Skill UI

This skill facilitates cross-version symbol migration and binary diffing. When existing symbols or reverse engineering results from an old version need to be quickly mapped to a new binary version, this tool is used. It leverages LLMs to perform structured structural comparisons between corresponding functions in different versions, enabling the programmatic transfer of function names and offsets even when original PDB files are lost. Ideal for kernel debugging, application updates, and binary analysis.

This tool provides a unified interface to run test suites for various programming stacks (Python, Node.js, Rust) within a CI/CD pipeline. It automatically detects the project's environment (by checking lock files or config) and executes the appropriate testing framework (e.g., pytest, vitest, cargo test), ensuring consistent code quality checks regardless of the underlying language. Ideal for pre-commit or CI/CD integration.

This stub file is automatically generated by tooling (e.g., missing import scanners). It serves as a placeholder where actual functional code should be implemented. It does not contain active logic and requires manual development.

This specialized skill traces the complete lifecycle of an uploaded or imported file through complex backend systems. It maps the sequence from ingress to final consumer, tracking every derived artifact, archive extraction, format conversion, parser invocation, and deserialization step. It is crucial for security analysis, vulnerability research, and understanding how a file reaches a decisive backend effect after initial sandbox assumptions are made.

This specialized skill is designed for Digital Forensics and Incident Response (DFIR) scenarios. It correlates evidence from multiple disparate sources—including EVTX, PCAP, registry, memory, and filesystem artifacts—to build a comprehensive, ordered, and replayable forensic timeline. Use it when the goal is to map the full sequence of attacker actions, establishing initial access, lateral movement, and persistence chains based on cross-source evidence correlation.

This skill is designed for deep forensic analysis of asynchronous processing chains, specifically focusing on 'drift'—behavioral or configuration differences between a synchronous request path and subsequent worker-executed tasks. Use it to trace payloads, inspect worker-only state, follow retry mechanisms, handle dead-letter queues, or connect enqueued items to eventual side effects (e.g., file writes, cache updates, emails). It is a specialized downstream tool, requiring prior orchestration context.

This specialized skill guides deep-dive analysis for binary-heavy challenges, including CTF, malware analysis, and advanced forensics. It covers reverse engineering binaries, unpacking samples, inspecting memory dumps, debugging crashes, and building exploit chains by correlating artifacts like files, memory, and network packets.

This skill allows users to select and implement various compliance-aligned privacy policies (such as HIPAA Safe Harbor, GDPR pseudonymization, and PIPEDA) for robust de-identification. It manages complex policy profiles, ensuring data is masked, redacted, or pseudonymized according to specific legal requirements, while also supporting custom surrogate generators for advanced research needs.

Orchestrates a robust, multi-stage cyber defense pipeline using specialized AI agents to analyze raw log files (e.g., nginx, auth, syslog). The system ingests logs, detects anomalies, classifies overall risk, and generates a comprehensive, actionable incident report, making it ideal for security investigations and breach analysis.

This tool audits and validates all Claude Code hooks defined across your settings files. It checks for validity, performance safety, correct event scoping, and proper exit-code handling (blocking vs. non-blocking). Essential for initial setup, debugging hooks that fail to fire, or performing routine system hygiene passes to ensure your agent's tool flow is robust and reliable.

An advanced tool designed to audit, validate, and maintain rule files (e.g., .claude/rules/). It checks structural correctness, validates glob patterns against actual project files, and runs an interactive session to confirm or improve the relevance of each rule. Ideal for initial setup, debugging, or periodic rule hygiene.

This skill facilitates the extraction of population-scale (cohort-level) clinical text from Electronic Health Records (EHR) or FHIR data warehouses using the FHIR Bulk Data Access ($export) operation. It manages the asynchronous job kickoff, polling, and downloading of NDJSON files. The resulting data stream is designed to be fed in batches into OpenMed for mandatory de-identification and Named Entity Recognition (NER) analysis.