414 skills · sorted by relevance
Design employee access management across multiple systems using HR records. This skill covers account changes when people join, move roles, or leave, along with role definitions, approval workflows, periodic access reviews, and cleanup of accounts left behind.
Analyze how ransomware encrypts files and manages keys to assess whether decryption is feasible. Examine implementation weaknesses, check existing decryptors, and document recovery options with technical reasons for the assessment.
Reconstruct Windows folder browsing activity from Shellbag registry records using SBECmd and ShellBags Explorer. Investigate traces of deleted directories, disconnected USB drives, and network shares while accounting for limits in what the records and timestamps show.
Investigate malware hidden in boot records, UEFI firmware, or the operating system’s core. The skill guides evidence collection, boot integrity checks, firmware and memory analysis, and reporting of persistence mechanisms and remediation steps when compromise survives an OS reinstall.
Analyze disk images with Autopsy and The Sleuth Kit to recover deleted files, search content, and examine recorded activity. Build investigation timelines and visual reports that help stakeholders understand evidence from one or multiple disk images.
Assess exposure of Windows secrets protected by DPAPI, the operating system’s data protection service, during authorized security tests. Guide examination and decryption of saved credentials and browser data using available user sessions, credentials, or backup keys.
Analyze access logs from AWS API Gateway, Kong, and Nginx with pandas, a Python data analysis library. Examine resource access patterns, authentication failures, and suspicious requests to investigate API abuse and inform detection rules.
Analyze NTFS file records and change journals to investigate deleted files on Windows disks. Recover surviving metadata and content where possible, reconstruct file activity timelines, and compare timestamps for signs of deliberate manipulation.
Examine suspicious Word, Excel, and PowerPoint documents by extracting macros and untangling code designed to hide its purpose. Identify download addresses, execution triggers, and attack steps, then document findings and indicators for detecting related threats.
Use TensorBoard to visualize training loss and accuracy, compare experiments, and inspect model structure. Includes PyTorch and TensorFlow logging examples for examining weight distributions, predictions, and performance bottlenecks during machine learning training.
Estimate the distribution of stockholders' purchase costs for Chinese A-share stocks using price and volume data. A triangular model produces cost concentration metrics, the estimated share below the current price, and visualization charts.
Assess legal risks in contracts and business matters by rating impact and likelihood. Organize risk levels, mitigation options, documentation, and criteria for involving senior legal staff or outside counsel.
Create or improve a company-specific data analysis skill by gathering analysts’ knowledge and examining database structures. Document business terms, metric formulas, table relationships, and common query patterns in reusable reference files.
Review FastGPT pull requests or local branch changes by examining actual code differences. Explain behavior changes and affected areas, identify unrelated changes, and report concrete concerns about code quality, consistency with nearby implementations, and missing test coverage.
Diagnose failing or intermittent Playwright tests by reproducing errors and examining execution traces. Classify the cause, apply a targeted fix, and run the test ten times to check stability, with recommendations to prevent recurrence.
Analyze failed launches, missed targets, or unsuccessful hires through a blameless review. Use five successive why questions to identify root causes, then record concrete changes with owners, deadlines, and ways to verify results.
Examine a plan by imagining it has failed twelve months later. Identify weak assumptions, linked dependencies, and commitments that are hard to reverse, then outline validation steps and criteria for continuing, changing direction, or stopping.
Examine business assumptions behind revenue forecasts, market estimates, or hiring plans. Identify counter-evidence, model worse outcomes, assess how changes affect results, and propose validation steps, backup plans, and early warning indicators.
Work through founder decisions with 13 executive-role agents and 21 slash commands. Use focused questions or multi-role discussions to clarify tradeoffs, record decisions, and turn the outcome into a 90-day action plan.
Review an executed business decision against its original success and stopping criteria. Compare actual results, revisit assumptions and dissenting views, and create a retrospective record with lessons and follow-up actions.
Review board memos and strategy briefs with available Claude, Codex, and Gemini models. Compare concerns, supporting arguments, and votes, then turn disagreements into questions to resolve before committing to a major business decision.
Review agent-written code changes before merge, focusing on concrete correctness defects. Uses independent subagent reviews, targeted verification, and fresh checks after substantial repairs, with a deeper evidence-based process for security, concurrency, persistence, or data-loss risks.
Create a Business Model Canvas, a nine-part overview of how a business creates value and earns revenue. Connect customers, offerings, channels, operations, costs, and income to examine the business model and identify assumptions and risks.
Identify untested assumptions behind a new product idea across eight areas, including customer value, usability, business viability, technology, ethics, market launch, strategy, and team. Rate confidence in each assumption and suggest a test, producing a Markdown analysis.