$npx -y skills add KevinSpringer1/conserved-primer-design --skill literature-taxonomy-curationUse when an agent must define viral genotype, subtype, clade, lineage, target/background groups, or PhyloGuide groups from cited literature before primer or tNGS panel design.
| 1 | # Literature Taxonomy Curation |
| 2 | |
| 3 | Use this skill before `prepare-phylo` or production primer design when group names affect the result. Do not infer genotype/subtype from sequence names alone. |
| 4 | |
| 5 | ## Workflow |
| 6 | |
| 7 | 1. Identify the exact species/virus, host, region/date scope, and design purpose. |
| 8 | 2. Search primary taxonomy/genotype papers, ICTV/NCBI/public-health references, and recent surveillance papers. |
| 9 | 3. Extract group names, representative accessions, distance thresholds or clade criteria, and citations. |
| 10 | 4. Write a taxonomy JSON with `species`, optional `target_group`, `references`, and `groups`. |
| 11 | 5. Validate it: |
| 12 | |
| 13 | ```bash |
| 14 | python agentskill/scripts/curate_references.py validate-taxonomy \ |
| 15 | --taxonomy-json taxonomy.json \ |
| 16 | --output taxonomy_report.json |
| 17 | ``` |
| 18 | |
| 19 | Optional PubMed search helper: |
| 20 | |
| 21 | ```bash |
| 22 | python agentskill/scripts/curate_references.py search-literature \ |
| 23 | --species "Target virus" \ |
| 24 | --extra-query "complete genome" \ |
| 25 | --max-records 20 \ |
| 26 | --output literature_candidates.json |
| 27 | ``` |
| 28 | |
| 29 | ## Required Output |
| 30 | |
| 31 | The downstream agent should receive: |
| 32 | |
| 33 | - `taxonomy.json`: curated groups and references. |
| 34 | - `taxonomy_report.json`: validation status, warnings, and errors. |
| 35 | - A short rationale explaining why these groups are appropriate for the current species and use case. |
| 36 | |
| 37 | If the species is missing or ambiguous, ask for clarification before assigning groups. |