Loading...
Loading...
Found 1,267 Skills
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
Configure AI Config targeting rules to control which variations serve to different users. Enable percentage rollouts, attribute-based rules, segment targeting, and guarded rollouts.
Guide for migrating OCaml projects, libraries, modules, and test suites to idiomatic MoonBit. Use when translating OCaml code to MoonBit, planning a large OCaml-to-MoonBit port, preserving byte/string-heavy behavior, replacing OCaml variants/records/exceptions/refs/arrays, mapping OCaml APIs to MoonBit packages, or building verification and test strategy for a migration.
External NeMo-RL end-to-end validation workflow for Megatron-Bridge model/provider changes, including downstream compatibility checks, external RL lifecycle behavior, Megatron policy setup, HF import/export, checkpoint/resume, non-colocated vLLM refit, delta weight transfer, optional LoRA/generation variants, and questions such as "does this model work in NeMo-RL", "run NeMo-RL e2e", or "external RL loop validation". Covers running NeMo-RL Megatron policy jobs from a Bridge checkout, choosing GRPO/SFT/checkpoint/non-colocated refit variants, setting PYTHONPATH so NeMo-RL imports the local Bridge tree, and reporting pass/fail evidence.
Use this skill when the user requests to "generate cover", "cover copy", "XHS title", "optimize title", says "help me write a cover", or needs Xiaohongshu cover text and title variants. Based on cognitive psychology and behavioral economics, it identifies content types and authoritative elements, automatically selects driving strategies, and outputs three versions of solutions: aggressive, balanced, and conservative. Each version includes cover copy plus 3 titles, accompanied by four-dimensional ratings and A/B testing suggestions. Do NOT trigger this skill for scenarios like writing video scripts (use li-writer) or optimizing openings (use li-opening).
Use when user explicitly asks Flink/Ververica/Realtime Compute Console workspace operations: 草稿(draft), SQL校验/执行, 部署(deployment), 作业(job), Session Cluster, namespace, 表(table), 成员(member), 变量(variable), 或 checkpoint timeout 诊断, especially with workspace/deployment/job IDs (w-*, d-*, j-*, sc-*, draft-*). Also use when prompt asks to test/verify Flink Console lifecycle flow, safety guardrails, or parameter validation for these operations. This includes prompts such as create draft, deploy draft, list deployments, start/stop job, create/list session cluster, get tables, list variables. Also use when prompt explicitly asks to run `python scripts/flink_ververica_ops.py` for Flink Console workspace operations. Do not trigger for unrelated "workspace" contexts or generic cloud/platform tasks (ECS, OSS, RDS, Kafka, Spark, Kubernetes, billing, weather). Do not trigger for Flink instance lifecycle operations (create/scale/delete/renew); those belong to alibabacloud-flink-instance-manage.
MCP server for comprehensive Node.js debugging via Chrome DevTools Protocol with breakpoints, stepping, variable inspection, and source maps
React/TypeScript UI component conventions, atomic hierarchy, classNames utility, variant/size dictionaries, polymorphic `as` prop, icon usage, composition slots, and Tailwind styling. Use when authoring or reviewing any `*.tsx` component.
Generate, edit, upscale, variate, and style-transfer images using the AgentOS multi-provider image pipeline with automatic fallback and character consistency.
Use when the user asks to "improve my agent", "self-improving agent", "auto-tune my agent", "iterate on my agent prompt", "fix my agent based on test results", "close the loop on agent quality", "auto-improve agent prompt", "use eval results to improve agent", "optimize my prompt based on failures", "rewrite my prompt", or describes agent self-improvement, prompt iteration from run results, or automated agent quality loops. Covers the full diagnose → propose → apply → re-validate loop for VAPI agents (squads + tool definitions) and for self-hosted agents (custom websocket servers, including the offline / pasted-prompt degenerate variant).
Generates .http files for the VS Code REST Client extension from Express, Next.js, Fastify, or other API routes. Creates organized request files with variables, environments, and authentication. Use when users request "generate http files", "rest client requests", "create .http file", or "vscode api testing".
When the user wants to build or improve a sales bot's ability to automatically test message variations to optimize conversion. Also use when the user mentions "message testing," "A/B testing bots," "optimizing bot messages," "testing variations," or "message optimization."