genomi

Files (200)

• ci.yml · .github/workflows/
• .gitignore
• AGENTS.md
• CITATION.cff
• CLAUDE.md
• GENOMILAB_PRODUCT_DEFINITION.md
• INSTALL_FOR_AGENTS.md
• LICENSE
• MANIFEST.in
• README.md
• README.zh-CN.md
• RELEASE_NOTES.md
• SKILL.md
• genomi-logo.png · assets/
• llms-full.txt
• llms.txt
• pyproject.toml
• _install_for_agents_downloads.py · scripts/
• _install_for_agents_lib.py · scripts/
• build_dashboard.py · scripts/
• build_llms.py · scripts/
• install_for_agents.py · scripts/
• _output-rules.md · skills/
• context-routing.md · skills/conventions/
• evidence-quality.md · skills/conventions/
• __init__.py · src/genomi/
• __main__.py · src/genomi/
• __init__.py · src/genomi/active_genome_index/
• _agi_build.py · src/genomi/active_genome_index/
• _agi_query.py · src/genomi/active_genome_index/
• _agi_readiness.py · src/genomi/active_genome_index/
• _agi_schema.py · src/genomi/active_genome_index/
• active_genome_index.py · src/genomi/active_genome_index/
• alignment.py · src/genomi/active_genome_index/
• array_genotypes.py · src/genomi/active_genome_index/
• build.py · src/genomi/active_genome_index/
• canonical.py · src/genomi/active_genome_index/
• clinvar.py · src/genomi/active_genome_index/
• dosage.py · src/genomi/active_genome_index/
• export.py · src/genomi/active_genome_index/
• filtering.py · src/genomi/active_genome_index/
• genotype_qc.py · src/genomi/active_genome_index/
• genotype_resolver.py · src/genomi/active_genome_index/
• identity.py · src/genomi/active_genome_index/
• normalize.py · src/genomi/active_genome_index/
• observations.py · src/genomi/active_genome_index/
• parallel_build.py · src/genomi/active_genome_index/
• query.py · src/genomi/active_genome_index/
• reader.py · src/genomi/active_genome_index/
• readiness.py · src/genomi/active_genome_index/
• record_kinds.py · src/genomi/active_genome_index/
• revisions.py · src/genomi/active_genome_index/
• source_capabilities.py · src/genomi/active_genome_index/
• __init__.py · src/genomi/active_genome_index/source_intake/
• agi_store.py · src/genomi/active_genome_index/source_intake/
• arrays.py · src/genomi/active_genome_index/source_intake/
• detection.py · src/genomi/active_genome_index/source_intake/
• dispatch.py · src/genomi/active_genome_index/source_intake/
• genome_bundle.py · src/genomi/active_genome_index/source_intake/
• reference.py · src/genomi/active_genome_index/source_intake/
• …and 140 more

SKILL.md (first lines)

# Genomi

Genomi gives agents local tools for genetics and DNA-aware evidence work. Use it
when the user's request is about variants, genes, phenotypes, disease genes,
biological screens, medication response, ancestry reference-panel context,
polygenic-score context, or a
genome source.

## How To Call Genomi

Call Genomi through the MCP server: `mcp__genomi__<operation>` (or your
host's equivalent namespace).

If those tools are missing from the current session's tool list but the
host's MCP list shows Genomi connected, the session pre-dates the server's
registration. Ask the user to start a new session.

## Core Rules

- Public by default: if the chat has not mentioned a genome source, answer
  from public/tool sources only.
- Active Genome Index context is chat-scoped: use it only when this conversation
  provides a genome source, names a previous run, asks about the selected Active Genome Index
  context, or says something like "my Active Genome Index" or "my genome".
- If the user provides a genome source path in this chat, that is approval to read
  that source for this session.
- If the user says "my Active Genome Index" or "my genome" without a path, it is acceptable to
  check for an already imported Active Genome Index context.
- Reading imported/parsed Active Genome Index artifacts, resuming a previous run for
  evidence, or searching for an existing "my Active Genome Index"/"my genome" context requires
  explicit user approval for this session. Record approval with
  `active_genome_index.approve_access` before calling those tools.
- A configured default user may select an Active Genome Index as metadata, but
  default selection never replaces current-session read approval.
- Do not use unrelated genome sources from other chats, workspaces, or external
  evaluation tasks.
- Call narrow tools first and inspect evidence before making a claim.
- Treat this root skill as static startup guidance. Do not infer live session
  state from it; use `genomi.describe_context`,
  `genomi.check_libraries`, and tool result envelopes for changing context.
- If an MCP tool returns `status="in_progress"`, call
  `genomi.check_background_job` with the returned `job_id`. Do not retry the
  same work with a capped parse or raw text scan unless the user asks for that
  fallback.
- Only send parameters supplied by the current user request, current Genomi
  context, a previous Genomi result, explicit user approval, or an explicit
  override. Omit unknown optional parameters.
- Defaults are part of the reasoning chain. Tool definitions expose
  `parameterDefaults`; returned results include `defaults_applied` for omitted
  defaults so the host agent can inspect and override them in a follow-up call
  when the user intent requires it.
- Tool definitions expose `dependencyContract` when a tool needs local
  installed libraries or external network/API sources. Missing local libraries
  return `requires_library_install`; unavailable external sources return
  `source_unavailable`; local source-file requirements appear as
  `localResources`.
- In the final answer, mention Active Genome Index use only when it materially
  affects the result: for example, it supports or refutes a user-specific claim,
  changes a limitation, blocks an operation until approval, or explains a
  required next action. Do not add a routine source-status line.
- Derive confidence dynamically for each Genomi-guided answer from tool
  evidence, source trust, coverage, conflicts, and missing evidence. Do not use
  a static default confidence or a user-selected confidence profile.
  Genomi result fields describe evidence support, coverage, overlap, and source
  state; they are not final answer-confidence labels.
- Use `genomi.describe_context` when the user asks about personal context,
  their own genome/context, a genome source, a previous run, a selected user,
  or before making sample-specific claims. When you call it, inspect
  `active_response_profile.guidance`; the active profile id is persisted in
  the Genomi registry (set via `genomi.set_response_profile`) and falls back
  to the catalog default when none is set. Do not call it only to bootstrap a
  public-only question.
- Handle Active Genome Index lifecycle states yourself. When a read op's
  envelope or `genomi.describe_context` returns
  `active_genome_index_readiness.status == "needs_reparse"`, look up the recorded source
  path under `active_genome_index.agi_intake_source_path` and call `genomi.parse_source`
  with it — routine maintenance, no user prompt needed. Only ask the user
  when `availability.agi_intake_source_path` is false (path moved or deleted) or the
  status is `schema_too_new` (Genomi runtime out of date). Never proceed
  with a stale Active Genome Index while silently substituting placeholder data;
  use the Active Genome Index skill for the full procedure.
- For search-like operations, pass host-inferred alternate wording in
  `semantic_context` when the current chat reasonably supports alternate
  biomedical wording. Send the user's original wording as `raw_query`, add
  `host_expansions` only as retrieval terms, and add `host_entities` for helpful
  proposed spans such as drug, gene, phenotype, trait_or_condition, variant, or
  rsid. These terms are retrieval inputs, not evidence; Genomi reports
  source/retrieval hits in `term_matches` and no-hit terms in `term_misses`.

## Routing

MCP `tools/list` returns only the default set:

- Core `genomi.*`, `research.*`, and `journal.*` operations.
- The complete direct `genomilab.*` host-application boundary.
- `genomi.invoke` — the dispatcher for every other capability tool.

Before using a `genomilab.*` operation, load `skills/genomilab/SKILL.md`.
Those tools keep the current Claude/Codex task in control; they require a
query-ready selected Active Genome Index, bind patient authorization to the
current MCP session, and use the portal only for onboarding, exact approvals,
provider setup, and committed-event monitoring.

To use a non-base capability tool, load the matching focused capability skill,
then call:

```
genomi.invoke({"tool": "<operation_name>", "params": {...}})
```

Example:

```
genomi.invoke({"tool": "variant.resolve", "params": {"rsid": "rs429358"}})
```

The dispatcher validates the registered operation name, runs the underlying tool's
input-schema validation, and returns the underlying tool's response with an
added `dispatched_tool` field.

From exon-research/genomi, Apache-2.0.

More from exon-research/genomi