{"id":"wshobson-agents-plugins-dgx-spark-ops-skills-spark-training-gotchas","title":"spark-training-gotchas","type":"skill","industry":"software-engineering","roles":["general"],"summary":"Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.","summary_lang":"en","source_url":"https://github.com/wshobson/agents/blob/main/plugins/dgx-spark-ops/skills/spark-training-gotchas/SKILL.md","raw_url":"https://raw.githubusercontent.com/SiinXu/agent-academy/main/data/mirror/wshobson-agents-plugins-dgx-spark-ops-skills-spark-training-gotchas.md","upstream_raw_url":"https://raw.githubusercontent.com/wshobson/agents/main/plugins/dgx-spark-ops/skills/spark-training-gotchas/SKILL.md","repo":"wshobson/agents","author":"wshobson","license":"MIT","redistributable":true,"content_policy":"mirror-with-attribution","original":{"kind":"full","license":"MIT","url":"https://github.com/wshobson/agents/blob/main/plugins/dgx-spark-ops/skills/spark-training-gotchas/SKILL.md"},"install":"npx skills add wshobson/agents --skill spark-training-gotchas","security":{"audited":false,"executes_code":false,"needs_credentials":false,"writes_external":false},"metrics":{"repo_stars":40824,"repo_pushed_at":"2026-10-14"},"course_step":"3-learn-rules","status":"active","first_seen":"2026-10-15T10:15:30Z","updated_at":"2026-10-15T10:15:30Z","checked_at":"2026-10-15T10:15:30Z","http_status":{"source":200},"page":"https://academy.incidental.site/r/wshobson-agents-plugins-dgx-spark-ops-skills-spark-training-gotchas/","source":"github"}