Matt Sims
Community@mbwsims · Oakland, CA
Founder at Better Engines. Previously: Applied AI at Spotter, Machine Learning at Sudowrite, Visiting Scientist at Netflix, and Postdoc at UC Berkeley.
Agent Skills by Matt Sims
Showing 20 vetted skills indexed across 1 GitHub repositories.
mbwsimsforecast
Analyzes git history to forecast file growth trends and risks.
mbwsimsdissect
Trace git history to identify when and why file or function complexity was introduced.
mbwsimsrecap
Summarize git repository activity into a structured JSON recap file.
mbwsimsthreat-model
Generate STRIDE-based threat models for software features and modules.
mbwsimsorbit
Audit codebases for security, tests, code quality, evolution, and instruction violations.
mbwsimsdiscover
Detect hidden code conventions and generate evidence-backed rule suggestions.
mbwsimsexplain
Generate context-aware code explanations from file content and git history.
mbwsimstrace
Traces feature execution paths with file-and-line step-by-step flows.
mbwsimstest
Generate unit and integration tests with deep assertions across JavaScript, Python, and Go.
mbwsimstest-review
Review JavaScript/TypeScript test files and produce a graded quality scorecard.
mbwsimscheck-rules
Check rule compliance in codebases and Claude sessions using CLAUDE.md files.
mbwsimshotspots
Identify high-risk files in a codebase using churn, complexity, and coupling.
mbwsimsrewind
Annotate file evolution from git history with change classifications.
mbwsimsscan
Scan codebases for security vulnerabilities and exposed secrets.
mbwsimsdrift
Detect architectural drift in code modules using git history and metrics.
mbwsimslint-rules
Detect vague language, conflicts, and redundancies in instruction files.
mbwsimsmap
Generate an architectural overview of codebase layers and dependencies.
mbwsimstest-plan
Generate structured test plans for code without writing test code.
mbwsimsimpact
Analyze direct and transitive dependents of a source file across a codebase.
mbwsimssecurity-review
Trace untrusted data flows to identify exploitable security weaknesses in code.