Imported from David-Li0406/meta-skill-evloving (skill-flow/data/skills-refined-agentskillos-36k/skillsmp/agent-survey-corpus/SKILL.md). Install upstream with npx skills add David-Li0406/meta-skill-evloving --skill agent-survey-corpus. Copyright stays with the author.

Agent Survey Corpus (arXiv PDFs → text extracts)

Name: agent-survey-corpus
Author: David-Li0406

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

Edit ref/agent-surveys/arxiv_ids.txt (one arXiv id per line).
Run the downloader to fetch PDFs and extract the first N pages to text.
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

python .codex/skills/agent-survey-corpus/scripts/run.py --help
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/:
- python .codex/skills/agent-survey-corpus/scripts/run.py --workspace . --max-pages 20
Download/extract into a specific folder (treated as workspace root):
- 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/).

{ "ocm": "1", "id": "david-li0406-meta-skill-evloving-agent-survey-corpus", "kind": "skill", "name": "agent-survey-corpus", "description": "Download a small corpus of open-access arXiv survey/review PDFs about LLM agents 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.", "publisher": "David-Li0406", "version": "1.0.0", "capabilities": { "domains": [ "coding" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Download a small corpus of open-access arXiv survey/review PDFs about LLM agents 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." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/David-Li0406/meta-skill-evloving", "path": "skill-flow/data/skills-refined-agentskillos-36k/skillsmp/agent-survey-corpus/SKILL.md", "ref": "ca3a335628981df10c36e00cb9850df2c247ab9a", "url": "https://github.com/David-Li0406/meta-skill-evloving/blob/ca3a335628981df10c36e00cb9850df2c247ab9a/skill-flow/data/skills-refined-agentskillos-36k/skillsmp/agent-survey-corpus/SKILL.md", "key": "David-Li0406/meta-skill-evloving/skill-flow/data/skills-refined-agentskillos-36k/skillsmp/agent-survey-corpus/SKILL.md" } }, "instructions": "# Agent Survey Corpus (arXiv PDFs → text extracts)\n\nGoal: create a small, local reference library so you can **learn from real agent surveys** when refining:\n- C2 outline structure (paper-like sectioning)\n- C4 tables/claims organization\n- C5 writing style and density\n\nThis is intentionally *not* part of the pipeline; it is an optional, repo-level toolkit.\n\n## Inputs\n\n- `ref/agent-surveys/arxiv_ids.txt`\n\n## Outputs\n\n- `ref/agent-surveys/pdfs/`\n- `ref/agent-surveys/text/`\n- `ref/agent-surveys/STYLE_REPORT.md` (tracked; auto-generated summary)\n\n## Workflow\n\n1) Edit `ref/agent-surveys/arxiv_ids.tx", "cost": { "context_tokens": 509 } }

agent-survey-corpus

About