Loading...
Loading...
Found 1,930 Skills
Run a single experiment iteration. Edit the target file, evaluate, keep or discard.
Connect AI agents to your live Chrome session via CDP for real-time tab interaction, screenshots, and JS evaluation without re-login
Run isolated eval and grading calls using CC 2.1.81 --bare mode. Constructs claude -p --bare invocations for skill evaluation, trigger testing, and LLM grading without plugin/hook interference. Use when running eval pipelines, grading skill outputs, benchmarking prompt quality, or testing trigger accuracy in isolation.
Execute a comprehensive React Project Health Audit. Analyzes tech stack, architecture, state management, testing, code quality, performance, CI/CD, and documentation. Produces a Google Docs-ready report with section scores and weighted overall score. Use when the user asks to audit a React project, run a health check, evaluate frontend quality, or assess technical debt. Triggers on: 'react audit', 'health audit', 'react health', 'frontend audit', 'next.js audit', 'vite audit', 'project quality check'.
Code-first Netra best-practices playbook covering setup, instrumentation, context tracking, custom spans/metrics, integration patterns, evaluation, simulation, and troubleshooting.
Critical analysis of research papers, academic manuscripts, preprints, and technical studies — evaluating methodology, claims-evidence alignment, contribution significance, and intellectual honesty. Produces coherent analytical responses (not checklists) that distinguish genuine weaknesses from standard field limitations. Governs intellectual posture: collegial reader, not adversarial reviewer. Triggers on: "critique this paper", "review this research", "what do you think of this paper", "analyze this study", "evaluate the methodology", "is this paper sound", "assess this research", "strengths and weaknesses of this paper", "does the evidence support the claims". Use this skill when the user provides a research paper, preprint, or technical study and asks for critical evaluation of its scientific merit, methodology, or contribution — not formatting, citation hygiene, or submission readiness (use manuscript-review for those).
Apply Difference-in-Differences (DID) to estimate causal treatment effects by comparing changes in outcomes between treatment and control groups. Use this skill when the user evaluates policy interventions, natural experiments, or regulatory changes, needs to test parallel trends, or when they ask 'did this policy work', 'how do I identify causal effects without randomization', or 'what is the treatment effect'.
Find and evaluate research datasets for any scientific question. Teaches how to reason about data needs, search across public repositories, evaluate dataset fitness, and identify access requirements. Use whenever users ask to find data, search for datasets, identify cohort studies, or need data for analysis. Also use when users ask about a specific survey or cohort (NHANES, HRS, UK Biobank, TCGA, etc.), when they want to know what data exists for a research question, or when they need to compare available data sources. If the user mentions "where can I get data" or "is there a dataset for X", this is the right skill.
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; add tracing or @observe; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools, retrieval, or agent behavior from eval failures. AI agents are the primary use case. Covers Python SDK, pytest eval suites, CLI generation, tracing, Confident AI reporting, and agent-driven improvement loops. DO NOT TRIGGER for unrelated generic pytest, non-AI test setup, or non-DeepEval observability work unless the user asks to compare or migrate to DeepEval.
Migrate an application with hardcoded LLM prompts to a full LaunchDarkly AgentControl implementation in five stages: audit the code, wrap the call, move the tools, add tracking, attach evaluators. Use when the user wants to externalize model/prompt configuration, move from direct provider calls (OpenAI, Anthropic, Bedrock, Gemini, Strands) to a managed config, or stage a full hardcoded-to-LaunchDarkly migration.
Use when the user asks to "create an evaluator", "create evals", "create a scenario", "write a test scenario", "design a test case", "test my agent", "build eval coverage", "plan a test suite", "create red team tests", "set up test profiles", "configure conditional actions", "write a conditional action evaluator", "build a deterministic test", "design an IVR test", "IVR navigation test", "write a unit test for a voice agent", "build a regression test", "scripted scenario", "scripted voice test", "structured evaluator", "exact flow test", "sequential conditions", "fixed sequence test", or "run evals". Covers individual evaluator design, suite coverage strategy, test profiles, mock-tool data design, conditional actions (deterministic / unit test / regression / IVR navigation flows), and best practices for workflow / red-team / edge-case / deterministic test types.
Measure and improve the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For deployment, use agent-platform-deploy.