Loading...
Loading...
Found 202 Skills
Design and implement end-to-end client onboarding workflows from prospect intake through funded account, covering KYC verification, document collection, e-signature, and custodian submission. Use when the user asks about building a digital onboarding flow, integrating identity verification or CIP checks, reducing NIGO rejection rates, opening complex account types like trusts or entities, connecting to custodian APIs, designing suitability questionnaires, or comparing advisor-assisted vs self-service models. Also trigger when users mention 'new account opening', 'onboarding bottleneck', 'KYC integration', 'beneficial ownership', 'OFAC screening', 'account funding', or 'onboarding automation'.
Takes a manual business workflow description and designs the automated version. Maps current steps, handoffs, decision points, and bottlenecks. Designs automated flow with triggers, conditions, actions, and error handling. Outputs workflow-automation.md with before/after Mermaid diagrams, tool recommendations, implementation steps, and time savings estimate.
Run an autonomous Humanize-governed vLLM SOTA performance loop for one LLM model: first perform the fixed fair vLLM/SGLang/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches vLLM code, optionally uses ncu-report-skill for kernel evidence, and revalidates until vLLM matches or beats the best observed framework under the same workload and SLA.
Expert blueprint for performance profiling and optimization (frame drops, memory leaks, draw calls) using Godot Profiler, object pooling, visibility culling, and bottleneck identification. Use when diagnosing lag, optimizing for target FPS, or reducing memory usage. Keywords profiling, Godot Profiler, bottleneck, object pooling, VisibleOnScreenNotifier, draw calls, MultiMesh.
C++ template skill for reading template errors and optimizing compile times. Use when deciphering template error stacks, setting -ftemplate-backtrace-limit, writing concepts and requires-clauses, understanding SFINAE vs concepts, or profiling template instantiation bottlenecks with Templight. Activates on queries about C++ templates, template error messages, concepts, requires expressions, SFINAE, template metaprogramming, or slow template compilation.
Guides managers out of the bottleneck role — provides the Team Rep pattern, Epic Ownership model, Task-Relevant Maturity framework, kingdom ownership, and three-layer assignment strategy. Use when the user wants to delegate work or says "I'm doing everything," "team isn't taking ownership," "I can't let go," "team rep," "project ownership," "I'm the go-to person," "bus factor," "I work weekends," "how do I delegate," or "engineers don't take initiative." Do NOT use for managing a specific underperformer (use performance-reviews) or deciding what work to prioritize (use roadmap-planning).
Use when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring, procurement spend. Triggers on "BizOps review", "where's the bottleneck", "vendor health", "internal SOP", "all-hands deck", "spend categorization", "capacity for Q3", "process mapping". Forks context to route to one of six BizOps sub-skills (process-mapper, vendor-management, capacity-planner, internal-comms, knowledge-ops, procurement-optimizer) and returns a digest. Distinct from business-growth (external sales motion) and c-level-advisor (strategic, not operational).
Use when debugging a Nemo Gym run or reward profiling job. Covers rollout collection failures, empty or partial JSONL outputs, stale materialized inputs, verifier/schema errors, Ray or Slurm issues, vLLM readiness, judge failures, tool/sandbox failures, cache problems, and throughput bottlenecks.
Optimize Harness CI/CD pipeline performance via MCP. Configure parallel test execution with Test Intelligence, design multi-layer caching strategies, analyze pipeline bottlenecks with stage-level timing breakdowns, optimize cache hit rates, and design monorepo CI pipelines with selective builds. Use when asked to speed up pipelines, improve cache hit rates, set up parallel testing, optimize build times, or configure monorepo builds. Do NOT use for creating new pipelines (use create-pipeline instead) or debugging failures (use debug-pipeline instead). Trigger phrases: pipeline speed, slow pipeline, cache hit rate, parallel tests, test intelligence, build optimization, caching strategy, monorepo pipeline, pipeline bottleneck, build speed.
Diagnose Harness pipeline executions via MCP. Analyzes any execution (failed or successful) to produce structured reports with stage/step breakdown, timing, bottlenecks, failure details, chained pipeline drill-down, and execution logs. Use when asked to debug a pipeline, investigate a failure, find out why a build failed, analyze pipeline errors, check execution logs, review execution performance, or find bottlenecks. Trigger phrases: debug pipeline, pipeline failed, why did my build fail, analyze failure, pipeline error, execution logs, fix pipeline, execution bottleneck, slow pipeline.
Build on Snowflake's AI Data Cloud with snow CLI, Cortex AI (COMPLETE, SUMMARIZE, AI_FILTER), Native Apps, and Snowpark. Covers JWT auth, account identifiers, Marketplace publishing. Prevents 11 documented errors. Use when: Snowflake apps, Cortex AI SQL, Native App publishing. Troubleshoot: JWT auth failures, account locator confusion, memory leaks, AI throttling.
Optimize Linux system performance. Configure kernel parameters, analyze bottlenecks, and tune resources. Use when improving system performance.