Loading...
Loading...
Found 1,211 Skills
Use whenever the user mentions LLM prompt/prefix cache misses, cached_tokens=0, cache_read_input_tokens/cache_creation_input_tokens, prompt_cache_key, cache_control/cachePoint placement, stable prefixes, tool/schema stability, TTFT/prefill latency, OpenAI/Claude/Bedrock/OpenRouter routing, vLLM/SGLang KV reuse, or LLM cost/speed regressions on repeated long prompts. Use when reviewing LLM request shape changes: prompt text, message order, request builders, tools, schemas, response_format, provider API surface, model/router settings, agent loop structure, context compaction, or inference deployment. Use for speeding up agents only when prompt-cache stability, TTFT, or cache cost is central. Do not use for generic prompt writing, generic RAG design, token counting, or non-LLM performance.
Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
Run an autonomous Humanize-governed SGLang SOTA performance loop for one LLM model: first perform the fixed fair SGLang/vLLM/TensorRT-LLM deployment search and benchmark, then start one RLCR loop that repeatedly decides the gap, profiles the current bottleneck, runs layer/kernel pipeline analysis, patches SGLang code, optionally uses ncu-report-skill for kernel evidence, and revalidates until SGLang matches or beats the best observed framework under the same workload and SLA.
Rewrite AI-generated text to sound natural and human-written. Removes LLM tells — cliché phrases, predictable structure, inflated language, and robotic patterns. Use when editing drafts, emails, articles, or any text that reads like it was written by AI.
Eight-axis judgment code review for the current diff — Correctness, Simplification, Tests, Documentation, Style, Intent, Design/API, Performance (+ Coherence on metadata changes). Five-phase pipeline scope → deterministic tool battery (npx/uvx-preferred, zero-install for the JS + Python majority) → 8 parallel LLM axis reviewers → Haiku validators on sub-80 findings (verbatim rubric, ≥80 threshold) → synthesis with no-silent-drop + Conventional Comments JSONL. Every report closes with "What I did NOT check" (security → /security-review, runtime perf, flaky detection). Opt-in flags `--verify-build`, `--mutation-test`, `--reconcile`, `--apply-safe`. Public-skill posture — zero auto-install, graceful skip on missing native tools.
Bootstrap evaluators from production traces — emit SDK code, a framework-agnostic JSON spec, or publish online LLM-judge evaluators directly to Datadog. Use when user says "bootstrap evaluators", "generate evaluators", "create evals from traces", "eval bootstrap", "write evaluators", "build eval suite", "publish evaluators", or wants to generate BaseEvaluator/LLMJudge code or online judge configs from production LLM trace data. Works with ml_app and optional RCA report or failure hypothesis.
Router skill for LLMQuant equities workflows. Use when the user needs stock analysis, equity comparison, research memos, merger-arb memos, or sell/take-profit work.
Router skill for LLMQuant commodities workflows. Use when the user needs commodity spot, futures curve, inventory, roll yield, or macro linkage analysis.
Router skill for LLMQuant hedge-fund and PM strategy workflows. Use when the user needs equity long/short, long-biased, event-driven, macro, quant, or multi-strategy playbooks.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration. Use when "build agent, AI agent, autonomous agent, tool use, function calling, multi-agent, agent memory, agent planning, langchain agent, crewai, autogen, claude agent sdk, ai-agents, langchain, autogen, crewai, tool-use, function-calling, autonomous, llm, orchestration" mentioned.