research-wiki
Research Wiki maintains a structured, project-level knowledge base that grows smarter as you add papers, test ideas, run experiments, and capture findings. Every entry connects through typed relationships—papers extend or contradict each other, ideas get tested by experiments, claims gain proof status—so your research compounds rather than scatters. Initialize once, keep it current, query it to avoid re-deriving insights.
Research Wiki builds a persistent knowledge base that accumulates papers, ideas, experiments, and claims across your entire research lifecycle.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-22
Research Wiki builds a persistent knowledge base that accumulates papers, ideas, experiments, and claims across your entire research lifecycle. Research Wiki maintains a structured, project-level knowledge base that grows smarter as you add papers, test ideas, run experiments, and capture findings. Every entry connects through typed relationships—papers extend or contradict each other, ideas get tested by experiments, claims gain proof status—so your research compounds rather than scatters. Initialize once, keep it current, query it to avoid re-deriving insights.
Use it when
- Research Wiki's init command creates your persistent knowledge base structure at the project level.
- Research Wiki supports ingesting arxiv papers with metadata and relationships through its sync and backfill workflows.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
wanshuiyin/Auto-claude-code-research-in-sleep/research-wiki · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is research-wiki and what does it do?
Research Wiki maintains a structured, project-level knowledge base that grows smarter as you add papers, test ideas, run experiments, and capture findings. Every entry connects through typed relationships—papers extend or contradict each other, ideas get tested by experiments, claims gain proof status—so your research compounds rather than scatters. Initialize once, keep it current, query it to avoid re-deriving insights.
How do I set up research-wiki and run the init command?
Research Wiki's init command creates your persistent knowledge base structure at the project level. Once initialized, you can begin adding papers, ideas, and experiments. The setup establishes the foundation for accumulating research artifacts and their relationships, enabling you to query and track your work as it grows.
How can I ingest arxiv papers into my research wiki?
Research Wiki supports ingesting arxiv papers with metadata and relationships through its sync and backfill workflows. You can add papers by arxiv ID, and the system organizes them with their connections to other entries in your knowledge base. This lets you build a comprehensive paper graph without manual entry overhead.
How do I query my research knowledge base and retrieve connections?
Research Wiki lets you query and retrieve structured research knowledge with relationships and connections. You can search across papers, ideas, and experiments to discover how they relate—which papers extend or contradict each other, which ideas have been tested, and which claims have proof status. This prevents re-deriving the same research paths.
Can research-wiki track failed ideas and prevent duplicate work?
Yes. Research Wiki tracks failed ideas and prevents re-deriving the same research paths by maintaining a persistent memory of what you've already explored. When you query your knowledge base, you can see which approaches didn't work, helping you avoid repeating dead ends and focus on new directions.
What verification and linting tools does research-wiki provide?
Research Wiki includes lint checks to verify your knowledge base for orphans, contradictions, and stale claims. You can also generate statistics overviews and gap maps to understand coverage and identify areas needing attention. These tools help keep your research wiki accurate and complete as it grows.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Research Wiki: Persistent Research Knowledge Base
Subcommand: $ARGUMENTS
Overview
The research wiki is a persistent, per-project knowledge base that accumulates structured knowledge across the entire ARIS research lifecycle. Unlike one-off literature surveys that are used and forgotten, the wiki compounds — every paper read, idea tested, experiment run, and review received makes the wiki smarter.
Inspired by Karpathy's LLM Wiki pattern: compile knowledge once, keep it current, don't re-derive on every query.
Core Concepts
Four Entity
(truncated - see the full file via the links below)
File tree — 1 file
skills/research-wiki/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Build and maintain a persistent research knowledge base that accumulates papers, ideas, and experiments”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
wiki-enrich completes scaffolded research papers by fetching content from multiple sources and rewriting 10 fillable TODO sections into concise prose. It preserves protected sections like Connections and Abstract (original), respects the --force flag for selective overwrites, and caps batches at 20 papers per run to manage token budgets.
arxiv lets you search the arXiv repository by keyword or paper ID, then download full PDFs and view complete metadata including authors, abstract, and publication date. Results display in a sortable table format, and papers can be saved to a local directory for offline access.
AlphaXiv delivers instant, machine-readable summaries of individual papers from arXiv, optimized for language models. When the overview isn't enough, it cascades to full markdown and LaTeX source inspection for deeper details. Ideal for explaining a specific paper—not for broad literature discovery.
Exa Search performs broad web searches across blogs, news, research papers, and company sites with automatic content extraction. Query results return highlights, summaries, or full text alongside metadata like publication dates and authors. Use it when you need web-wide coverage beyond academic databases.
DeepXiv enables layered exploration of open-access research papers, letting you search by topic or ID and read specific sections without loading entire documents. It supports trending paper discovery, web search, and integrates with Semantic Scholar metadata for citation context.
research-lit discovers research papers on any topic by searching your personal library, Zotero collections, local PDFs, and academic web sources in one query. It extracts key ideas, pulls annotations, and generates summaries to accelerate literature review work. Configure which sources to prioritize or download papers directly to your collection.
More skills openalex (MIT) · deep-research (MIT) · Alibabacloud Bailian Rag Knowledgebase (unlicensed)