Skip to content
Agentmart
Submit a tool

biomedical-evidence-search

Use for variant, gene, trait, eQTL/PheWAS, score, or literature lookups via biomedical_search.

Skill by sounkou-bioinfo

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying biomedical-evidence-search?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sounkou-bioinfo-biomedical-evidence-search

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use for variant, gene, trait, eQTL/PheWAS, score, or literature lookups via biomedical_search.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 2, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/biomedical-evidence-search

What's inside

Skill name
biomedical-evidence-search
Description
Use for variant, gene, trait, eQTL/PheWAS, score, or literature lookups via biomedical_search.
License
MIT
Instructions
35 lines in SKILL.md · view on GitHub

Files (4)

  • SKILL.md
  • gpmapr.md · references/
  • resources.md · references/
  • upstream-port.md · references/

SKILL.md (first lines)

# Biomedical evidence search

Use the single `biomedical_search` tool, not a new per-provider skill or client.
`list` discovers providers; `describe` gives a provider's current operations and
arguments; `call` runs 1–12 fixed read-only operations. Describe unfamiliar
contracts instead of guessing names. Reuse an already-observed contract within
the task rather than rediscovering it before every call.

Resolve identifiers and assembly before coordinate queries. Batch independent
calls when useful; bound pagination with `max_pages` (1–20). Partial failures and
page/byte limits must remain visible. Profiles are routing metadata, not a
network sandbox; the host's network policy remains authoritative.

## Load the reference for the question

- Source selection, provider-specific semantics, or ontology-wide GWAS SNP
  enumeration: [provider contracts](references/resources.md). For enumeration,
  claim "all" only when `complete=true`; otherwise report the retrieved extent.
- gpmapr uploads or archive/TSV workflows: [R package guide](references/gpmapr.md).
  The search tool itself is read-only.
- Imported-client compatibility or provenance: [upstream port](references/upstream-port.md).

## Evidence contract

Summarize returned payloads with provider/operation, arguments, identifiers and
assembly, pagination extent, source URLs, limitations, and failed calls. Do not
force heterogeneous scores, p-values, effect directions, or evidence classes into
a common schema. Abstain where missing evidence would require guessing.

Europe PMC supports literature discovery; LitVar2 indexes variant publications.
LitVar2 API results do **not** substantiate web-interface snippets or quotations.
Inspect the actual page before attributing a snippet, and identify that source.
API evidence supports retrieval, not clinical diagnosis or treatment advice.

From sounkou-bioinfo/pi-skills, MIT.

Signals

Stars
2
Forks
1
Open issues
2
Last commit (this folder)
Sep 6, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get biomedical-evidence-search running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying biomedical-evidence-search?

CallGet help
Cite this page

biomedical-evidence-search skill. Agent Mart. https://agentmart.dev/skills/sounkou-bioinfo-biomedical-evidence-search (last updated 2026-10-24)