157 skills · sorted by relevance
Explore concepts learned by language models using sparse autoencoders, which separate internal activity into a small set of features. Analyze pretrained models, train custom autoencoders, assess reconstruction quality, and experiment with feature based output adjustments.
Work on advanced RuView sensing with signals from multiple WiFi nodes. Explore position estimation, three-dimensional occupancy reconstruction, changes in movement patterns over time, and defenses against suspicious signals, with guidance on implementation modules and validation.
Investigate a GitHub project through repository data and web sources, then produce a Markdown report covering its development history, technical structure, activity metrics, and alternatives, with citations and diagrams where useful.
Rebuild slide images, screenshots, scanned PDFs, or image-only presentations as editable PowerPoint files. Reconstruct text and simple shapes as separate objects, retain complex visuals as image assets where needed, and check rendered slides against their sources.
Reconstruct how an AI coding agent produced a feature, pull request, or report using local ax records. Connect sessions, commits, skills, and tool activity into an evidence-based sequence with key decisions, checks, and a repeatable recipe.
Analyze a custom protocol in a CTF sandbox and reproduce an accepted exchange. Recover message boundaries, checksums, and session state, then build a small replay program that preserves the required message order.
Analyze packet captures in a CTF sandbox by rebuilding communication sessions and decoding message contents. Recover transferred files and connect packet order, timing, and reconstructed streams to observed host or malware behavior.
Build an evidence-backed incident timeline in a CTF sandbox by correlating logs, network captures, and other artifacts. Trace attacker actions across sources, distinguish confirmed events from inferred gaps, and preserve the sequence that supports the conclusion.
Trace uploaded files through extraction, conversion, parsing, and reconstruction of saved objects in a CTF sandbox, an isolated competition environment. Preserve original and derived files, distinguish visible validation from backend behavior, and document the smallest reproducible processing chain.
Investigate memory dumps, disk records, and captured network traffic while preserving evidence. The skill guides timeline reconstruction and examination of system traces to identify suspicious activity and produce findings that others can review.
Create a structured review after a production incident, focusing on systems and processes without blaming individuals. Reconstruct events, quantify impact, investigate causes, and document specific follow-up actions with named owners and deadlines.
Check training data and machine learning models for malicious changes, including backdoors that cause unexpected behavior on specific inputs. Combine data quality checks, model analysis, and file integrity verification, then document findings and retest after remediation.
Build a shared incident timeline in Timesketch from endpoint, server, and cloud logs. Search events, add tags and investigator notes, reconstruct the attack sequence, and organize findings into a story for incident reporting.
Investigate security incidents in Splunk by connecting authentication, endpoint, and network logs. Use SPL, Splunk’s search language, to identify suspicious activity, reconstruct event timelines, document findings, and develop detection rules.
Analyze Windows Amcache records to investigate applications, deleted executable traces, and drivers. Extract file details, compare SHA-1 hashes with malware databases, and combine records into a timeline to support incident investigations.
Investigate Linux intrusions using auditd records. Configure audit rules, search events with ausearch, summarize activity with aureport, reconstruct a timeline of suspicious actions, and forward logs to a central security monitoring system.
Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.
Organize responses to service outages and degraded performance, from initial assessment through recovery review. Classify severity, reconstruct event timelines, draft stakeholder updates, and create response guides and follow-up actions based on incident findings.
Build and test threat detection rules in Google SecOps using YARA-L 2.0, its rule language. The skill also checks existing coverage with simulated attack events, proposes rules for confirmed gaps, and deploys approved rules.
Build a Three.js 3D model from an object or character reference image using code. The workflow develops shapes and materials in stages, compares rendered views with the reference, and guides corrections through quality checks.
Assess LoRaWAN and sub-GHz wireless devices by capturing signals, examining packet formats, and checking key reuse and replay weaknesses, where recorded messages are resent. It covers IoT networks, fixed-code remotes, and proprietary radio protocols.
Assess GraphQL APIs during penetration tests, from finding endpoints and mapping data structures to checking access controls, query limits, subscriptions, and uploads. Includes example queries, guidance for testing tools, and defensive controls for interpreting findings.
Plan authorized security tests involving phone calls, text messages, physical access, and USB devices. Helps develop scenarios from public information, document interactions, and assess how staff verification procedures and physical controls respond.
Investigate exposed source maps, configuration files, Git history, and API specifications on websites. The skill guides source reconstruction and artifact inspection to identify leaked secrets, internal routes, and build details during the initial stages of security research.