{"$schema":"https://schemas.agentskills.io/discovery/0.2.0/schema.json","skills":[{"name":"tracing","type":"skill-md","description":"Add LangWatch tracing and observability to your code. Use for both onboarding (instrument an entire codebase) and targeted operations (add tracing to a specific function or module). Supports Python and TypeScript with all major frameworks.","url":"https://langwatch.ai/docs/.well-known/agent-skills/tracing/SKILL.md","digest":"sha256:02c69a6e8b92d36477ea9046d8107da395fd233b8c952ddf662185c41cc924eb"},{"name":"experiments","type":"skill-md","description":"Create and run LangWatch experiments for pre-deployment batch testing. Use when the user wants to test an agent against a dataset, compare prompts or models, benchmark quality, detect regressions, or add a CI quality gate. Do not use for production monitoring or guardrails.","url":"https://langwatch.ai/docs/.well-known/agent-skills/experiments/SKILL.md","digest":"sha256:3a7e3deefa086ae21a015238c579f4836048b52213eb8856f1164cff312a6952"},{"name":"online-evaluations","type":"skill-md","description":"Configure LangWatch online evaluations and guardrails for production traffic. Use when the user wants to score live traces or threads, monitor production quality, sample incoming traffic, or synchronously block unsafe requests and responses. Do not use for batch experiments.","url":"https://langwatch.ai/docs/.well-known/agent-skills/online-evaluations/SKILL.md","digest":"sha256:0c1a2d1a5a32986dd26ab6a376157c0fea3b2fd7dc14437e0a66757c1ed7e405"},{"name":"evaluations","type":"skill-md","description":"Compatibility router for LangWatch evaluation requests. Use only when the user asks for evaluations without making it clear whether they mean pre-deployment experiments or production online evaluations. Routes the request to the focused companion skill and does not implement either workflow itself.","url":"https://langwatch.ai/docs/.well-known/agent-skills/evaluations/SKILL.md","digest":"sha256:fb461d8b2b9ccb51f5717e398c13b6068ceace759c73de6136e2b8a381bbe7b2"},{"name":"scenarios","type":"skill-md","description":"Test your AI agent with simulation-based scenarios. Covers writing scenario test code (Scenario SDK), creating platform scenarios via the `langwatch` CLI against a connected agent, reading the run parameters that agent declares so the scenarios and comparison runs turn its real levers, and red teaming for security vulnerabilities. Auto-detects whether to use code or platform approach based on context.","url":"https://langwatch.ai/docs/.well-known/agent-skills/scenarios/SKILL.md","digest":"sha256:b78299005641d65e7973324920af0d412bfb4a067ffc0b7a1f57b84e4e2948f3"},{"name":"connect-agent","type":"skill-md","description":"Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run parameters, confirms the agent is Online, and runs the first test suite. Falls back to an HTTP registration when the agent cannot import the SDK. Use when the user wants platform scenarios to test their real agent.","url":"https://langwatch.ai/docs/.well-known/agent-skills/connect-agent/SKILL.md","digest":"sha256:e55ecd8a93642c6af7317e150908bad893629182bd96429a9b9e63f164a6a0bc"},{"name":"prompts","type":"skill-md","description":"Version and manage your agent's prompts with LangWatch Prompts CLI. Use for both onboarding (set up prompt versioning for an entire codebase) and targeted operations (version a specific prompt, create a new prompt version). Supports Python and TypeScript.","url":"https://langwatch.ai/docs/.well-known/agent-skills/prompts/SKILL.md","digest":"sha256:24d390d5f2c8d457af692d3b007cac18a24ceddcb0da91189467deec7eef3059"},{"name":"datasets","type":"skill-md","description":"Generate realistic synthetic evaluation datasets by analyzing the user's codebase, prompts, production traces, and reference materials. Interactive and consultant-style. Asks clarifying questions, proposes a plan, generates a preview for approval, then delivers a complete dataset uploaded to LangWatch. Use when user asks to generate, create, or build a dataset for evaluation, testing, or benchmarking.","url":"https://langwatch.ai/docs/.well-known/agent-skills/datasets/SKILL.md","digest":"sha256:f1f6432a57aa87365447e150938c1e35115d5e677d9282ad825d80ff03fac92a"},{"name":"context-sweet-spot","type":"skill-md","description":"Investigates the context economics of your own coding-agent sessions in LangWatch. Reads real sessions to find where carrying a fat context stops paying for itself, measured in cache rebuilds, compactions and cost per turn, and delivers a report with the context size your sessions should stay under, with example sessions behind every claim. Use when coding-agent sessions feel expensive or degrade as they grow.","url":"https://langwatch.ai/docs/.well-known/agent-skills/context-sweet-spot/SKILL.md","digest":"sha256:1aed228c1fd6e23d30a9bb5ca67df4308b3e4d1a7569681ea93d7f3b65954e2d"},{"name":"provider-cost-comparison","type":"skill-md","description":"Prices your real LangWatch usage mix against other model providers. Exports your actual token mix per model, including the cache read and write split, fetches current price cards, and reprices the same month of usage under each candidate, with the cache sensitivity stated. Use when someone asks whether a cheaper provider or model would actually save money on your workload.","url":"https://langwatch.ai/docs/.well-known/agent-skills/provider-cost-comparison/SKILL.md","digest":"sha256:cb776406acd12264a853938b441481f30b4d77d822f4d2cf1f3441401ff2c030"},{"name":"coding-agent-cost","type":"skill-md","description":"Reads your Claude Code sessions in LangWatch and recommends the settings that cut their cost and context, each with the evidence from your own data, the exact settings.json change and the expected saving marked as measured or estimated. Covers older model versions, the auto-compact window, the prompt cache lifetime for API-key and subscription users, the model your built-in sub-agents run on, and sessions that should have been split. Use when someone asks why their coding agents cost so much, how to make a Claude Code plan last longer, or which Claude Code settings to change.","url":"https://langwatch.ai/docs/.well-known/agent-skills/coding-agent-cost/SKILL.md","digest":"sha256:ed13ea9c7f2207b8b9226b4406f64f4f6ec61e68ee972326c7c4d22238a9088e"},{"name":"level-up","type":"skill-md","description":"Take your AI agent to the next level with full LangWatch integration. Adds tracing, prompt versioning, evaluation experiments, and simulation tests in one go. Use when the user wants comprehensive observability, testing, and prompt management for their agent.","url":"https://langwatch.ai/docs/.well-known/agent-skills/level-up/SKILL.md","digest":"sha256:c4e1d714ea48d10900c1100ab5d20a3cca33d6a2bffe6c2e03268da54a00808e"},{"name":"agent-improve","type":"skill-md","description":"Turns production evidence into tested improvements for your AI agent. Forms hypotheses from real traces and analytics, explains the reasoning behind each one, then executes with the user: scenario tests that reproduce production failures, prompt and code changes as reviewable PRs, new evaluators and monitors that capture production signals, and experiments that settle open questions. Use when you want to know what to do next to improve your agent.","url":"https://langwatch.ai/docs/.well-known/agent-skills/agent-improve/SKILL.md","digest":"sha256:45d8551f70b77d1a3c1dd2ab79c1fdfbf7ca00fc88ec04f622a05e314e3e55a0"},{"name":"agent-performance","type":"skill-md","description":"Deep-dive diagnosis of how your AI agent behaves in production. Explores LangWatch analytics and traces end to end to map failure patterns, dissatisfied users, token cost hotspots, edge cases, behavior changes, and outliers, then delivers an HTML report where every finding links to real example traces. Use when you want to truly understand what your agent is doing in production.","url":"https://langwatch.ai/docs/.well-known/agent-skills/agent-performance/SKILL.md","digest":"sha256:608249509578eea505897553bf3ea5a191a10d7b9f052be33f96c8b67e1ff4ea"},{"name":"agent-best-practices","type":"skill-md","description":"Expert AI engineering consultant for your agent development practices. Audits your codebase, traces, evaluations, and scenarios against best practices, then guides you to close the gaps, starting from low-hanging fruit and going deeper. Use when you want to level up your agent's engineering quality.","url":"https://langwatch.ai/docs/.well-known/agent-skills/agent-best-practices/SKILL.md","digest":"sha256:8d322ebc765fa509b9acf6ed727acb307d1783167b982433b77aa76f99bae8f2"},{"name":"debug-instrumentation","type":"skill-md","description":"Debug and improve your LangWatch traces. Inspects production traces for missing input/output, disconnected spans, unlabeled traces, and missing metadata. Use when traces look broken or incomplete.","url":"https://langwatch.ai/docs/.well-known/agent-skills/debug-instrumentation/SKILL.md","digest":"sha256:b0f0a05ad4e6cfeb933fbf7996becef0ccb59b36005ab9032a193c1a93af7160"},{"name":"debug-with-langwatch","type":"skill-md","description":"Root-cause production errors and misbehaving agent runs with LangWatch. Finds errored traces, inspects spans, checks monitor and evaluator scores, then narrows to a root cause. Use when something is failing or misbehaving in production (errors, bad answers, latency spikes).","url":"https://langwatch.ai/docs/.well-known/agent-skills/debug-with-langwatch/SKILL.md","digest":"sha256:be85ccd25796336b9a3b8db679703e2874297d4506805385987577d1fa3e4c0d"},{"name":"eval-triage","type":"skill-md","description":"Investigate failing experiments and evaluations with LangWatch. Triage a failing experiment run to the exact rows and evaluator scores that regressed, then to a root cause. Use when an experiment fails, scores drop, or evaluations regress.","url":"https://langwatch.ai/docs/.well-known/agent-skills/eval-triage/SKILL.md","digest":"sha256:910145bfff58dc31f856de57413a77abdc6fc4952d779b02a58d852596815925"},{"name":"evaluate-multimodal","type":"skill-md","description":"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.","url":"https://langwatch.ai/docs/.well-known/agent-skills/evaluate-multimodal/SKILL.md","digest":"sha256:b4a827794cc229ae1650d228bb05a368b55909c1f9978070bbe6a3f3ade8de23"},{"name":"generate-rag-dataset","type":"skill-md","description":"Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.","url":"https://langwatch.ai/docs/.well-known/agent-skills/generate-rag-dataset/SKILL.md","digest":"sha256:34278d5b494703c3a8e915a5895c64baa040a52a1cd6884080c5e75ffc7e55d8"},{"name":"setup-lw","type":"skill-md","description":"Set up and troubleshoot the LangWatch CLI, covering login (cloud and self-hosted), endpoint configuration, project selection, and connection problems. Use when the CLI isn't authenticated, can't reach LangWatch, or talks to the wrong project.","url":"https://langwatch.ai/docs/.well-known/agent-skills/setup-lw/SKILL.md","digest":"sha256:1affa2d1ad43e674156ddf209f65cca6dadaa2ff89d90f0e6dadbc37be0fa9d9"},{"name":"test-compliance","type":"skill-md","description":"Test that your AI agent stays observational and doesn't give prescriptive advice in regulated domains (healthcare, finance, legal). Creates scenario tests for boundary enforcement and red team tests for adversarial probing. Use when your agent advises but must not prescribe.","url":"https://langwatch.ai/docs/.well-known/agent-skills/test-compliance/SKILL.md","digest":"sha256:e433ef3725cd94fa94cb920255930824b568433fe6a60746e69cb02a9516d867"},{"name":"test-cli-usability","type":"skill-md","description":"Write scenario tests that verify your CLI tool is usable by AI agents. Ensures commands work non-interactively, provide clear output, and don't hang on prompts. Use when you want to prove your CLI is agent-friendly.","url":"https://langwatch.ai/docs/.well-known/agent-skills/test-cli-usability/SKILL.md","digest":"sha256:296d2c1f7c637b7e91737db0815a7ffe0680b714d02134760769b63210b48be1"},{"name":"lwql-charts","type":"skill-md","description":"Author a saved analytics chart from a plain question and place it on a dashboard. Discovers the LangWatchQL analytics schema, writes and test-runs the SQL, saves it as a chart with a Vega-Lite specification, and places it where the team already looks. Use when asked to build, save, run, or dashboard a metric or chart.","url":"https://langwatch.ai/docs/.well-known/agent-skills/lwql-charts/SKILL.md","digest":"sha256:6b7e8cf8120025b1f1a6d8df1776ccfa9e7f427d070bb1696d1ac3a59edb9e3b"},{"name":"dashboard-widgets","type":"skill-md","description":"Author a dashboard widget — a small React component backed by named LangWatchQL queries — from a plain question. Discovers the analytics schema, writes the queries, writes the widget file, saves it, then proves it renders. Use when asked to build, prototype, or iterate on a custom chart widget, or to add a widget beyond what a standard saved chart can express.","url":"https://langwatch.ai/docs/.well-known/agent-skills/dashboard-widgets/SKILL.md","digest":"sha256:9d54b9a67afdbabb6ceb22605a79f154af9fab6893c8d7de9aae6c37f0ca9fc6"},{"name":"find-traces","type":"skill-md","description":"Find the traces that match what the user describes, such as thumbs down, a user, an error, an evaluator label or a phrase. Drives the Trace Explorer when finding traces is the ask, and answers with result cards and a link when traces are a step in another task. Searches every form a concept can take before reporting that nothing matches. Use when asked to find, show, filter or count traces.","url":"https://langwatch.ai/docs/.well-known/agent-skills/find-traces/SKILL.md","digest":"sha256:582c9900b32493d5575004e64eb262bc67f13ffe5060b8f297b1c8153753119b"}]}