Skip to content
Get packs

Wiki Enrich

Fills in TODO summary sections of research-wiki paper pages using fetched paper abstracts and content.

Source Download skill
Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Stars
18,482
Licence
MIT
Files
1 file

What it does

After a literature-ingest step creates empty paper pages in a research wiki, this skill reads each page and fetches the paper's content from online sources (alphaxiv, deepxiv, arXiv, or fallback pages). It then rewrites the empty sections (thesis, method, results, limitations and so on) as short prose summaries, leaving protected sections like Connections and the original abstract untouched.

Great for

  • Researchers who have built a research-wiki with batch literature ingestion and want the paper pages filled in automatically
  • Students or analysts maintaining a literature knowledge base who want to avoid manually reading every paper for notes
  • Users already running the ARIS research toolkit who need a follow-up step after ingesting papers

Skip it if

  • Projects without a research-wiki/ folder, since the skill hard-fails without it and cannot run blind
  • Situations where summaries must be strictly accurate for publication, because generated prose from fetched abstracts may overstate or miss details and should be checked
  • Users who do not want the agent making network requests to paper hosts, since the skill fetches from external sources

Try asking

  • “enrich wiki”
  • “fill paper TODOs”
  • “/wiki-enrich vllm”
  • “/wiki-enrich missing --max 50”
Step-by-step guide: how to use Wiki EnrichInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    wiki-enrich.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip wiki-enrich.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip wiki-enrich.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Run /wiki-enrich vllm on a single paper first to check the quality of the generated summaries before a large batch.
  • Use the default missing target so already-filled papers are skipped and tokens are saved.
  • Keep the default 20-paper cap or set --max deliberately, since each paper costs fetch and token budget.

What's inside

  • SKILL.md

Redistributed unmodified from wanshuiyin/Auto-claude-code-research-in-sleep under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.