Total 55,321 skills, AI & Machine Learning has 9191 skills
Showing 12 of 9191 skills
Use this skill when > Ultra-compressed communication mode that reduces token usage by ~75% by eliminating articles, filler words, pleasantries, and hedging while preserving technical accuracy. Activate with "caveman mode", "less tokens", "be brief", or "/caveman". Deactivate with "stop caveman" or "normal mode".
Analyze product reviews across any e-commerce platform. Extract actionable insights from customer feedback including pain points, praise patterns, feature requests, and sentiment trends.
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.
Use when testing, reviewing, pressure-testing, refining, packaging, or validating agent skills for academic research workflows before installing or relying on them.
Generates a self-contained Python experiment client that uses the ddtrace.llmobs SDK. Emits either a runnable .py script or a Jupyter .ipynb notebook matching the canonical DataDog reference notebook style. Use when the user says "generate Python experiment", "write an SDK experiment", "create a ddtrace experiment", "Python notebook experiment", "use the LLM Obs SDK", or has `ddtrace` installed and wants idiomatic SDK code.
Configure an AI agent to send OpenTelemetry traces to Coval. Use when a user wants to add Coval tracing, instrument an agent for simulations or conversation monitoring, make traces show up in Coval, handle SIP/PSTN/WebSocket trace correlation, or replace the one-command wizard with a security-reviewable manual setup.
Interactively set up a first Coval AI evaluation. Guides users through installing the CLI, connecting an agent, creating personas, building test cases, selecting metrics, and launching their first eval run. Use when user says "onboard", "get started", "set up evaluation", "first eval", "new to coval", or wants help creating their first test run.
For in-depth research on the core investment logic of individual stocks, focusing on individual stock research / fundamental analysis / institutional research. This Skill is mainly applied in scenarios such as question answering, report writing, and financial article creation. The output content of this report is relatively extensive, making it unsuitable for simple conversation scenarios. For acquiring various information and data, the wind.financial.data tool can be used with appropriate keywords or keyword combinations. After users input a stock name, they expect to quickly obtain a high-quality individual stock analysis similar to the style of sell-side analysts.
Interactive sub-agent creation skill for Claude Code. Use when user wants to create a custom subagent or mentions needing a specialized agent for specific tasks. This skill guides the entire subagent creation process including identifier design, system prompt generation, skill/context selection, and writing properly formatted agent files to .claude/agents.
Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.
Systematic approach to exploring the TensorRT-LLM codebase before implementing new features or optimizations. Teaches how to discover existing infrastructure, trace code paths, and avoid reimplementing what already exists. Derived from real mistakes where ~250 lines of code were written and deleted because existing forward methods weren't discovered upfront. Use when starting any new feature, optimization, or code modification in TRT-LLM.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.