By sciknow-io
Store, retrieve, and analyze scientific literature as a knowledge graph using TypeDB. Ingest papers and notes, run schema-driven graph queries combined with semantic search, and automate data pipelines from connected services for persistent context across sessions.
Brief description of what this skill does
Builds a large-scale structured personal context dataset in TypeDB from connected services, with minimal operator effort. The `aos-operator-profile` role (borne by `alh-person` via `alh-role-bearing`) is the hub all context links through.
TypeDB-backed ontological memory with schema-driven retrieval. Introspects the live knowledge graph schema, composes TypeQL queries dynamically, and combines graph traversal with embedding-based semantic search for three-stage retrieval (plan, execute, organize with provenance).
REQUIRED FIRST — starts TypeDB + dashboard via Docker, loads the Alhazen base schema. Must install before any other Alhazen skill.
Design and implement TypeDB-backed curation skills using the Skillful Alhazen methodology
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A TypeDB-powered agentic knowledge notebook — run interactively with Claude Code or deployed persistently via OpenClaw
Prototype software — APIs, schemas, and skill interfaces are subject to change without notice.
"The duty of the man who investigates the writings of scientists, if learning the truth is his goal, is to make himself an enemy of all that he reads, and, applying his mind to the core and margins of its content, attack it from every side."
— Ibn al-Haytham (Alhazen), 965–1039 AD
Skillful Alhazen is an agentic curation system with knowledge graph memory. The agent reads scientific papers, disease databases, job postings, news articles, and more — building structured understanding in a TypeDB knowledge graph that persists across sessions and grows over time.
Three layers work together:
Skills are not just prompts. Each skill contributes a typed schema namespace to the knowledge graph, a set of CLI commands the agent calls to read and write structured data, and (optionally) a Next.js dashboard for browsing what has been learned.
📖 Full documentation: github.com/GullyBurns/skillful-alhazen/wiki
Prerequisites: Claude Code, Docker, uv
git clone https://github.com/GullyBurns/skillful-alhazen
cd skillful-alhazen
make build # install deps + resolve skills + start TypeDB
claude # open Claude Code and start talking
Then just talk to Claude:
You: Search PubMed for papers about CRISPR delivery mechanisms and build a corpus
You: What are the pathophysiological mechanisms underlying Marfan syndrome?
You: Ingest this job posting: https://example.com/senior-ml-engineer
You: Remember that lipid nanoparticles are most effective for hepatic delivery
You: What skill gaps do I have across my top three job prospects?
Built into this repository (skills/ directory). Always available.
| Skill | What it does |
|---|---|
typedb-notebook | Core knowledge operations — remember facts, recall notes, create collections, tag entities, track schema gaps |
web-search | Web search via SearXNG (self-hosted metasearch, no API key needed) |
curation-skill-builder | Design and build new TypeDB-backed curation skills; 6-phase system design framework with TypeDB tracking |
tech-recon | Systematic investigation of software systems against user-defined success criteria |
Resolved from sciknow-io/alhazen-skill-examples and custom repositories. Cloned into local_skills/ on make build-skills.
| Skill | Domain | What it does | Dashboard |
|---|---|---|---|
scientific-literature | Biomedical research | Multi-source literature search (Europe PMC, PubMed, OpenAlex, bioRxiv/medRxiv) + semantic search via Voyage AI + Qdrant | — |
alg-precision-therapeutics | Rare disease | Investigate disease mechanism of harm and therapeutic landscape from a MONDO diagnosis | ✓ |
literature-trends | Research analysis | Trace how explanatory hypotheses evolve over time in a tagged literature corpus | — |
they-said-whaaa | Journalism | Track consistency of public figures — ingest transcripts and articles, extract claims, detect contradictions | ✓ |
jobhunt | Career | Track job applications — ingest postings, fit analysis, skill gap identification | ✓ |
dismech | Disease mechanisms | Browse the DisMech knowledge graph (750+ curated disease mechanism entries) | — |
| Mode | Setup | Best for |
|---|---|---|
| (A) Claude Code | make build && claude | Exploration, skill development, one-off research |
| (B) OpenClaw on Mac Mini | ./deploy/deploy.sh --target-type macmini | Persistent local service with Telegram triage |
| (C) OpenClaw on VPS | ./deploy/deploy.sh --target-type vps | Always-on, hardened production deployment |
See the Deployment guide for the A → B → C progression.
npx claudepluginhub sciknow-io/skillful-alhazen --plugin agent-os11 research-hub skills: literature triage matrix, context compression, project orientation, design dialog, multi-AI routing, NotebookLM brief verification, paper-memory builder, paper summarizer, Zotero curator, the gap-to-topic decision dossier, and the research-hub orchestrator. Auto-discovered from skills/<name>/SKILL.md.
A research infrastructure for AI agents. Search, read, and analyze papers from your local knowledge base while coding. Includes arXiv discovery, layered reading, ingestion, topic modeling, citation graphs, insights analytics, Office document inspection, scientific tool docs, and academic writing workflows. Requires Python 3.10+ and pip install.
Academic research agents — hypothesis generation, experiment design, paper drafting, peer review simulation, and more.
Semi-automated research assistant for academic research and software development, with skills for literature review, experiments, analysis, writing, and project knowledge management
Persistent knowledge graph for AI agents — typed entities, closed edge ontology, hybrid search, GQL queries.
Scientific writing, citations, grants, posters, and academic career (13 skills)