matthewdeaves

Diagnose, fix, and advise on Rockport infrastructure issues. ALWAYS USE THIS SKILL when the user asks anything about Rockport infrastructure — including casual questions like 'is it ok', 'is it up', 'is it working', 'check the infra', 'how's rockport', 'did…

Detect drift between pentest suite and codebase. Use when the user says 'align pentests', 'check pentest coverage', 'pentest drift', or 'pentest sync'.

Review and triage pentest scan results. Use when the user says 'review pentest', 'check scan results', 'what failed', 'pentest findings', or 'triage results'.

Run security scans against Rockport deployment. Use when the user says 'pentest', 'security scan', 'check for vulns', 'test WAF', 'security audit', 'run pentest', or 'scan rockport'.

Deep factcheck of project documentation (README.md, CLAUDE.md, SVG diagrams, skill definitions) against the actual codebase. Finds inaccuracies, stale references, missing information, and bloat. Use after making code changes, when docs may be stale, or when…

Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning…

Use before sending any message containing a file, a line number, a count, a severity, a commit hash, or a statement that X does Y. Also use before retracting one.

Use when about to write "that is the user's call", "waiting on them", or "I'll ask" -- and when a session asks you to choose between options.

Use when porting, compiling, benchmarking, or debugging vintage Mac OS X (10.3 Panther through 10.5 Leopard) games across PowerPC (G3, G4, G5), Intel (Lion), and Apple Silicon. Covers endianness, AltiVec SIMD, Mach-O fat binaries, and legacy OpenGL.

Find and apply the next fps or graphics-quality win for the old-Mac Quake II (yquake2) port across the shared bench fleet (G3/Rage128, G4/GeForce2·Radeon9000·9200, Intel-Lion/GMA950, G5/Radeon9600). Re-runnable, each run profiles one target machine class,…

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism,…

Check if your implementation plan will succeed with Claude Code. Evaluates whether phases fit context windows and follow iterative patterns for session-based development.

Smart git commits with security checks, .gitignore validation, and intelligent commit messages. Analyzes your changes, catches potential secrets, generates conventional commit messages, and provides QA-aware formatting when issue tracking documents are…

Create structured QA round documents for manual testing phases. Generates tracking docs with issue logging, session planning, and verification workflows.

Align pentest suite with current codebase. Use when: 'align pentests', 'sync pentest config', 'check coverage', 'pentest drift', 'update pentest config'.

Review pentest scan results and classify findings. Use when: 'review pentest', 'check scan results', 'what failed', 'any vulns found', 'pentest report'.

Run security tests against the live target. Use when: 'pentest', 'security scan', 'check for vulns', 'run headers', 'is the vuln fixed', 'security audit', 'install pentest-kit'.

Build, deploy, and benchmark QuakeSpasm on the bench fleet (yosemite, yosemite-tiger, sawtooth, quicksilver, mini-g4, imac-g5, mini-intel, imac-2019) from the orchestration Mac via a claimed Intel Lion cross-build mini. Use this skill any time the user asks…

Find and apply the next fps or graphics-quality win for the old-Mac QuakeSpasm (Quake 1) port across the shared bench fleet (G3/Rage128, G4/GeForce2·Radeon9000·9200, Intel-Lion/GMA950, G5/Radeon9600). Re-runnable, each run profiles one target machine class,…

Find and apply the next fps or graphics-quality win for the old-Mac ioquake3 port across the shared bench fleet (G3/Rage128, G4/GeForce2·Radeon9000·9200, Intel-Lion/GMA950, G5/Radeon9600). Re-runnable - each run profiles one target machine class, forms ONE…

Full automated QA audit using Playwright MCP. Walks through every user journey — creating profiles, searching, importing, cooking, organizing — testing every button, modal, and popup. Supports testing with or without AI features. Documents bugs, then fixes…

Fact-check and update ARCHITECTURE.md against the actual codebase. Reads source files, counts lines and functions, compares against the existing diagrams, and fixes any drift. Only changes what's wrong — does not regenerate from scratch.