pinakes-verifiable-retrieval

id	skill_ad46655dfa65459495db46461e581c09
name	pinakes-verifiable-retrieval
display-name	Pinakes Verifiable Retrieval
description	Retrieve reproducible, complete, verifiable records from 26 public biomedical sources (PDB, UniProt, NCBI Protein/Virus/Datasets, ClinVar, Ensembl, gnomAD, PubChem, AlphaFold, ClinicalTrials, openFDA, Open Targets, Reactome, GTEx, GWAS Catalog, and more — run `catalog` for the full list) via Pinakes — the same 8 verbs over an MCP server (pinakes_<verb> tools) or the identical pinakes CLI. Use when an agent must pull biomedical data that has to be reproducible, deterministic, byte-identical, complete-or-fail, or independently verifiable; when a record count, cited fact, or dataset must carry provenance a reviewer can re-derive offline; when pinning a content-addressed snapshot; reading a manifest's completeness or reproducible flag; verifying before citing; or self-correcting a rejected filter. Teaches the judgement the tool schemas do not: pin-or-no-determinism, complete vs best_effort, and verify-before-cite.
short-description	Retrieve reproducible, complete, verifiable biomedical records via Pinakes (MCP pinakes_<verb> tools or the identical CLI) over 26 public sources. Use when data must be deterministic, byte-identical, complete-or-fail, snapshot-pinned, or carry provenance a reviewer can re-derive offline — and when reading a manifest, verifying before citing, or self-correcting a rejected filter.
category	methodology
keywords	pinakes, reproducible, deterministic, verifiable, provenance, manifest, snapshot, content-addressed, complete-or-fail, verify, offline, MCP, CLI, biomedical, UniProt, PDB, ClinVar, Ensembl, gnomAD, PubChem, AlphaFold, NCBI Virus, NCBI Protein, NCBI Datasets, ClinicalTrials, openFDA, Open Targets, Reactome, GTEx, GWAS Catalog, InterPro, Rhea, JASPAR, Monarch, HPO, Gene Ontology, citation, completeness, maturity
version	1.0
last-updated	2026-06-13

Pinakes Verifiable Retrieval

Pinakes is a deterministic, verifiable input layer for AI agents over 26 public biomedical sources, shipped as one static Go binary that exposes the same 8 verbs over an MCP server (pinakes_<verb> tools), an identical CLI (pinakes <verb>), and a loopback REST server. Its value is invisible from the tool schemas, which is why this skill exists: every result pins a content-addressed snapshot (byte-reproducible forever), retrieval is complete-or-fail (reconciled against the source's authoritative total — never a silent partial), and every result ships a re-runnable manifest that verify re-derives offline. This skill teaches the judgement layer — pin or you get no determinism, read completeness honestly, verify before you cite — not the schemas (tools/list and pinakes catalog already carry field names, operators, and enums; do not duplicate them here).

Boundary. Pinakes fixes the input only. It does not run analysis, does not build evolutionary trees, and never claims a source is wrong — the public databases are authoritative. It fixes naive client retrieval (no imposed order, no reconciliation, no provenance). It covers public sources only. The arXiv literature corpus is not yet shipped — do not assume it. Hand the verified manifest to a domain skill for the actual science.

---

When to Use This Skill

✅ Use when:

• An agent must pull biomedical data that has to be reproducible / deterministic / byte-identical across runs.
• You need a record count that goes in a methods section and must reproduce next month.
• You need a cited fact a reviewer can independently re-fetch and check.
• You are handed a manifest and must confirm it reproduces before building on it (verify-before-cite).
• A query was rejected (UNKNOWN_FIELD, BAD_ENUM, INVALID_FILTER, UNSATISFIABLE_QUERY) and the agent must self-correct rather than retry blind.
• You must know whether a result is complete vs best_effort vs partial, or whether it is reproducible at all.
• You are pulling from PDB, UniProt, NCBI Protein, NCBI Virus, ClinVar, Ensembl, gnomAD, PubChem, AlphaFold, ChEMBL, ClinicalTrials, openFDA, cBioPortal, or NCBI Datasets and want provenance, not just bytes.