Loading...
Loading...
Found 776 Skills
Build a custom browser-based annotation interface tailored to your data for reviewing LLM traces and collecting structured feedback. Use when you need to build an annotation tool, review traces, or collect human labels.
Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction. Use after writing a judge prompt (write-judge-prompt) when you need to verify alignment before trusting its outputs. Do NOT use for code-based evaluators (those are deterministic; test with standard unit tests).
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).
Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces. Use when starting a new eval project, after significant pipeline changes (new features, model switches, prompt rewrites), when production metrics drop, or after incidents.
vLLM Ascend plugin for LLM inference serving on Huawei Ascend NPU. Use for offline batch inference, API server deployment, quantization inference (with msmodelslim quantized models), tensor/pipeline parallelism for distributed serving, and OpenAI-compatible API endpoints. Supports Qwen, DeepSeek, GLM, LLaMA models with Ascend-optimized kernels.
INVOKE THIS SKILL when building evaluation pipelines for LangSmith. Covers three core components: (1) Creating Evaluators - LLM-as-Judge, custom code; (2) Defining Run Functions - how to capture outputs and trajectories from your agent; (3) Running Evaluations - locally with evaluate() or auto-run via LangSmith. Uses the langsmith CLI tool.
LLM inference via paid API: OpenAI-compatible chat completions proxied through x402 providers. Supports Kimi K2.5, MiniMax M2.5. Uses x_payment tool for automatic USDC micropayments ($0.001-$0.003/call). Use when: (1) generating text with a specific model, (2) running chat completions through a pay-per-request LLM endpoint, (3) comparing outputs across models.
Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.
Auto-generates an LLM usage monitoring page in a PM admin dashboard. Tokuin CLI-based token/cost/latency tracking + user ranking system + inactive user tracking + data-driven PM insights + Cmd+K global search + per-user drilldown navigation. Supports OpenAI/Anthropic/Gemini/OpenRouter.
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.
Fact-checks LLM responses by extracting verifiable claims, verifying each via web search, producing an audit report with verdicts, and optionally revising inaccurate responses. Use when the user asks to audit, fact-check, double-check, or verify a response.