Research Workbench — Development skill for Claude Code
Use when running a formal research project on typed research records — creating a project, importing sources, capturing evidence with locators, building supported claims, auditing provenance, and gene.
How to install Research Workbench
Installs to ~/.claude/skills/cavi-ai-obsidian-agent-research-workbench/SKILL.md
mkdir -p ~/.claude/skills/cavi-ai-obsidian-agent-research-workbench && curl -fsSL https://raw.githubusercontent.com/cavi-ai/obsidian-agent/HEAD/commands/research-workbench.md -o ~/.claude/skills/cavi-ai-obsidian-agent-research-workbench/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Research Workbench does
description: Use when running a formal research project on typed research records — creating a project, importing sources, capturing evidence with locators, building supported claims, auditing provenance, and generating an evidence-backed outline via the research_* tools. argument-hint: "[project, source, question, or desired stage]"
Claude compatibility adapter
Invoke **`obsidian-agent:research-workbench`** with the user's arguments:
`$ARGUMENTS`
Follow that canonical skill exactl
Alternatives in Development
- Supported Languages — 22.1k ★
- IPolloWork — Enterprise-grade, local-first Agent Workbench for people and agent teams 4.9k ★
- Chiasmus — Chiasmus is an MCP server that gives language models access to formal verification 208 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Source Digest
Use when comparing notes that are typed or tagged as sources or papers, building an evidence or comparison tab
Ques Source
Find, evaluate, cross-check, and document sources for research claims. Assess provenance, authority, recency,
Enrich Person
Resolve the person at {{linkedin_url}} and verify employment at {{company_domain}} using public sources. Prese
Source Ingestion
Skill for ingesting raw sources into the knowledge base with proper storage, metadata, and provenance tracking
System One Models Getting Started
TypeSafe's System One launch claims, each as a runnable experiment: Jev vs Claude vs keyword rules through one
Context Graph
Evidence-first Knowledge Engineering Skill for Codex and Claude Code—turning sources into traceable records, v
Related Agents
Wiki Extract
Read-only worker: read one chunk of one document and return what it says as an Item Map (subjects with their k
Po Steward
Steward seat on the Atlas PO Council. Sole owner of ontology and agent value; protects typed meaning, provenan
Asset Curator
Resolves named AI and tool identities to exact user-supplied, original-owner, pinned Vibe SVGs, or verified Lo