agentleFS
Sign inStart free
Google CloudKnown publisherGoogleCloudPlatform/LifeSciences/applications/open-agentic-science-engine/skills/hypex-tool-setup/SKILL.md

hypex-tool-setup

Skill53 starsChanged 55 days agoApache-2.0View on GitHub

Activate and verify the OASE-provisioned Hypex tools before running a hypothesis-exploration workflow.

Create a free account to mount
Files
SKILL.md

Hypex Tool Setup in OASE

The OASE bootstrapper provisions hypex, elo, and prox from the source vendored in applications/open-agentic-science-engine/tools/vendor/hypex. Literature access is part of the oase CLI; there is no separate lit executable in OASE.

Activate

Source the generated environment file, not the venv activation script:

source /scion-volumes/tools/env.sh

This activates the OASE venv, adds /scion-volumes/tools/bin to PATH, sets OASE_TOOLS_HOME, and selects the provisioned environment stamp.

Verify

oase doctor --json
hypex --help
elo --help
prox --help

oase doctor must report binary hypex, binary elo, binary prox, and hypothesis strategy: hypex as ok. A missing or non-runnable command is a capability failure. Report it to the supervisor; do not build tools ad hoc in a worker container or install packages into the shared venv.

Tool Inventory

ToolProvisioningPurpose
oaseOASE Python packageLiterature, citations, Hypex ingest/analyze, and OASE artifacts
hypexVendored Go sourceHypothesis datastore lifecycle and schema validation
eloVendored Go sourceTournament pairings, ratings, and standings
proxVendored Python sourceSimilarity, clustering, and near-duplicate detection

The bootstrapper is the only owner of provisioning. Repair a missing tool by re-running applications/open-agentic-science-engine/tools/install.sh; --binaries-only is suitable when the full Python environment, including prox dependencies, already exists.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free