Loading...
Loading...
Found 2,435 Skills
Run scored behavioral evaluations and repair gaps. Use when the user says "evaluate this agent" or "I want proof this behaves correctly"
Help users evaluate emerging technologies. Use when someone is assessing new tools, making build vs buy decisions, evaluating AI vendors, or deciding on technical architecture.
Professionally evaluate story outlines, judge and score from the dimensions of market potential, innovation attributes, and content highlights. Suitable for story outline quality assessment, IP adaptation potential judgment, and project approval decision-making
Consult this skill when building evaluation or scoring systems. Use when implementing evaluation systems, creating quality gates, designing scoring rubrics, building decision frameworks. Do not use when simple pass/fail without scoring needs.
Applies multi-disciplinary cognitive frameworks (e.g., Inversion, First Principles, Second-Order Thinking) to user plans and system designs to stress-test decisions.
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).
Evaluate multimodal AI agents that process images, audio, PDFs, or other files. Sets up evaluations using LangWatch's LLM-as-judge with image inputs, Scenario's multimodal testing, and document parsing evaluation patterns. Use when your agent handles non-text inputs.
Use this skill when the user asks how much their app is worth, what they could sell their app for, how app valuations or acquisitions work, or how to prepare a subscription app for sale/exit.
Organize online information of IPs and conduct multi-dimensional evaluation and scoring. Suitable for assessing the adaptation value of IPs such as novels and scripts, analyzing market potential and innovative attributes
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, or plugin-owned Evaluator skills.
Determine and execute the smallest defensible EvalGate workflow for an AI change, response, artifact, or non-chat model event. Use for prompts, models, tools, agents, retrieval, skills, MCP, judges, datasets, routing, safety, cost, latency, release policy, external optimization imports, or governed improvement and confirmation cycles; skip it for work proven not to affect observable AI behavior.
Use for search evaluation, a POC or bake-off, Parallel vs Exa/Tavily comparisons, SimpleQA/DeepSearchQA benchmarks, or diagnosing search evaluation results. For product selection use choose-your-parallel-api; for integration migration use migrate-to-parallel.