メニュー
Use when an agent must batch-submit, poll, summarize, retry, or compare long-running VirusPrimerPro Agent API jobs without holding a long HTTP connection open.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when an agent needs to call the VirusPrimerPro Agent API instead of the GUI, or prepare viral genome inputs for it: request/use API keys, download viral genomes from NCBI, install/run MAFFT, check and repair abnormal sequences, prepare phylogenetic trees/annotations, upload aligned FASTA/tree/GenBank files, poll runs, and fetch artifacts.
Use when an agent needs a stricter or publication-grade phylogeny workflow for PhyloGuide, including tree/MSA validation, FastTree/IQ-TREE planning, and external-tree checks.
Use 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.
Use when an agent must split tNGS or multiplex primer pairs into pools while minimizing primer-primer interaction risk and reporting pool overflows.
Use when an agent must evaluate primer candidates for wet-lab constraints such as length, GC, Tm, degeneracy, self-complementarity, pair complementarity, and amplicon size.
Use when an agent must select, filter, deduplicate, and document NCBI/GenBank/reference viral genomes before alignment, primer design, PhyloGuide, or tNGS panel design.
| name | run-orchestration |
| description | Use when an agent must batch-submit, poll, summarize, retry, or compare long-running VirusPrimerPro Agent API jobs without holding a long HTTP connection open. |
Use this when testing parameter sweeps, comparing modes, or running long jobs. The API is asynchronous: submit, poll, summarize, download artifacts.
python agentskill/scripts/run_orchestrator.py make-batch \
--msa aligned.fasta \
--mode primer_site \
--mode phylo_guide \
--profile standard \
--output batch.json
python agentskill/scripts/run_orchestrator.py submit-batch \
--batch-json batch.json \
--output batch_state.json
python agentskill/scripts/run_orchestrator.py poll-batch \
--state-json batch_state.json \
--output batch_state.polled.json
For monitoring loops, use --watch --poll-interval 30; do not keep one request open for computation time.
python agentskill/scripts/run_orchestrator.py summarize-runs \
--input batch_state.polled.json \
--output batch_summary.json