Loading...
Loading...
Found 299 Skills
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).
Drop-in Vite/Webpack plugin that mirrors React Fiber trees, profiles renders, and provides visual debugging overlay for React 16-19 apps.
Profile and explore datasets to understand their shape, quality, and patterns before analysis. Use when encountering a new dataset, assessing data quality, discovering column distributions, identifying nulls and outliers, or deciding which dimensions to analyze.
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
Debugging and troubleshooting Tokio applications using tokio-console, detecting deadlocks, memory leaks, and performance issues. Use when diagnosing async runtime problems.
Evaluate GitHub contributors for MLOps/engineering roles. Use when analyzing candidates, researching GitHub profiles, or updating CONTRIBUTORS.md with hiring assessments.
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.
LinkedIn post generation from meeting transcripts, Slack dumps, and other source material, written in the user's personal writing style. Use this skill when: generating LinkedIn posts, creating social content from internal material, ghostwriting LinkedIn content, or when the user mentions LinkedIn, social posts, or content generation from transcripts/notes. Supports personal style profiles stored locally per user. Can auto-pull source material from Fireflies.ai, Slack channels, and Google Drive.
Segment users from feedback data based on behavior, JTBD, and needs. Identifies at least 3 distinct user segments. Use when segmenting a user base, analyzing diverse user feedback, or building a segmentation model.
Diagnose inference regressions with Doppler's shared browser/Node command contract, runtime presets, and report artifacts. (project)
Write a comprehensive design brief that defines the problem space, constraints, audience, and success criteria.
Implement content-based recommendation by matching item features to user preference profiles. Use this skill when the user needs to recommend items based on attributes, solve the cold start problem for new items, or build recommendations without collaborative data — even if they say 'recommend similar products', 'items like this', or 'feature-based matching'.