moReviewAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

citation-management

davila7

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

2395

microsoft-docs

github

Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work. Use for Azure, .NET, Microsoft 365, Windows, Power Platform, and all Microsoft technologies. Get accurate, current information from learn.microsoft.com and other official Microsoft websites—architecture overviews, quickstarts, configuration guides, limits, and best practices.

1059

peer-review

davila7

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards, for manuscript and grant review across disciplines.

1146

notion-research-documentation

openai

Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

551

context7-auto-research

davila7

Automatically fetch latest library/framework documentation for Claude Code via Context7 API

550

fact-check

leonardomso

Verify technical accuracy of JavaScript concept pages by checking code examples, MDN/ECMAScript compliance, and external resources to prevent misinformation

746

Search skills

Search the agent skills registry