Loading...
Loading...
Found 231 Skills
Orchestrates end-to-end interview preparation for senior ML/AI engineers targeting Anthropic and peer companies. Use for prep timeline generation, story coherence across rounds, mock scheduling, and debrief analysis. Activate on "interview prep", "interview loop", "Anthropic interview", "prep timeline". NOT for resume writing, career narratives, or individual round-type practice.
When the user wants to plan production or distribution capacity, analyze capacity requirements, optimize resource utilization, or balance capacity with demand. Also use when the user mentions "capacity analysis," "resource planning," "bottleneck analysis," "capacity expansion," "load balancing," "throughput planning," "utilization optimization," or "capacity modeling." For production scheduling, see master-production-scheduling. For long-term network capacity, see network-design.
Social media management strategy — publishing, scheduling, content calendars, engagement workflows, analytics, team collaboration, tool comparison (Sprout Social, Hootsuite, Buffer, Agorapulse, Sendible, Later, Brandwatch, Meltwater Engage, Influencity, Pallyy, Statusbrew, Sociality.io, Loomly, Planable). Use when social posts aren't getting engagement, you're spending too much time manually publishing, your content calendar is chaotic, you don't know when to post for best reach, DMs and comments are piling up unanswered, team approval workflows are slowing you down, or you can't prove social media ROI. Do NOT use for platform-specific config (use /sales-later, /sales-sproutsocial, /sales-meltwater, /sales-brandwatch, or /sales-influencity), social listening strategy (use /sales-social-listening), influencer marketing (use /sales-influencer-marketing), or paid social ads (use /sales-retargeting or /sales-b2b-advertising).
Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info. Use when the user asks about their emails, calendar, contacts, meetings, or scheduling.
Designing meeting schedulers and booking experiences that qualify leads, set up calls well, and convert at higher rates than a generic Calendly link. Availability logic, qualification gating, prep automation, follow-up sequencing. Honest about any-time-friction (no qualification, just a booking link), interrogation-gate (so much qualification it scares users off), and qualified-fast-path (just enough qualification to set up the call well) patterns. Triggers on scheduler design, meeting booking, demo scheduling, sales call scheduling, calendar tool, booking page, qualification flow. Also triggers when sales team complains about cold demos, when booking conversion is poor, or when scheduler is being scoped for the first time.
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
Analyze host/CPU overhead in TensorRT-LLM inference from nsys traces. Detect whether host overhead is the bottleneck using GPU idle ratio, host prep exposed ratio, and per-phase evidence. For regressions, isolate forward steps via allreduce/NVTX patterns, compare host operation breakdowns across versions, and identify scheduling or request-management overhead. Supports optional inter-kernel gap, eager-vs-graph, pattern mapping, and multi-rank straggler drill-down. Use standalone or within perf-analysis. Triggers: host overhead, inter-step gap, scheduling overhead, forward step isolation, nsys iteration analysis, NVTX breakdown, request management overhead, GPU idle, host bottleneck, host prep exposed, inter-kernel gap, bubble analysis, graph coverage, eager kernel, rank imbalance, straggler detection.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
Track, categorize, and prioritize technical debt across the codebase. Scans for debt indicators, maintains a debt register, and recommends repayment scheduling.
This skill should be used when interfacing with the Buffer social media scheduling API. It handles scheduling social media posts, checking the queue, listing channels, creating ideas, and managing Buffer accounts.
Operate SkipCalls AI phone receptionists through MCP. Use when the user mentions SkipCalls, AI receptionist/answering service/front desk, missed or inbound calls, call transcripts, scheduling a one-time outbound call, greetings, tasks, calendars, transfers, SMS behavior, business profile Q&A, or MCP connector setup.
Cron and scheduled task management. node-cron, cron expressions, Spring @Scheduled, APScheduler (Python), and distributed scheduling patterns. USE WHEN: user mentions "cron", "scheduled task", "cron job", "node-cron", "@Scheduled", "APScheduler", "periodic task", "crontab" DO NOT USE FOR: job queues with workers - use `job-queues`; one-off delayed tasks - use `job-queues`