Loading...
Loading...
Found 843 Skills
Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.
Generates a heat-map and metrics report of a repository based on code complexity, lack of tests, and 'TODO/FIXME' density. Use when you need to identify high-risk areas for refactoring or when planning technical debt reduction sprints.
This skill should be used when the user asks to "set up oodle integration", "onboard to oodle", "integrate kubernetes with oodle", "connect AWS to oodle", "install oodle collector", or mentions setting up observability with Oodle. Discovers the environment, recommends matching integrations from available setup specs, and executes step-by-step installation. Not for querying existing metrics, logs, or traces (use /oodle-metrics-query, /oodle-logs, /oodle-traces instead).
Use when the user asks "what predefined metrics are available", "which built-in metrics should I use", "what does CSAT measure", "how does hallucination detection work", "what's the difference between Interruption Score and AI Interrupting User", "which metrics are free", "which metrics need audio", "configure silence threshold", "set up sentiment metric", or any question about Cekura's out-of-the-box metrics. Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options, and when to use each one.
Install and configure ktx, the self-improving context layer that teaches AI agents to query data warehouses accurately with approved metrics, semantic layer, and business knowledge.
Context layer for AI data agents - query warehouses accurately with semantic layers, metrics, and wiki knowledge through MCP
Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experiment's learner on a portion of the real `data/` source and predicts on a *disjoint* portion that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is the executable proof of the X-marker placement rule from `build-ml-pipeline`. TRIGGER when: `test-ml-pipeline` has dispatched here to write the smoke test for an approved experiment; `pytest tests/smoke/` is failing on row count; the user asks "why is the smoke test failing?"; a pipeline edit in `build-ml-pipeline` needs an executable proof; an experiment script changes the pipeline shape and the matching smoke test needs revisiting. SKIP when: the design note does not exist or is not yet approved (route to `iterate-ml-experiment`); the user is asking about a regression test or schema invariant (route to `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` once those exist); the question is the *interpretation* of CV metrics, not predict-time correctness (route to `evaluate-ml-pipeline`). HOW TO USE: read the matching experiment's `journal/NN_*.md` and `experiments/NN_*.py` first to understand the pipeline's source binding (what env-dict keys does `build_learner` expect?). Then construct two env-dicts from the **real `data/` source** — a train env and a predict env — such that the predict env carries *only the rows we want predictions for* and *no pre-history buffer*. The hard assertion is that the prediction count matches the predict-env row count exactly. The soft assertion is that the smoke set's MAE is within `3 × CV_mean` (or the task-appropriate analogue). **Do not write the design note or run CV — that's other skills' job.**
Generates structured OKR plans (Objectives and Key Results) for teams and companies following Google/Intel methodology. Takes company goals, team function, quarter, and current metrics to produce a comprehensive okr-plan.md with objectives, key results, scoring criteria, alignment mapping, tracking cadence, and retrospective templates.
Master metrics definition, KPI tracking, dashboarding, A/B testing, and data-driven decision making. Use data to guide product decisions.
Guide teams and individuals through setting Objectives, Key Results (OKRs), and annual goals that translate strategy into measurable execution. Use when planning quarterly or annual cycles, setting individual or team goals, aligning on priorities, creating OKRs, writing SMART goals with FROM-TO metrics, reviewing goal cascades, or when the user asks about objectives, key results, goal setting, or planning frameworks. Do not use for purely operational SLA-driven work (use KPIs instead), uncertainty-heavy research (use Discovery OKRs), or reviewing past performance (use a check-in/feedback skill).
Build a growth strategy with frameworks, metrics, and experimentation. Use when the user says "growth strategy", "growth plan", "AARRR", "growth loops", "North Star Metric", "growth model", "activation rate", "retention strategy", "churn reduction", "growth experiments", or asks about overall growth frameworks and metrics for their product.
Detects unrealistic planning and hidden delivery risks like overcommitment, missing dependencies, resource mismatches, and undefined metrics. Use when reviewing quarterly roadmaps or sprint plans.