LangWatch
Official@langwatch
Offers structured engineering oversight through issue-driven implementation, architectural critique, and end-to-end browser validation for complex software repositories.
Agent Skills by LangWatch
Showing 41 vetted skills indexed across 1 GitHub repositories.
langwatchlangwatch
Read LLM traces and coding-agent sessions from LangWatch using the langwatch CLI.
langwatchfeature-map
Maintains the canonical LangWatch feature map JSON registry across APIs, MCP tools, CLI commands, and skills.
langwatchcode-review
Reviews code diffs against LangWatch codebase rules for IDs, multitenancy, layering, and naming.
langwatchlangwatch-kanban
Manage the LangWatch GitHub project board by syncing statuses, moving issues, and assigning work.
langwatchbrowser-pair
Drives a headed Playwright Chromium session for interactive UI feedback and live code verification.
langwatchtracing
Instrument Python and TypeScript codebases with LangWatch tracing and observability.
langwatchprovider-cost-comparison
Reprice real LangWatch token usage against other model providers including cache costs.
langwatchevaluations
Routes LangWatch evaluation requests to the experiments or online-evaluations skill.
langwatchtest-cli-usability
Write scenario tests verifying CLI tools work non-interactively for AI agents.
langwatchdebug-with-langwatch
Diagnose production LLM agent failures by inspecting LangWatch traces, spans, and monitor scores.
langwatchagent-improve
Turns production traces into tested agent improvements via hypotheses, scenario tests, and reviewable PRs.
langwatchdrive-the-ui
Executes live UI actions on the user's open LangWatch page via CLI commands.
langwatchexperiments
Creates and runs LangWatch batch experiments to test agents against datasets with evaluators.
langwatchtest-compliance
Creates scenario and red team tests verifying agents stay observational in regulated domains.
langwatchprompt-optimization
Improves prompts on the LangWatch evaluations workbench through a measured baseline-to-candidate loop.
langwatchdatasets
Generate realistic synthetic evaluation datasets and upload them to LangWatch.
langwatchonline-evaluations
Configure LangWatch online evaluations and guardrails for production LLM traffic.
langwatchgenerate-rag-dataset
Generate synthetic Q&A evaluation datasets from a RAG knowledge base for LangWatch experiments.
langwatchlevel-up
Integrates LangWatch tracing, prompt versioning, evaluations, and simulation tests into an AI agent.
langwatchagent-performance
Diagnose production AI agent behavior from LangWatch analytics and traces into an HTML report.
langwatchevaluate-multimodal
Evaluate multimodal AI agents processing images, audio, and PDFs with LangWatch.
langwatchgithub
Clone repositories, commit changes, and open pull requests on GitHub via the gh CLI.
langwatchagent-best-practices
Audits agent codebases and LangWatch traces, scenarios, and evaluators against engineering best practices.
langwatchlwql-charts
Creates saved LangWatchQL analytics charts with Vega-Lite specs and places them on dashboards.
Frequently Asked Questions About LangWatch
FAQPage SchemaWhat specific engineering tasks does LangWatch enable?▼
LangWatch enables structured issue-driven development, automated end-to-end browser validation, and multi-perspective code review synthesis. It facilitates architectural risk assessment and ensures test specifications align with standard pyramid quality metrics through systematic audit and planning phases.
Which technical personas benefit most from these capabilities?▼
Software engineers, quality assurance leads, and technical architects benefit from these capabilities. It is designed for teams managing complex repositories who require rigorous oversight, consistent feature file generation, and high-fidelity validation of browser-based interfaces.
What are the prerequisites for implementing these capabilities?▼
Implementation requires a GitHub-based repository structure and existing support for Playwright-compatible environments. Users must define acceptance criteria within feature files to enable the planning, coding, and review loops effectively.