Loading...
Loading...
Found 155 Skills
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.
Generate the competitive analysis section with competitor profiles, SWOT analysis, competitive matrix, differentiation strategy, market share positioning, and sustainable competitive advantage (moat). Proves the business can win against alternatives. Use when building or reviewing competitive analysis sections, benchmarking against competitors, or defining market positioning. Incorporates Farris's competitive metrics, guerrilla positioning strategy, value-based differentiation frameworks, Teece's business model vs strategy distinction (business model = architecture of value creation and capture; strategy = how the model is made difficult to imitate), Kaza's four differentiation types (aesthetic experience, social experience, boundary interactions, purposeful experiences), Ohmae's 3C Strategic Triangle and Key Factors for Success, and the Portable MBA onstage/backstage model with Value Net complementors framework.
Design, build, and optimize dashboards for RIA practice management with AUM tracking, revenue analytics, and KPI frameworks. Use when the user asks about tracking firm-level metrics, monitoring advisor productivity, measuring organic growth rate, analyzing client retention and attrition, building executive or branch manager views, setting up exception alerts for NIGO or rebalancing drift, benchmarking against industry peers, or designing role-based dashboard access. Also trigger when users mention 'how is the practice doing', 'revenue per advisor', 'client attrition', 'net new assets', 'effective fee rate', 'practice benchmarking', 'AUM growth decomposition', 'advisor capacity', or 'referral tracking'.
Automates benchmark test creation for C++ projects using Google Benchmark with consistent software testing patterns. Use when creating performance benchmarks, profiling tests, or when the user mentions benchmarking, Google Benchmark, or performance testing.
Benchmark vLLM or OpenAI-compatible serving endpoints using vllm bench serve. Supports multiple datasets (random, sharegpt, sonnet, HF), backends (openai, openai-chat, vllm-pooling, embeddings), throughput/latency testing with request-rate control, and result saving. Use when benchmarking LLM serving performance, measuring TTFT/TPOT, or load testing inference APIs.
Use this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
Quickly creates new Claude Code skills or translates ChatGPT projects into Claude Code skills. Handles skill scaffolding, frontmatter, directory structure, and ChatGPT-to-Claude migration. Use when the user wants to 'create a skill,' 'make a new slash command,' 'convert a ChatGPT project,' 'translate a GPT to Claude,' or 'migrate prompts to Claude Code.' For full eval/testing/benchmarking workflows, use skill-creator instead.
Generate realistic synthetic evaluation datasets by analyzing the user's codebase, prompts, production traces, and reference materials. Interactive, consultant-style — asks clarifying questions, proposes a plan, generates a preview for approval, then delivers a complete dataset uploaded to LangWatch. Use when user asks to generate, create, or build a dataset for evaluation, testing, or benchmarking.
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations, and team alignment trigger questions. Final step in the three-skill competitive pipeline.
Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong to, and which sources to mine. First step in the three-skill competitive pipeline; precedes benchmark-methodology.
Retrieve ESG benchmark comparison metrics by sector using Octagon MCP. Use when comparing ESG performance across industries, analyzing sector-level sustainability benchmarks, identifying ESG leaders and laggards by industry, or referencing frameworks like MSCI, S&P Global, CDP, and CSRD.