菜单
Use this skill to render, submit, and inspect a minimal Slurm smoke job before submitting heavier workloads on a real cluster.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this skill to search the current ClinicalTrials.gov v2 API for condition or keyword matches when you need official clinical-study metadata. Do not use it for legacy API URLs or offline work.
Use this skill to resolve a gene symbol to Ensembl IDs and fetch a canonical Ensembl gene record. Do not use it for full transcript annotation pipelines or offline work.
Use this skill to search NCBI Gene by symbol and organism, then fetch compact official Entrez Gene summaries. Do not use it for variant interpretation, transcript-level modeling, or bulk offline annotation.
Use this skill to author and run a minimal Common Workflow Language CommandLineTool and one-step workflow with cwltool. Do not use it for containerized production execution or complex scatter/gather workflows.
Use this skill to run a minimal Nextflow workflow through the repo-managed Java and Nextflow prefix, either locally or on the Slurm cluster. Do not use it for containerized production pipelines.
Use this skill to verify the repo-managed nf-core tools install and retrieve a cleaned summary of available pipelines. Do not use it for interactive launch flows or full pipeline downloads.
| name | slurm-job-debug-template |
| description | Use this skill to render, submit, and inspect a minimal Slurm smoke job before submitting heavier workloads on a real cluster. |
Generate a conservative sbatch template, submit it to Slurm, and capture the accounting record needed to verify the cluster path end to end.
sbatch scriptsacct summarysbatch, squeue, and sacctpython3 skills/hpc/slurm-job-debug-template/scripts/render_sbatch.py --command "echo hello" --job-name smoke.--out.python3 skills/hpc/slurm-job-debug-template/scripts/submit_smoke_job.py --partition cpu --job-name slurm-smoke --sleep 2 --out slurm/reports/slurm-smoke.json.job_id, the log paths in slurm/logs/, and the accounting block from sacct.#SBATCH directives and the command body.State=COMPLETED.ExitCode is 0:0.sacct lags briefly after completion: retry once accounting catches up.python3 .../render_sbatch.py --command "python analysis.py" --partition short --time 00:10:00 --mem 2Gpython3 .../submit_smoke_job.py --partition cpu --job-name slurm-smoke --sleep 1sbatch reference: https://slurm.schedmd.com/sbatch.htmlsacct reference: https://slurm.schedmd.com/sacct.htmlsnakemake-toy-workflow-starter