Every skill in this repository in one plugin: hardware-lab, agent-workflow and dev-tools combined. driver-porting lives in the driver-lab repository and is installed on its own. Install either this or the themed plugins, not both.
Plugin everything from marketplace curtisg-skills in curtisgalloway/public-skills. Commands read from the repo's manifest — 8 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
python3 "${CLAUDE_PLUGIN_ROOT}/plugins/agent-workflow/skills/consult/scripts/runner_guard.py"
python3 "${CLAUDE_PLUGIN_ROOT}/plugins/agent-workflow/skills/orchestrate-milestones/scripts/implementer_guard.py"
Working with a coding agent over time: session learning and teaching summaries, handoffs, transcript access, loop safety (intern-mode), design partnership, harness-agnostic skill authoring, and Google Docs review rounds.
17 skills · hooks
Bench and USB-analysis skills: Cynthion setup, capture, pcap decode and protocol reverse-engineering, USB device profiles, the MCCI 3411 test device, Bus Pirate, Siglent oscilloscope control, OWON electronic load queries, and FNIRSI DPS-150 supply control.
10 skills
Engineering utilities: Jujutsu (jj) in place of git, evidence-based dependency scoring (dep-quality), conventions for CLIs that agents drive (cli-conventions), a seven-arm adversarial code review with a referee (review-swarm), and a release train that installs and smoke-tests every distribution channel before tagging (release-train).
5 skills
Driver porting and review: peripheral specs whose every fact cites the line it came from, reference reviews of a driver against another implementation, a hardware investigator that answers a question as anchored facts from sources a spec repository's license accepts, board specs with the board-expert reader and a scaffold for new ones, a spec verifier, and campaign review. The clean-room skills are a separate plugin in curtisgalloway/cleanroom-skills. Lives in curtisgalloway/driver-lab; this entry points there.
Statically analyze a local JS/Electron app you're authorized to study, with file+line evidence, and build an original reimplementation of what you find. Experimental. Phase 1: JS/Electron static analysis. Phase 2: native ELF/PE/Mach-O container inspection. Phase 3: .NET assembly metadata. Phase 4: EVM bytecode inventory. Phase 5: CUDA fatbin, cubin and PTX inventory. Parses, never executes. Dynamic analysis is a future phase, not yet implemented.
1 skill · 1 command · 1 agent
Reverse-engineer any codebase into a complete PRD. Frontend (React, Vue, Angular, Next.js), backend (NestJS, Django, Express, FastAPI), and fullstack. 2 Python scripts (codebase_analyzer, prd_scaffolder), 2 reference guides, /code-to-prd slash command.
1 skill
Network observability skills powered by Kubeshark MCP — root cause analysis, KFL traffic filtering, snapshot forensics, PCAP extraction.
4 skills · 1 MCP server
Mod almost any game you own with an AI agent: engine recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos, and a shared knowledge base of how games were modded.
13 skills · 3 agents · 1 MCP server · hooks
Decompile Android APK/JAR/AAR with jadx, trace call flows through libraries, and document extracted APIs.
1 skill · 1 command
Operate a real iPhone from Claude Code through a local MCP server in the Zeptap Mac app. Claude sees the screen over USB and taps and types over Bluetooth, with nothing installed on the phone. Tools include screenshot, find_text, tap, tap_text, type_text, open_app and unlock. The Mac app is closed source and paid (macOS 14+), with the first hour free.
1 skill · 1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.