dcramer

Designs, reviews, and iterates on LLM agents and agent-like workflows. Use when asked to "design an agent", "review this agent", "improve our system prompt", "optimize prompts for caching", "improve tool calling", "reduce hallucinated tool calls", "add structured outputs", "decide if this should be multi-agent", "reduce false positives", "tune agent thresholds", or "build evals for this agent". Covers architecture choice, cache-friendly prompt templates, tool and schema design, runtime loops, trust boundaries, and eval-driven iteration.

ALWAYS use this skill when creating pull requests — never create a PR directly without it. Follows Sentry conventions for PR titles, descriptions, and issue references. Trigger on any create PR, open PR, submit PR, make PR, push and create PR, or prepare changes for review task.

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Manage tasks via dex CLI. Use when breaking down complex work, tracking implementation items, or persisting context across sessions.

Create dex task from markdown planning documents (plans, specs, design docs, roadmaps)

Manage Gmail and Google Calendar with capability-backed auth and operations. Use when asked to check inbox, summarize emails, give a day at a glance, send an email, review calendar events, or schedule meetings.

Use when reviewing codebase health, finding structural issues, or auditing architecture quality before major changes

Guide for writing tests. Use when adding new functionality, fixing bugs, or when tests are needed. Emphasizes integration tests, real-world fixtures, and regression coverage.