Loading...
Loading...
Found 147 Skills
End-to-end SGLang SOTA performance workflow. Use when a user names an LLM model and wants SGLang to match or beat the best observed vLLM and TensorRT-LLM serving performance by searching each framework's best deployment command, benchmarking them fairly, profiling SGLang if it is slower, identifying kernel/overlap/fusion bottlenecks, patching SGLang code, and revalidating with real model runs.
Quickly creates new Claude Code skills or translates ChatGPT projects into Claude Code skills. Handles skill scaffolding, frontmatter, directory structure, and ChatGPT-to-Claude migration. Use when the user wants to 'create a skill,' 'make a new slash command,' 'convert a ChatGPT project,' 'translate a GPT to Claude,' or 'migrate prompts to Claude Code.' For full eval/testing/benchmarking workflows, use skill-creator instead.
Generate comprehensive philosophy and standards documents for any domain (UX design, landing pages, email outbound, API design, etc.). Load when user says "create philosophy doc", "generate standards for [domain]", "build best practices guide", or "create benchmarking document". Conducts deep research, synthesizes findings, and produces structured philosophy documents with principles, frameworks, anti-patterns, checklists, case studies, and metrics.
Social listening and brand monitoring strategy — monitoring, Boolean queries, sentiment, competitive intel, crisis detection, AI visibility monitoring, LLM brand mentions. Platform comparison (Meltwater, Brandwatch, Talkwalker, Brand24, Sprout Social, Mention, Hootsuite, BrandJet, Influencity), monitoring setup (keywords, sources, alerts), sentiment analysis, competitive benchmarking (share of voice), crisis detection (real-time alerts, escalation), consumer insights, and reporting. Use when you don't know what people are saying about your brand, competitors are getting mentioned more than you, negative sentiment is spiking and you need to understand why, you're missing PR crises until it's too late, you can't tell if your brand shows up in AI/LLM answers, or you need to pick the right social listening tool. Do NOT use for platform-specific config (use /sales-meltwater), influencer discovery (use /sales-influencer-marketing), social media publishing/scheduling, or SEO keyword research (use /sales-semrush).
Terminal-Bench integration for Mux agent benchmarking and failure analysis
DTC Data Dashboard & Health Check Engine — Full-link data analysis, KPI tracking, industry benchmarking, data health assessment, market trend monitoring. Use when user mentions: data health check, data audit, KPI, dashboard, metrics tracking, metrics, baseline, benchmark, data analysis, revenue report, channel data, advertising data, ROAS tracking.
Design and operate back-office account opening processes from application intake through activation. Use when building account opening automation or improving STP rates, reducing NIGO rejection rates from custodians or clearing firms, defining document requirements for trusts entities IRAs or estate accounts, implementing approval workflows and regulatory holds for complex account types, setting up multi-custodian account opening across Schwab Fidelity or Pershing, designing account numbering titling or classification schemes, troubleshooting account opening failures or processing delays, integrating with custodian or clearing firm submission systems, or benchmarking account opening cycle times and operational efficiency.
CRITICAL: Use for performance optimization. Triggers: performance, optimization, benchmark, profiling, flamegraph, criterion, slow, fast, allocation, cache, SIMD, make it faster, 性能优化, 基准测试
Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has an approved optimization plan from xcode-build-orchestrator, wants to apply specific build fixes, needs help implementing build setting changes, script phase guards, source-level compilation fixes, or SPM restructuring that was recommended by an analysis skill.
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
Jmeter Test Plan Creator - Auto-activating skill for Performance Testing. Triggers on: jmeter test plan creator, jmeter test plan creator Part of the Performance Testing skill category.