davidanthonyn

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's…

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward…

Systematic peer review toolkit. Evaluate methodology, statistics, design, reproducibility, ethics, figure integrity, reporting standards…

Generate testable hypotheses. Formulate from observations, design experiments, explore competing explanations, develop predictions…

Generate marketing screenshots with Playwright.

Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits.

Creates language variants of existing Semgrep rules.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the…

Optimize for search engine visibility, ranking, and AI citations.

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches…

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels…

Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks…