327 skills · sorted by relevance
Search Google SecOps events for threats that have not triggered alerts. Test attack hypotheses, check historical records for compromise indicators, and examine unusual activity, then document findings and add them to relevant security cases.
Investigate security incidents in Google SecOps by connecting host, user, and network events. Reconstruct attack timelines, trace movement between systems, assess affected assets, and organize findings into case notes and investigation reports.
Structure problem solving around clear goals, competing explanations, experiments, and measurable results. Use the cycle to diagnose bugs, validate features, compare prompts, or evaluate an early product, then choose the next step based on evidence.
Explore explanations for poorly understood phenomena through repeated hypothesis generation and selection. Compare causal mechanisms, test what happens when components change, and retain distinct candidates with predictions, rival comparisons, and clearly stated unresolved questions.
Investigate errors, crashes, and unexpected behavior by reproducing failures, tracing execution, and comparing logs. Tests one explanation at a time, then provides a verified fix, supporting evidence, and tests or safeguards to prevent recurrence.
Create distinct paid advertising concepts, headlines, copy, and production briefs from validated brand information and campaign goals. Each concept connects its message to evidence, audience needs, platform requirements, and a hypothesis to test.
Design and evaluate paid-ad experiments with clear hypotheses, comparison groups, sample requirements, and stopping rules. Check data quality before estimating effects, then deliver structured results and a plain-language decision that reflects uncertainty and the population tested.
Investigate bugs, failing tests, and unexpected behavior through reproducible steps, logs, and comparisons with working code. Follow four stages to identify the root cause, test a hypothesis, apply a focused fix, and verify the result.
Investigate bugs, failed tests, and unexpected behavior through reproducible steps, evidence gathering, and comparison with working code. Test one hypothesis at a time, then implement a focused fix and verify it with tests.
Hunt for signs of compromise in web and application logs without an initial alert. Establish normal activity, record investigative hypotheses, check source code, and reproduce issues locally before producing incident records and a report.
Evaluate an AI product or feature idea by connecting customer problems, business outcomes, testable assumptions, risks, and differentiation. Produce a structured recommendation with lightweight experiments, success measures, and next steps for an investment decision.
Turn business goals and customer problems into a product roadmap. Define initiatives, rank priorities, check dependencies and team capacity, and organize releases with clear reasons stakeholders can review and discuss.
Build an initial customer profile from existing research, market data, and team knowledge. Organize behaviors, frustrations, goals, and buying influences into a shared working hypothesis, with assumptions clearly marked for later validation.
Work through eight canvas sections to clarify a business problem, target users, desired outcomes, and possible solutions. Turn assumptions into testable hypotheses and choose the smallest experiment to investigate the most important uncertainty before development.
Use three adaptive questions to identify where product growth is stuck. The skill recommends a path through new customer segments, geographies, distribution channels, or products, then suggests a low-cost first experiment and a common trap to watch for.
Investigate bugs and failing tests through four stages: finding the root cause, comparing working patterns, testing a hypothesis, and implementing a fix. Uses reproduction steps, diagnostic evidence, and regression tests to check the result.
Review technical claims and deliverables by checking evidence and testing alternative explanations. Confirm that references and API endpoints exist, then report verified, unverified, or contradicted claims alongside evidence and an overall review verdict.
Analyze A/B test results to assess whether observed differences are likely due to chance. Check test duration and sample size, compare audience segments, distinguish statistical findings from practical value, and generate hypotheses for follow-up tests.
Develop a research idea through a structured conversation, then turn the answers into a written research specification. Clarify the question, testable hypothesis, data needs, methods for assessing cause and effect, expected findings, and feasibility.
Coordinate research from question development through literature searches, analysis, and publication with specialized agents. Supports quantitative, qualitative, and mixed methods studies, plus systematic reviews, with human approval at key decisions about research direction and methods.
Helps build a research framework by comparing theories, mapping relationships between variables, and deriving testable hypotheses. Explores less conventional options, examines weaknesses and competing explanations, and produces diagrams with anticipated reviewer objections.
Coordinate AI research from literature review to paper drafting. The skill alternates focused experiments with broader reviews of findings, tracks hypotheses and decisions, and uses specialist skills to carry out research tasks and prepare progress reports.
Test one risky assumption through a prototype with an agreed deadline, hypothesis, and success signal. Record observations and the source revision, then return a keep, discard, or inconclusive verdict with the status of each artifact.
Analyze research data with guidance on choosing statistical tests, checking their assumptions, and measuring effect sizes, meaning the magnitude of differences or relationships. It also supports sample size planning, Bayesian analysis, and APA-style reports.