Total 50,611 skills, AI & Machine Learning has 8484 skills
Showing 12 of 8484 skills
Generate interface documents for Triton operators of Ascend NPU. Used when users need to create or update interface documents for Triton operators of Ascend NPU. Core capabilities: (1) Generate standardized documents based on templates (2) Support the list of Ascend NPU product models (3) Provide specifications for operator parameter descriptions (4) Generate call example frameworks.
Analyze official Megatron-LM commits, PRs, and branch change sets to identify feature evolution, candidate breaking changes, and migration-relevant events. Use when Codex already has a normalized Megatron change set and needs to explain what changed, which new features matter, and which changes should flow into MindSpeed adaptation work.
Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.
Troubleshoot and optimize the performance of Ascend C operators. This skill is applicable when users develop, review or optimize Ascend C kernel operators, or triggered when users mention keywords such as Ascend C performance optimization, operator optimization, tiling, pipeline, data copy, memory optimization, NPU/Ascend.
根据CATLASS算子设计文档生成算子工程交付件
Calculate comprehensive ROI for AI implementation projects. Takes current costs, manual process time, team size, and hourly rates. Generates detailed roi-analysis.md with executive summary, cost-benefit tables, sensitivity analysis, break-even timeline, and comparison scenarios. Use when evaluating AI investments, building business cases, or justifying automation spend.
Deploys swarms of sub-agents for massive parallel data processing tasks. Unlike agent-army (which is for code changes), this is for DATA tasks -- processing 1000 documents, analyzing datasets, bulk content generation. Configurable swarm size, task distribution, result aggregation, progress tracking, and error recovery.
Connect to local LLM endpoints (Ollama, llama.cpp, vLLM) with automatic provider fallback. Use when: (1) you need to run LLM inference locally for privacy/cost, (2) you want to use models not available via cloud APIs, (3) you need offline capability, (4) you want automatic fallback to cloud providers when local fails.
Guide for creating, improving, benchmarking, and packaging Claude Agent Skills (SKILL.md files). Invoke when users want to create a skill from scratch, improve or test an existing skill, benchmark skill performance with variance analysis, or optimize a skill description for triggering accuracy. Also invoke when users say "turn this into a skill", "make a skill for X", "help me write a SKILL.md", "my skill isn't firing correctly", or want to convert a workflow/conversation into a reusable skill. Invoke proactively when a conversation has produced a repeatable workflow worth capturing. If the user mentions SKILL.md, skill files, skill descriptions, or skill triggering, this skill applies.
POLAR v2.4 — ETH Alpha Hunter (sniper recalibration). Single-asset ETH lifecycle scanner with conviction-scaled leverage, move-exhaustion scoring, and same-direction re-entry cooldown. v2.4 recalibration after -31.7% ROE on 381 trades: MIN_SCORE raised 8→10 (Cheetah v5.1 APEX pattern), leverage tiers shifted to 7x at 10-11 / 10x at 12+, cooldown raised 120→240 min, new MIN_SM_ACCEL_PCT=0.3 hard gate on 15m velocity. DSL exit managed by plugin runtime via runtime.yaml.
Conduct deep research on any topic — get comprehensive reports with citations, key findings, and actionable insights in minutes. Use when user wants to "deep research", "research this", "investigate", "analysis report", "深度研究", "调研", "リサーチ", "심층 연구".
Provides autonomous project pattern learning by analyzing the codebase to discover development conventions, architectural patterns, and coding standards, then generates project rule files in .claude/rules/. Use when user asks to "learn from project", "extract project rules", "analyze codebase conventions", "discover project patterns", or wants to auto-generate Claude Code rules for the current project.