llmwiki-collect
Ingest academic papers and blogs into a personal Markdown wiki, or validate reference archives, when requested by the user.
Skill by zedong-peng
Chalk Labs
Need help deploying llmwiki-collect?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zedong-peng-llmwiki-collect
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, research
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/llmwiki-collect
What's inside
- Skill name
llmwiki-collect- Description
- Ingest academic papers and blogs into a personal Markdown wiki, or validate reference archives, when requested by the user.
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (28)
- SKILL.md
- LICENSE · paper-search/
- README.md · paper-search/
- programmatic_api.md · paper-search/references/
- requirements.txt · paper-search/
- _env.py · paper-search/scripts/
- _http_runtime.py · paper-search/scripts/
- postprocess.py · paper-search/scripts/
- search_papers.py · paper-search/scripts/
- search_papers_by_arxiv.py · paper-search/scripts/
- search_papers_by_crossref.py · paper-search/scripts/
- search_papers_by_dblp.py · paper-search/scripts/
- search_papers_by_google_scholar.py · paper-search/scripts/
- search_papers_by_open_alex.py · paper-search/scripts/
- search_papers_by_openreview.py · paper-search/scripts/
- search_papers_by_semantic_scholar.py · paper-search/scripts/
- source_worker.py · paper-search/scripts/
- citation.bib · research-template/topic-template/assets/example-2000/
- .gitkeep · research-template/topic-template/assets/example-2000/github-repo/
- note.md · research-template/topic-template/assets/example-2000/
- .gitkeep · research-template/topic-template/assets/example-2000/paper-pdf/
- .gitkeep · research-template/topic-template/assets/example-2000/paper-tex/archives/
- .gitkeep · research-template/topic-template/assets/example-2000/paper-tex/extracted/
- index.md · research-template/topic-template/
- idea1.md · research-template/topic-template/threads/
- scaffold-template.md
- lint.py · scripts/
- search.md
SKILL.md (first lines)
Use the target wiki's AGENTS.md and existing conventions. - Search as needed: [search tools](search.md). - Floor: exclude arXiv-only papers with no code repository and no major-company or top-lab affiliation. Verify; missing metadata alone does not establish these. - Above the floor, skip work the topic would not cite: claims its own evidence does not support, or nothing beyond references already archived. - Report each skipped candidate with the reason. Flag a user-supplied reference instead of skipping it, unless the user agrees. - Archive layout and invariants: [template](scaffold-template.md). - Archive the PDF when available, even if reading TeX. - A blog with a corresponding paper: archive the paper; link the blog only if it adds evidence. Otherwise archive the blog as one PDF with images, no HTML/TXT copies. - Write `note.md` only after reading; separate paper claims, code observations, local reproduction, and interpretation. - Reference pages describe the source. Analysis for a particular project of the user's goes in that project's thread, which links the references. - After ingestion, update the topic index; the commit message is the log. - Validation means checking the layout invariants; report, and fix only with approval. - Do not execute downloaded research code or its install/build scripts, upload private material, or delete, commit, or publish wiki content without authorization.
From zedong-peng/llmwiki-skill, MIT.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 18, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/zedong-peng/llmwiki-skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zedong-peng
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get llmwiki-collect running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
llmwiki-collect skill. Agent Mart. https://agentmart.dev/skills/zedong-peng-llmwiki-collect (last updated 2026-10-24)