Search: "assisted"

Plans and audits use of ChicagoHAI HypoGeniC/HypoRefine for LLM-assisted hypothesis generation from labeled text datasets. Use for the `hypogenic` package, its task configs, hypothesis banks, or HypoBench datasets—not for manual hypothesis formulation or scientific validation.

Performs graph-assisted triage of a single security finding, SARIF result, weAudit annotation, suspicious function, or report excerpt using Trailmark reachability, entrypoint paths, taint, privilege-boundary, blast-radius, caller/callee, and neighborhood evidence. Use when deciding whether one candidate issue is reachable, prioritizing a finding before PoC work, preparing evidence for exploit validation, or checking whether a static-analysis result is actionable.

Analyzes Neuropixels extracellular recordings end-to-end with SpikeInterface. Covers loading SpikeGLX/Open Ephys/NWB data, preprocessing, drift/motion correction, Kilosort4 (and CPU) spike sorting, quality metrics, and unit curation (threshold-based, model-based UnitRefine, and AI-assisted visual review). Use when working with Neuropixels 1.0/2.0 recordings, spike sorting, or extracellular electrophysiology analysis.

A universal CLI toolkit for serious AI-assisted development. Works across Cursor, Claude Code, Antigravity, Codex, and more.

An AI-assisted workflow for managing Unreal Engine UMG assets. This plugin uses JSON as the source of truth, enabling robust version control (Git), programmatic UI manipulation, and automation for UMG development.

A user-friendly chat-based LLM assisted security research, pen test, and training suite. all-in-one.

Use this skill when an agency operator wants to work through a brand's pending Awin publisher applications and approve or decline them in one assisted batch. The pending queue is read from the Awin API; the approve or decline click is carried out in the operator's own authenticated Awin session through Claude-in-Chrome, because Awin exposes no public approve/decline endpoint. Decisions follow the brand's recorded strategy only, and the whole batch runs against a single explicit human confirmation. Trigger on: "approve pending Awin publishers for Acme", "work through Acme's Awin application queue", "auto-approve Awin applicants for [brand]", "clear the Awin pending publishers for Acme".

A portable evidence record for AI-assisted work.

An AI-assisted development method combining Iterative Context Management with [RIPER-5](https://forum.cursor.com/t/i-created-an-amazing-mode-called-riper-5-mode-fixes-claude-3-7-drastically/65516) rules (Research, Innovate, Plan, Execute, Review) to produce better-quality code that meets requirements.

Reusable Cursor rules, prompts, and workflows for AI-assisted development as used at Jung von Matt TECH.