Loading...
Loading...
Found 301 Skills
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
Use this skill when an AI agent needs to inspect, verify, debug, or profile a live Vite app by running temporary snippets inside the browser page and reading browser logs or captured artifacts. Use for client state after interactions, imported app modules, DOM state, human-like input, canvas/WebGL/Three.js state, screenshots, videos, CPU/network/performance/heap analysis, WebXR/Three.js XR with IWER, and runtime-only behavior without editing app files.
Conduct a full-spectrum public intelligence (OSINT) investigation on any individual given their name, job title, and company. Produces a structured intelligence dossier. Use when asked to research a person, build a profile, investigate a contact, create a dossier, or gather publicly available intelligence on an individual.
Diagnose inference regressions with Doppler's shared browser/Node command contract, runtime presets, and report artifacts. (project)
Audit datasets for completeness, consistency, accuracy, and validity. Profile data distributions, detect anomalies and outliers, surface structural issues, and produce an actionable remediation plan.
Visualize a specific transformer decoder layer from an AutoDeploy FX graph text dump as a hierarchical DOT/PNG diagram. Optionally annotate nodes with actual GPU kernel names and durations from an nsys trace. Use when the user wants to visualize, inspect, or debug a layer in an AutoDeploy model graph dump. Triggers on: "visualize layer", "show layer", "graph of layer", "layer visualization", "dump graph layer". Assumes graph dumps already exist in a directory (produced by AD_DUMP_GRAPHS_DIR).
Research competitors using web search, product pages, review sites, and public data. Use when a PM needs competitive intelligence, feature comparisons, or market positioning analysis.
Market and competitive analysis toolkit. Research competitors, analyze market positioning, identify differentiation opportunities, and create comprehensive competitive landscape assessments for software projects.
Porter's Five Forces, SWOT analysis, and competitive landscape mapping. Use when analyzing market position, evaluating competitive threats, building battlecards, or assessing industry dynamics.
Build detailed ideal customer profiles with pain points, objections, buying triggers, and messaging angles. Includes community research to find where ICPs gather online and extract their exact language. Use when researching audiences, creating buyer personas, or developing targeted messaging.
Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.
Inspect LLM torch profiler traces at forward-pass, layer, and kernel level. Use when you need layer timings, anchor-kernel boundaries, representative kernel flows, or Perfetto time ranges.