Agent Skills by Dammian Miller
Showing 18 vetted skills indexed across 1 GitHub repositories.
DammianMillernear-miss
Isolate and fix individual failing tests while preventing regressions in passing suites.
DammianMillergit-forensics
Recover lost commits and repair corrupted Git repositories via reflog analysis.
DammianMillerservice-config
Configure and test services in dependency order with smoke testing.
DammianMillerunreal-engine-developer
Control Unreal Engine 5 editor via MCP, Python, Blueprints, and C++.
DammianMilleradversarial
Enumerate and test attack vectors to bypass security controls.
DammianMillertypescript-node-expert
Enforce strict TypeScript configurations and modern Node.js development patterns.
DammianMillerballs-mode
Decompose complex problems into scored sub-questions and synthesize a final confidence-rated answer.
DammianMillerchess-engine
Analyze chess positions and determine optimal moves with Stockfish.
DammianMillerpolyglot
Construct polyglot programs valid in multiple languages using comment syntax.
DammianMillercompression
Compress data and create encoders/decoders for specific formats.
DammianMillerbatch-review
Submit non-urgent tasks to the Anthropic Batch API for cost-effective analysis.
DammianMillercodebase-navigator
Query codebase symbols, dependencies, call graphs, and git history via roam-code.
DammianMillerterminal-bench-strategies
Provides strategies and patterns for completing tasks in Terminal-Bench 2.0.
DammianMillercli-design-expert
Provides expert UX guidance for designing CLIs and TUIs with help systems and error messages.
DammianMillerterminal-bench
Classify Terminal-Bench 2.0 tasks and apply domain-specific strategies.
DammianMillermemory-management
Manage a 4-layer memory system using SQLite and Qdrant for AI coding agents.
DammianMillerworktree-workflow
Manage Git worktrees to isolate multi-file changes and automate feature branches.
DammianMillernear-miss-iteration
Fix failing tests one at a time while preserving passing code.