This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
Built for context-aware security review of MCP servers, AI agent skills, coding-agent plugins, and CLI extensions. It compares a repository's stated purpose with actual files, permissions, network calls, env var access, install scripts, and tool definitions, then returns an evidence-backed install-risk brief with severity, confidence, permission map, least-privilege notes, and a practical install decision.
Supabase RLS Security Auditor assesses and audits Supabase apps across RLS, Auth/IAM, data security, APIs, Edge Functions, storage, secrets, third-party integrations, governance, logging, and security operations. Built for founders, vibe-coded apps, SaaS teams, and builders preparing to launch. Returns prioritized findings, exploit paths, safe SQL/architecture fixes, regression tests, and launch-blocker guidance.
A creator growth strategy skill for analyzing public creator accounts, content metrics, benchmark patterns, monetization paths, and platform safety risks across TikTok, YouTube Shorts, Instagram Reels, LinkedIn, X, Threads, Substack, Medium, newsletters, and blogs. It includes local JavaScript tools for CSV/JSON content analysis, policy-risk review, and account scoring.
Compliance auditor for YouTube 2025/2026 policies. Automatically audits any YouTube script, niche research, or video-idea brainstorm for Inauthentic Content, AI Disclosure, Misleadi ng Content, Child Safety, Advertiser-Friendliness, Originality, and AI Slop signals, then appends a 0-10 demonetization risk score with concrete mitigations.
Audits soccer analysis before conclusions are trusted: source tiers, dates and seasons, competition splits, 450-minute sample checks, availability flags, and uncertainty labels.
Review an AI Skill before installation or publication. Get a concrete verdict with evidence, permissions, secret risks, license constraints, and the safest next step.
Verify AI tools, models, GitHub repos, papers and technical claims. Get evidence, feasibility, project-fit analysis, and a ready-to-paste implementation handoff.
I've spent years building production software, designing enterprise architectures, reviewing thousands of code changes, and optimizing AI-assisted development workflows. This Skill packages proven engineering, planning, documentation, testing, and code-review practices into a lightweight workflow that helps AI understand any project before making changes, reducing mistakes, hallucinations, unnecessary token usage, and repeated context loading.