[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7541M9EB0ZD79A1PZ2FX96R":3,"skill-same:01M7541M9EB0ZD79A1PZ2FX96R":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":48,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":50,"updatedAt":51,"install":52,"resources":64},"01M7541M9EB0ZD79A1PZ2FX96R","active-genome-index",null,"Register, parse, and digitize private genome source files into a local Active Genome Index and\nsupporting evidence stores. Use when the session explicitly supplies a VCF\u002FgVCF, BAM,\ngenome.computer .genome\u002F1.0 bundle, 23andMe raw genotype export, AncestryDNA raw genotype export, MyHeritage raw\ngenotype export, FamilyTreeDNA Family Finder export, Living DNA autosomal export, supported source zip\u002Ftar,\nor known Active Genome Index.","exon-research\u002Fgenomi","exon-research","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287072540?v=4","01M754130SK0JVWXNQKF8XANKV","Exon Research","01M754131W4AFK5CDRWT1KHP8X",492,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Factive-genome-index\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: active-genome-index\ndescription: |\n  Register, parse, and digitize private genome source files into a local Active Genome Index and\n  supporting evidence stores. Use when the session explicitly supplies a VCF\u002FgVCF, BAM,\n  genome.computer .genome\u002F1.0 bundle, 23andMe raw genotype export, AncestryDNA raw genotype export, MyHeritage raw\n  genotype export, FamilyTreeDNA Family Finder export, Living DNA autosomal export, supported source zip\u002Ftar,\n  or known Active Genome Index.\ntools:\n  - genomi.describe_context\n  - active_genome_index.approve_access\n  - active_genome_index.select_user\n  - active_genome_index.assign_user_genome\n  - genomi.parse_source\n  - active_genome_index.rename_user\n  - active_genome_index.set_default_user\n  - active_genome_index.clear_default_user\n  - active_genome_index.summarize\n  - active_genome_index.classify_callset_qc\n  - active_genome_index.classify_genotype_support\n  - active_genome_index.classify_region_callability\n  - active_genome_index.clear_selection\n  - active_genome_index.revoke_access\n  - active_genome_index.list\n  - active_genome_index.remove\nmutating: true\n---\n\n# Active Genome Index\n\nUse this skill when the user provides a genome result file, asks to parse a genome\nsource, asks what local Active Genome Index context exists, or asks a sample-specific question\nthat requires a user file.\n\n## Goal\n\nCreate or refresh the private Active Genome Index and local evidence stores. Interpret health meaning\nonly after the relevant evidence skill gathers support for the user's claim.\n\n> **Convention:** See `skills\u002Fconventions\u002Fcontext-routing.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## Contract\n\nContract:\n\n- A supplied source file or an Active Genome Index explicitly approved in the current session is accessible before sample-specific work.\n- `GENOMI_HOME` stores durable Active Genome Index records.\n- Every genome source parsed by Genomi becomes an Active Genome Index record.\n- User\u002Fprofile nicknames belong to users, not genome artifacts.\n- A user can have multiple genome records and one selected Active Genome Index.\n- A default user is auto-selected as metadata for every session using this `GENOMI_HOME`; its selected Active Genome Index still requires current-session approval before a private read.\n- `genomi.parse_source` digitizes the intake file so future inquiries use the Active Genome Index.\n- The original intake path is hidden from normal agent-facing context after parsing.\n- Parsing success creates a source-appropriate Active Genome Index for later interpretation.\n\n## Supported Sources\n\n- VCF\u002FgVCF: variant callsets with VCF records, genotype fields, optional depth\u002Fquality, and possible region callability.\n- BAM: aligned sequencing reads. Genomi derives a local VCF from the reads with a matching reference FASTA, then builds an Active Genome Index for the derived callset for normal sample-specific tools.\n- FASTQ (paired-end): raw reads from sequencing services such as Nebula, Dante Labs, and Sequencing.com. Genomi auto-detects the R2 sibling, picks minimap2 (long reads) or bwa-mem2 (short reads) by the median sniffed read length, sorts the aligned BAM with samtools, then hands the BAM off to the standard BAM → derived-VCF path. Requires the `wgs-alignment` install purpose (or aligner binaries on PATH); a missing aligner returns `requires_library_install` instead of failing.\n- 23andMe raw genotype text or zip\u002Ftar archive: consumer SNP-array calls with `rsid`, chromosome, position, and plus-strand genotype on GRCh37.\n- genome.computer `.genome\u002F1.0` bundle directory or archive with `manifest.json`, `schema.json`, and partitioned `variants.parquet` records.\n- AncestryDNA raw genotype text or zip\u002Ftar archive: consumer SNP-array calls with `rsid`, chromosome, position, `allele1`, and `allele2` on GRCh37\u002Fbuild 37.1.\n- MyHeritage raw genotype CSV or zip\u002Ftar archive: comma-delimited `RSID,CHROMOSOME,POSITION,RESULT` exports prefixed with a `# MyHeritage DNA raw data` banner, GRCh37.\n- FamilyTreeDNA Family Finder autosomal CSV or compressed\u002Fzip\u002Ftar archive: same `RSID,CHROMOSOME,POSITION,RESULT` columns as MyHeritage but with no banner, build encoded in the filename (`_o37_`), GRCh37.\n- Living DNA autosomal text or zip\u002Ftar archive: tab-separated `rsid\u002Fchromosome\u002Fposition\u002Fgenotype` rows with a `# Living DNA customer genotype data` banner on GRCh37.\n\nVCF deliverables from named consumer sequencing services (Nebula Genomics, Dante Labs, Sequencing.com) are accepted through the generic VCF path; the source provider is detected from header signatures and surfaced as `provider` on the parse result.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### active_genome_index.classify_callset_qc\n\nClassify genome callset shape, depth\u002Fquality field availability, and absence-claim boundaries using an Active Genome Index.\n\n**Use when**: Use before broad Active Genome Index claims when the agent needs callset shape, QC fields, and absence-claim boundaries.\n\n**Why necessary**: Broad Active Genome Index claims depend on whether the artifact actually contains the fields and coverage needed to support them.\n\n### active_genome_index.summarize\n\nSummarize local parse\u002Freadiness\u002Fevidence state for an Active Genome Index.\n\n**Use when**: The agent needs a compact status check for an Active Genome Index before deciding whether parsing, library-scoped evidence materialization, or evidence refresh is needed.\n\n**Why necessary**: Agents need Active Genome Index readiness and artifact status before deciding whether to reuse, resume, materialize, or answer.\n\n**Example prompts**: What Active Genome Index context is active?\n\n**Result semantics**: Summarizes local Active Genome Index and evidence artifact state; it does not parse new input or perform interpretation.\n\n### active_genome_index.assign_user_genome\n\nAssign an existing or supplied genome source to a user\u002Fprofile and optionally make it that user's selected Active Genome Index.\n\n**Use when**: A genome source or existing genomi agi should belong to a named user\u002Fprofile.\n\n**Why necessary**: One user can own multiple genome artifacts while selecting exactly one Active Genome Index as active for that profile.\n\n**Not for**: Parsing a source into a complete Active Genome Index; use genomi.parse_source when digitization is needed.\n\n**Example prompts**: Assign this VCF to Alice.\n\n**Result semantics**: Links user metadata to genomi agi metadata. Supplying a source path grants scoped session access to that source's resolved Active Genome Index.\n\n### active_genome_index.clear_default_user\n\nClear persistent default user\u002Fprofile selection for this GENOMI_HOME.\n\n**Use when**: The user no longer wants any user\u002Fprofile auto-selected by default.\n\n**Why necessary**: Users need an explicit way to remove persistent default Active Genome Index context without deleting users or Active Genome Index artifacts.\n\n**Example prompts**: Stop auto-selecting the default user.\n\n**Result semantics**: Clears default=true from all known users; session selections and artifacts remain.\n\n### active_genome_index.list\n\nList users and Active Genome Index records.\n\n**Use when**: The user asks what AGIs or users exist, or gives a vague AGI lifecycle request that needs disambiguation before selecting exact records.\n\n**Result semantics**: Returns structured `users` and `active_genome_indexes`; AGI records include IDs, hashes, names, typed source references, source metadata, linked users, readiness, and artifact availability. It does not approve private reads.\n\n### active_genome_index.remove\n\nRemove confirmed Active Genome Index records, user\u002Fprofile records, and\nGenomi-owned AGI artifacts.\n\n**Use when**: The user has confirmed the exact AGI and\u002For user\u002Fprofile record(s)\nto remove.\n\n**Result semantics**: AGI targets remove the targeted AGI registry\u002Fsession\nrecord, session access grant, user\u002Fprofile AGI links, and Genomi-owned run\nartifacts. User targets remove user\u002Fprofile metadata and default\u002Fsession user\nselection; linked AGIs remain unless the same confirmed call also targets those\nAGIs. The original intake source and shared evidence database are not deleted.\n\n### genomi.parse_source\n\n`genomi.parse_source` is a core `genomi.*` tool, documented in the root Genomi\nskill (`SKILL.md` → \"Parsing A Genome Source\"). This skill drives the workflow\naround it — select user, approve access, assign the parsed genome to a profile,\nand lifecycle reparse — plus the `active_genome_index.*` interpretation tools.\n\n### active_genome_index.rename_user\n\nRename a user\u002Fprofile nickname.\n\n**Use when**: The user wants to rename a person\u002Fprofile.\n\n**Why necessary**: Human-friendly names belong to users, while Active Genome Index IDs remain stable hash-based artifact identifiers.\n\n**Example prompts**: Rename this user to Alice.\n\n**Result semantics**: Updates one user nickname. Active Genome Index artifact IDs are unchanged.\n\n### active_genome_index.select_user\n\nSelect a user\u002Fprofile for this session without granting private artifact access.\n\n**Use when**: The user names a person\u002Fprofile and the agent needs to make that user's selected Active Genome Index the session metadata context.\n\n**Why necessary**: Selecting another user should be metadata-only until active_genome_index.approve_access grants access to that user's selected Active Genome Index.\n\n**Example prompts**: Use Alice's genome context.\n\n**Result semantics**: Sets the selected user and selected Active Genome Index metadata; private reads still require scoped current-session approval, including for the default user.\n\n### active_genome_index.set_default_user\n\nSet the default user\u002Fprofile for this GENOMI_HOME.\n\n**Use when**: The user wants one profile's selected Active Genome Index selected as metadata by default in every session.\n\n**Why necessary**: Default selection identifies one profile without selecting every genome or user; it does not grant private read access.\n\n**Example prompts**: Make Alice the default user.\n\n**Result semantics**: Sets exactly one default user for metadata selection. The selected Active Genome Index requires explicit approval in every session before private reads.\n\n## Selection Notes\n\n- Use `genomi.describe_context` to inspect selected session context.\n- If the user supplied a source file and the answer needs sample evidence, first\n  inspect whether the same source or a known complete Active Genome Index is\n  already selected. Use the existing complete Active Genome Index when available; call\n  `genomi.parse_source --params '{\"source\":\"\u003Cpath>\"}'` only when no complete\n  matching Active Genome Index exists or Genomi reports the Active Genome Index is incomplete.\n- If `genomi.parse_source` returns `status=\"in_progress\"` with a\n  `job_id`, keep polling `genomi.check_background_job` for that job. Do not\n  switch to a capped parse or raw text scan as a substitute for the full active\n  Active Genome Index unless the user explicitly asks for a temporary fallback.\n- Do not add `max_records` for user-facing inspection when a complete Active Genome Index may\n  already exist. A capped parse is only an explicit sampling\u002Fdebug choice, not\n  the normal path for \"anything notable?\".\n- If a focused evidence tool returns\n  `status=\"requires_library_install\"`, explain what the named library enables\n  for the user's intent and ask whether they want it installed. Do not treat\n  missing library data as negative evidence.\n- If the user supplied a known `agi_id`, call\n  `active_genome_index.approve_access --params '{\"approved_by_user\":true,\"agi_id\":\"...\"}'`\n  only after explicit approval for this session.\n- If the user supplied a user nickname, call `active_genome_index.select_user` for metadata\n  selection, then call `active_genome_index.approve_access` if sample evidence is needed\n  for that user's selected Active Genome Index.\n- For interpretation work, load the matching focused capability skill and call its capability tools through `genomi.invoke`.\n\n## Boundaries\n\n- Raw genome source files stay local.\n- Durable Active Genome Index records in `GENOMI_HOME` become readable only when the session\n  explicitly approves the resolved `agi_id` or supplies its source path. Default\n  user selection is metadata-only.\n- VCF\u002FgVCF parsing does not import public sources or build whole-callset static\n  artifacts. Use focused tools such as `clinvar.match_variants`,\n  `active_genome_index.classify_genotype_support`, or\n  `region.retrieve_features` when that evidence is needed. BAM\n  parsing also requires local `samtools` and `bcftools`.\n- Consumer array calls support rsID\u002Flocus presence checks. Sequencing depth,\n  genotype quality, phasing, and region callability come from sequencing-derived sources.\n- If the user asks a tiny factual question and an Active Genome Index already exists, prefer\n  `variant.resolve` from the variant evidence skill to resolve the\n  target and query the Active Genome Index.\n- If parsing already succeeded, the original file is an intake source. Future\n  inquiries should normally use the Active Genome Index.\n- For genetics questions outside Active Genome Index workflows, use Journal\n  source-review memory, GWAS, or normal agent research without adding a routine\n  source-status line.\n\n## Reference pass (`variants_ready` → `completed`)\n\nA gVCF parse returns `variants_ready` once every variant is stored, then\nappends the reference-block tail in a detached background job. At\n`variants_ready` every variant query is correct; only \"is this locus confirmed\nreference vs not-callable\" coverage answers are provisional (readiness and the\nindividual coverage\u002Fcallability\u002Fgenotype-support results carry\n`reference_pending`). Don't reparse to \"finish\" it — poll\n`genomi.check_background_job` with the surfaced `job_id`, or simply re-query\nonce readiness reports `completed`.\n\n### active_genome_index.build_reference_pass\n\n**Internal — do not invoke by hand.** `genomi.parse_source` launches this\nautomatically as a background job after a gVCF reaches `variants_ready`, and\nsurfaces its `job_id` in the parse result's `next_actions`. It appends the\nreference-block tail to the variants_ready index and flips it to `completed`.\nIt is idempotent (a no-op on an already-complete index). The only thing you do\nwith it is poll its `job_id` via `genomi.check_background_job` if the user is\nwaiting on reference-coverage answers.\n\n## After Parsing\n\nSelect the focused skill from the user intent:\n\n- ClinVar discovery: ClinVar skill\n- Specific variant\u002Fgene\u002FrsID: variant evidence skill\n- GWAS phenotype plus rsIDs: GWAS Catalog skill\n- All-at-once dashboard \u002F one-shot rundown: decode skill\n\n## Lifecycle: handle `needs_reparse` and `schema_too_new` automatically\n\n`genomi.describe_context` (and every read op's error envelope) returns an\n`active_genome_index_readiness` block with `status` and a structured `reason` code. The\nagent must reconcile lifecycle state on its own before falling back to the\nuser.\n\n**`status: needs_reparse`** (`reason: active_genome_index_needs_reparse`)\n\nThe on-disk Active Genome Index was built by an older Genomi runtime than the current\n`SCHEMA_VERSION`. Reparse rebuilds it at the current schema.\n\n1. Read `active_genome_index.agi_intake_source_path` from\n   `genomi.describe_context`. Check `active_genome_index.availability.agi_intake_source_path`.\n2. If `availability.agi_intake_source_path` is true (path is still on disk), call\n   `genomi.parse_source({\"source\": \"\u003Cpath-from-describe_context>\"})`\n   without prompting the user — this is routine maintenance.\n3. If `availability.agi_intake_source_path` is false (path moved or deleted), ask the user\n   once: *\"Your Active Genome Index needs to be reparsed at the new schema,\n   but the original source isn't at `\u003Crecorded path>` anymore. Send me the\n   current path, or restore the file there.\"* Wait for the user, then parse\n   that path.\n4. After reparse, call `genomi.describe_context` again to confirm\n   `active_genome_index_readiness.status == \"complete\"`. Then continue the original\n   request (decode, variant lookup, PharmCAT, whatever the user asked for).\n\n**`status: schema_too_new`** (`reason: active_genome_index_schema_too_new`)\n\nThe Active Genome Index was built by a newer Genomi than the current process. Do not\nreparse — that would downgrade the Active Genome Index. Tell the user the runtime is out\nof date and they need to upgrade Genomi.\n\n**Incomplete (missing objects)**\n\nContinue with what's available; surface honest \"Not gathered\" notes in any\ndownstream artifacts. Do not silently substitute mock or placeholder data.\n\n## Context Checks\n\n- Select the Active Genome Index from the session's source path, approved `agi_id`, or default-user metadata; approve any previously imported Active Genome Index before reading it.\n- Use an existing Active Genome Index when it answers the question.\n- Use `variant.resolve` for rsID, allele, locus, or region checks after parsing.\n- Treat broad candidate inventories as triage inputs.\n- Keep raw genome source content and broad match files local.\n","# Active Genome Index\n\nUse this skill when the user provides a genome result file, asks to parse a genome\nsource, asks what local Active Genome Index context exists, or asks a sample-specific question\nthat requires a user file.\n\n## Goal\n\nCreate or refresh the private Active Genome Index and local evidence stores. Interpret health meaning\nonly after the relevant evidence skill gathers support for the user's claim.\n\n> **Convention:** See `skills\u002Fconventions\u002Fcontext-routing.md`.\n> **Convention:** See `skills\u002F_output-rules.md`.\n\n## Contract\n\nContract:\n\n- A supplied source file or an Active Genome Index explicitly approved in the current session is accessible before sample-specific work.\n- `GENOMI_HOME` stores durable Active Genome Index records.\n- Every genome source parsed by Genomi becomes an Active Genome Index record.\n- User\u002Fprofile nicknames belong to users, not genome artifacts.\n- A user can have multiple genome records and one selected Active Genome Index.\n- A default user is auto-selected as metadata for every session using this `GENOMI_HOME`; its selected Active Genome Index still requires current-session approval before a private read.\n- `genomi.parse_source` digitizes the intake file so future inquiries use the Active Genome Index.\n- The original intake path is hidden from normal agent-facing context after parsing.\n- Parsing success creates a source-appropriate Active Genome Index for later interpretation.\n\n## Supported Sources\n\n- VCF\u002FgVCF: variant callsets with VCF records, genotype fields, optional depth\u002Fquality, and possible region callability.\n- BAM: aligned sequencing reads. Genomi derives a local VCF from the reads with a matching reference FASTA, then builds an Active Genome Index for the derived callset for normal sample-specific tools.\n- FASTQ (paired-end): raw reads from sequencing services such as Nebula, Dante Labs, and Sequencing.com. Genomi auto-detects the R2 sibling, picks minimap2 (long reads) or bwa-mem2 (short reads) by the median sniffed read length, sorts the aligned BAM with samtools, then hands the BAM off to the standard BAM → derived-VCF path. Requires the `wgs-alignment` install purpose (or aligner binaries on PATH); a missing aligner returns `requires_library_install` instead of failing.\n- 23andMe raw genotype text or zip\u002Ftar archive: consumer SNP-array calls with `rsid`, chromosome, position, and plus-strand genotype on GRCh37.\n- genome.computer `.genome\u002F1.0` bundle directory or archive with `manifest.json`, `schema.json`, and partitioned `variants.parquet` records.\n- AncestryDNA raw genotype text or zip\u002Ftar archive: consumer SNP-array calls with `rsid`, chromosome, position, `allele1`, and `allele2` on GRCh37\u002Fbuild 37.1.\n- MyHeritage raw genotype CSV or zip\u002Ftar archive: comma-delimited `RSID,CHROMOSOME,POSITION,RESULT` exports prefixed with a `# MyHeritage DNA raw data` banner, GRCh37.\n- FamilyTreeDNA Family Finder autosomal CSV or compressed\u002Fzip\u002Ftar archive: same `RSID,CHROMOSOME,POSITION,RESULT` columns as MyHeritage but with no banner, build encoded in the filename (`_o37_`), GRCh37.\n- Living DNA autosomal text or zip\u002Ftar archive: tab-separated `rsid\u002Fchromosome\u002Fposition\u002Fgenotype` rows with a `# Living DNA customer genotype data` banner on GRCh37.\n\nVCF deliverables from named consumer sequencing services (Nebula Genomics, Dante Labs, Sequencing.com) are accepted through the generic VCF path; the source provider is detected from header signatures and surfaced as `provider` on the parse result.\n\n## Cross-Capability Synthesis\n\nA scope-limited result from this capability is not a final user-facing answer\nwhen other Genomi capabilities can contribute orthogonal evidence to the same\nquestion. Returning \"cannot answer\" while applicable capabilities remain\nunexamined is a host-agent failure mode.\n\n## Tools\n\n### active_genome_index.classify_callset_qc\n\nClassify genome callset shape, depth\u002Fquality field availability, and absence-claim boundaries using an Active Genome Index.\n\n**Use when**: Use before broad Active Genome Index claims when the agent needs callset shape, QC fields, and absence-claim boundaries.\n\n**Why necessary**: Broad Active Genome Index claims depend on whether the artifact actually contains the fields and coverage needed to support them.\n\n### active_genome_index.summarize\n\nSummarize local parse\u002Freadiness\u002Fevidence state for an Active Genome Index.\n\n**Use when**: The agent needs a compact status check for an Active Genome Index before deciding whether parsing, library-scoped evidence materialization, or evidence refresh is needed.\n\n**Why necessary**: Agents need Active Genome Index readiness and artifact status before deciding whether to reuse, resume, materialize, or answer.\n\n**Example prompts**: What Active Genome Index context is active?\n\n**Result semantics**: Summarizes local Active Genome Index and evidence artifact state; it does not parse new input or perform interpretation.\n\n### active_genome_index.assign_user_genome\n\nAssign an existing or supplied genome source to a user\u002Fprofile and optionally make it that user's selected Active Genome Index.\n\n**Use when**: A genome source or existing genomi agi should belong to a named user\u002Fprofile.\n\n**Why necessary**: One user can own multiple genome artifacts while selecting exactly one Active Genome Index as active for that profile.\n\n**Not for**: Parsing a source into a complete Active Genome Index; use genomi.parse_source when digitization is needed.\n\n**Example prompts**: Assign this VCF to Alice.\n\n**Result semantics**: Links user metadata to genomi agi metadata. Supplying a source path grants scoped session access to that source's resolved Active Genome Index.\n\n### active_genome_index.clear_default_user\n\nClear persistent default user\u002Fprofile selection for this GENOMI_HOME.\n\n**Use when**: The user no longer wants any user\u002Fprofile auto-selected by default.\n\n**Why necessary**: Users need an explicit way to remove persistent default Active Genome Index context without deleting users or Active Genome Index artifacts.\n\n**Example prompts**: Stop auto-selecting the default user.\n\n**Result semantics**: Clears default=true from all known users; session selections and artifacts remain.\n\n### active_genome_index.list\n\nList users and Active Genome Index records.\n\n**Use when**: The user asks what AGIs or users exist, or gives a vague AGI lifecycle request that needs disambiguation before selecting exact records.\n\n**Result semantics**: Returns structured `users` and `active_genome_indexes`; AGI records include IDs, hashes, names, typed source references, source metadata, linked users, readiness, and artifact availability. It does not approve private reads.\n\n### active_genome_index.remove\n\nRemove confirmed Active Genome Index records, user\u002Fprofile records, and\nGenomi-owned AGI artifacts.\n\n**Use when**: The user has confirmed the exact AGI and\u002For user\u002Fprofile record(s)\nto remove.\n\n**Result semantics**: AGI targets remove the targeted AGI registry\u002Fsession\nrecord, session access grant, user\u002Fprofile AGI links, and Genomi-owned run\nartifacts. User targets remove user\u002Fprofile metadata and default\u002Fsession user\nselection; linked AGIs remain unless the same confirmed call also targets those\nAGIs. The original intake source and shared evidence database are not deleted.\n\n### genomi.parse_source\n\n`genomi.parse_source` is a core `genomi.*` tool, documented in the root Genomi\nskill (`SKILL.md` → \"Parsing A Genome Source\"). This skill drives the workflow\naround it — select user, approve access, assign the parsed genome to a profile,\nand lifecycle reparse — plus the `active_genome_index.*` interpretation tools.\n\n### active_genome_index.rename_user\n\nRename a user\u002Fprofile nickname.\n\n**Use when**: The user wants to rename a person\u002Fprofile.\n\n**Why necessary**: Human-friendly names belong to users, while Active Genome Index IDs remain stable hash-based artifact identifiers.\n\n**Example prompts**: Rename this user to Alice.\n\n**Result semantics**: Updates one user nickname. Active Genome Index artifact IDs are unchanged.\n\n### active_genome_index.select_user\n\nSelect a user\u002Fprofile for this session without granting private artifact access.\n\n**Use when**: The user names a person\u002Fprofile and the agent needs to make that user's selected Active Genome Index the session metadata context.\n\n**Why necessary**: Selecting another user should be metadata-only until active_genome_index.approve_access grants access to that user's selected Active Genome Index.\n\n**Example prompts**: Use Alice's genome context.\n\n**Result semantics**: Sets the selected user and selected Active Genome Index metadata; private reads still require scoped current-session approval, including for the default user.\n\n### active_genome_index.set_default_user\n\nSet the default user\u002Fprofile for this GENOMI_HOME.\n\n**Use when**: The user wants one profile's selected Active Genome Index selected as metadata by default in every session.\n\n**Why necessary**: Default selection identifies one profile without selecting every genome or user; it does not grant private read access.\n\n**Example prompts**: Make Alice the default user.\n\n**Result semantics**: Sets exactly one default user for metadata selection. The selected Active Genome Index requires explicit approval in every session before private reads.\n\n## Selection Notes\n\n- Use `genomi.describe_context` to inspect selected session context.\n- If the user supplied a source file and the answer needs sample evidence, first\n  inspect whether the same source or a known complete Active Genome Index is\n  already selected. Use the existing complete Active Genome Index when available; call\n  `genomi.parse_source --params '{\"source\":\"\u003Cpath>\"}'` only when no complete\n  matching Active Genome Index exists or Genomi reports the Active Genome Index is incomplete.\n- If `genomi.parse_source` returns `status=\"in_progress\"` with a\n  `job_id`, keep polling `genomi.check_background_job` for that job. Do not\n  switch to a capped parse or raw text scan as a substitute for the full active\n  Active Genome Index unless the user explicitly asks for a temporary fallback.\n- Do not add `max_records` for user-facing inspection when a complete Active Genome Index may\n  already exist. A capped parse is only an explicit sampling\u002Fdebug choice, not\n  the normal path for \"anything notable?\".\n- If a focused evidence tool returns\n  `status=\"requires_library_install\"`, explain what the named library enables\n  for the user's intent and ask whether they want it installed. Do not treat\n  missing library data as negative evidence.\n- If the user supplied a known `agi_id`, call\n  `active_genome_index.approve_access --params '{\"approved_by_user\":true,\"agi_id\":\"...\"}'`\n  only after explicit approval for this session.\n- If the user supplied a user nickname, call `active_genome_index.select_user` for metadata\n  selection, then call `active_genome_index.approve_access` if sample evidence is needed\n  for that user's selected Active Genome Index.\n- For interpretation work, load the matching focused capability skill and call its capability tools through `genomi.invoke`.\n\n## Boundaries\n\n- Raw genome source files stay local.\n- Durable Active Genome Index records in `GENOMI_HOME` become readable only when the session\n  explicitly approves the resolved `agi_id` or supplies its source path. Default\n  user selection is metadata-only.\n- VCF\u002FgVCF parsing does not import public sources or build whole-callset static\n  artifacts. Use focused tools such as `clinvar.match_variants`,\n  `active_genome_index.classify_genotype_support`, or\n  `region.retrieve_features` when that evidence is needed. BAM\n  parsing also requires local `samtools` and `bcftools`.\n- Consumer array calls support rsID\u002Flocus presence checks. Sequencing depth,\n  genotype quality, phasing, and region callability come from sequencing-derived sources.\n- If the user asks a tiny factual question and an Active Genome Index already exists, prefer\n  `variant.resolve` from the variant evidence skill to resolve the\n  target and query the Active Genome Index.\n- If parsing already succeeded, the original file is an intake source. Future\n  inquiries should normally use the Active Genome Index.\n- For genetics questions outside Active Genome Index workflows, use Journal\n  source-review memory, GWAS, or normal agent research without adding a routine\n  source-status line.\n\n## Reference pass (`variants_ready` → `completed`)\n\nA gVCF parse returns `variants_ready` once every variant is stored, then\nappends the reference-block tail in a detached background job. At\n`variants_ready` every variant query is correct; only \"is this locus confirmed\nreference vs not-callable\" coverage answers are provisional (readiness and the\nindividual coverage\u002Fcallability\u002Fgenotype-support results carry\n`reference_pending`). Don't reparse to \"finish\" it — poll\n`genomi.check_background_job` with the surfaced `job_id`, or simply re-query\nonce readiness reports `completed`.\n\n### active_genome_index.build_reference_pass\n\n**Internal — do not invoke by hand.** `genomi.parse_source` launches this\nautomatically as a background job after a gVCF reaches `variants_ready`, and\nsurfaces its `job_id` in the parse result's `next_actions`. It appends the\nreference-block tail to the variants_ready index and flips it to `completed`.\nIt is idempotent (a no-op on an already-complete index). The only thing you do\nwith it is poll its `job_id` via `genomi.check_background_job` if the user is\nwaiting on reference-coverage answers.\n\n## After Parsing\n\nSelect the focused skill from the user intent:\n\n- ClinVar discovery: ClinVar skill\n- Specific variant\u002Fgene\u002FrsID: variant evidence skill\n- GWAS phenotype plus rsIDs: GWAS Catalog skill\n- All-at-once dashboard \u002F one-shot rundown: decode skill\n\n## Lifecycle: handle `needs_reparse` and `schema_too_new` automatically\n\n`genomi.describe_context` (and every read op's error envelope) returns an\n`active_genome_index_readiness` block with `status` and a structured `reason` code. The\nagent must reconcile lifecycle state on its own before falling back to the\nuser.\n\n**`status: needs_reparse`** (`reason: active_genome_index_needs_reparse`)\n\nThe on-disk Active Genome Index was built by an older Genomi runtime than the current\n`SCHEMA_VERSION`. Reparse rebuilds it at the current schema.\n\n1. Read `active_genome_index.agi_intake_source_path` from\n   `genomi.describe_context`. Check `active_genome_index.availability.agi_intake_source_path`.\n2. If `availability.agi_intake_source_path` is true (path is still on disk), call\n   `genomi.parse_source({\"source\": \"\u003Cpath-from-describe_context>\"})`\n   without prompting the user — this is routine maintenance.\n3. If `availability.agi_intake_source_path` is false (path moved or deleted), ask the user\n   once: *\"Your Active Genome Index needs to be reparsed at the new schema,\n   but the original source isn't at `\u003Crecorded path>` anymore. Send me the\n   current path, or restore the file there.\"* Wait for the user, then parse\n   that path.\n4. After reparse, call `genomi.describe_context` again to confirm\n   `active_genome_index_readiness.status == \"complete\"`. Then continue the original\n   request (decode, variant lookup, PharmCAT, whatever the user asked for).\n\n**`status: schema_too_new`** (`reason: active_genome_index_schema_too_new`)\n\nThe Active Genome Index was built by a newer Genomi than the current process. Do not\nreparse — that would downgrade the Active Genome Index. Tell the user the runtime is out\nof date and they need to upgrade Genomi.\n\n**Incomplete (missing objects)**\n\nContinue with what's available; surface honest \"Not gathered\" notes in any\ndownstream artifacts. Do not silently substitute mock or placeholder data.\n\n## Context Checks\n\n- Select the Active Genome Index from the session's source path, approved `agi_id`, or default-user metadata; approve any previously imported Active Genome Index before reading it.\n- Use an existing Active Genome Index when it answers the question.\n- Use `variant.resolve` for rsID, allele, locus, or region checks after parsing.\n- Treat broad candidate inventories as triage inputs.\n- Keep raw genome source content and broad match files local.\n",{"name":5,"tools":24,"mutating":41,"description":42},[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"genomi.describe_context","active_genome_index.approve_access","active_genome_index.select_user","active_genome_index.assign_user_genome","genomi.parse_source","active_genome_index.rename_user","active_genome_index.set_default_user","active_genome_index.clear_default_user","active_genome_index.summarize","active_genome_index.classify_callset_qc","active_genome_index.classify_genotype_support","active_genome_index.classify_region_callability","active_genome_index.clear_selection","active_genome_index.revoke_access","active_genome_index.list","active_genome_index.remove",true,"Register, parse, and digitize private genome source files into a local Active Genome Index and\nsupporting evidence stores. Use when the session explicitly supplies a VCF\u002FgVCF, BAM,\ngenome.computer .genome\u002F1.0 bundle, 23andMe raw genotype export, AncestryDNA raw genotype export, MyHeritage raw\ngenotype export, FamilyTreeDNA Family Finder export, Living DNA autosomal export, supported source zip\u002Ftar,\nor known Active Genome Index.\n","master","1df4f5bfb635e2d08f93a1102b70b840fbe80d86","skills\u002Factive-genome-index",61,"https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi","https:\u002F\u002Fwww.genomiagent.com\u002F","https:\u002F\u002Fgithub.com\u002Fexon-research","Building local-first AI co-scientist for genomic research","2026-09-01 03:30:56",{"source":8,"skillName":5,"commands":53,"prompt":63,"zipAvailable":41},[54,57,60],{"tool":55,"command":56},"npx","npx skills add exon-research\u002Fgenomi --skill active-genome-index",{"tool":58,"command":59},"bunx","bunx skills add exon-research\u002Fgenomi --skill active-genome-index",{"tool":61,"command":62},"pnpm","pnpm dlx skills add exon-research\u002Fgenomi --skill active-genome-index","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Factive-genome-index\u002FSKILL.md",[],[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M75442YT3ZG6MG47E5MJ3HG2","variant-evidence","Answer specific rsID, allele, gene, region, genotype, and absence\u002Fcallability\nquestions using explicit session context or public evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fvariant-evidence\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M754400MW6S0MEN19S4CM9DE","journal-source-research","Journal sub-skill for focused public\u002Fsource evidence review and reviewed\nfinding write-back before interpretation or answer synthesis.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsource-research\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7543X67TA0MBK3YGC0NJAX9","sequence","Deterministic sequence utilities for translation, ORFs, restriction sites,\nKozak context, primer checks, and local FASTA record matching.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fsequence\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7543RHCHF4WJ69P0K0QTTFB","rare-disease-cancer","Plan rare disease, hereditary disease, cancer risk, carrier-relevance, and\nobserved-condition source investigation from public targets or selected\nactive genome evidence.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Frare-disease-cancer\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7543NDTVZB8T3RQBD0RK3MC","prs","Apply published polygenic scores from PGS Catalog to approved local personal DNA and return raw weighted score plus overlap QC.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fprs\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7543FDFTWSYVVTEGHQSPHQK","pharmacogenomics","Answer drug-response, medication, PharmGKB-style, PGxDB, ATC, DrugBank,\ngene-drug, and variant-drug questions using public PGx evidence plus local\nsample genotype support when an Active Genome Index is selected.","https:\u002F\u002Fgithub.com\u002Fexon-research\u002Fgenomi\u002Fblob\u002Fmaster\u002Fskills\u002Fpharmacogenomics\u002FSKILL.md",[],[]]