416 skills · sorted by relevance
Investigate malicious code placed inside legitimate Windows processes using memory analysis, event logs, and API monitoring. Identify injection methods, examine extracted code, and produce evidence reports and detection rules for suspicious process behavior.
Investigate suspicious mobile apps by examining permissions, network traffic, and runtime behavior. Use observed evidence to identify signs of data theft, SMS interception, credential stealing, or communication with attacker control servers, then classify the suspected malware.
Build or tune a monitoring pipeline that learns normal user behavior from activity logs. Use Elasticsearch or OpenSearch to score unusual activity, compare colleagues in similar roles, and combine warning signs into insider threat alerts.
Analyze authentication logs to spot suspicious sign-ins, password attacks, and possible account compromise. Statistical baselines and machine learning help compare login activity with normal user behavior, while example SIEM queries support security investigations.
Analyze AWS CloudTrail logs against normal activity patterns to spot unusual API calls, IP addresses, errors, and sensitive changes. Produce a JSON report with anomaly scores, suspicious users, and suggested investigation steps.
Investigate possible insider threats by correlating endpoint and security logs. Examine unusual data access, off-hours activity, bulk downloads, and privilege abuse, then document supporting evidence, risk, confidence, and recommended actions after checking the context for false positives.
Investigate business email compromise, where impersonated executives or vendors request payments or sensitive data. Check sender details, unusual communication patterns, mailbox changes, and payment approval procedures to develop detection rules and verification controls.
Analyze endpoint, cloud storage, and email logs for signs of insider data theft. Use pandas to compare upload volumes with normal user behavior and examine data loss prevention alerts, unusual file access, and activity outside working hours.
Deploy CrowdStrike Falcon sensors across Windows, macOS, and Linux endpoints. Configure threat prevention and response policies, verify installation and detection, troubleshoot sensor issues, and connect events to SIEM platforms, which collect security logs for analysis.
Collect indicators of compromise, technical clues such as suspicious domains and file hashes, from incident evidence. Add context and confidence scores, then prepare them for detection, blocking, and structured sharing with partners.
Apply consistent architecture and coding conventions when building cross-platform apps with Avalonia UI and Zafiro. The skill guides separation of interface and logic, reactive data handling, explicit error results, and reuse of existing helpers.
Turn a resume and job description into interview questions, talking points, and structured experience stories. Organize answers around situation, task, action, and result, and prepare a tailored introduction and questions for interviewers.
Investigate why a PyTorch model behaves a certain way by changing its internal values with pyvene. The skill guides experiments that swap or remove activations, train interventions, compare outputs, and save or share intervention configurations.
Design tests that assess an AI agent's capabilities and reliability. Covers repeated runs to measure variation, checks for required behavior, and adversarial testing to expose failures that ordinary successful examples may miss.
Adapt an AI agent’s approach to brainstorming, implementation, debugging, review, teaching, or release preparation. Defines how each mode should ask questions, prioritize work, and present results, with automatic mode selection and explicit switching examples.
Guide an RxJS 7 project to RxJS Next by testing existing behavior, reviewing how subscriptions start and end, and validating small batches of changes. Record approved behavior choices, verification results, and unresolved blockers in migration reports.
Prepare self-assessments, manager reviews, and documents for meetings that align employee ratings. Structure achievements, goal evidence, development plans, and promotion cases, turning vague feedback into specific observations about behavior and impact.
Create or improve AI prompts through a guided conversation about goals, roles, examples, and output formats. Receive a complete, reusable prompt with an explanation of its design, including behavioral boundaries for public-facing AI roles when needed.
Analyze meeting transcripts to understand speaking share, verbal habits, listening, and facilitation. Receive feedback grounded in specific quotes, practical suggestions for future meetings, and comparisons across periods when enough meeting data is available.
Investigate hidden attacker activity using focused hypotheses, indicators of compromise such as malicious domains, and statistical checks on logs. Rank investigation priorities, generate indicator sweep targets, and flag unusual behavior for human review.
Choose checks for cmux changes, add tests that reproduce observable bugs, and verify that Swift test files are included in build targets. It also guides local and CI validation, including evidence that selected tests actually ran.
Turn survey responses, interviews, and other research data into three distinct user personas. Each profile explains the outcome users seek, their main difficulties, desired benefits, an unexpected behavioral insight, and how well the product meets their needs.
Review skill and agent definitions for structural issues and whether their instructions meet expected behavior. Four modes cover structure, test specifications, category criteria, and coverage reports that reveal missing specifications or checks.
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.