zaffnet

deep-pr-review

Multi-model code review: one independent reviewer per model you can reach (OpenAI, Anthropic, Google, ...), findings merged by agreement. Reviews a GitHub PR URL and posts inline comments after per-comment confirmation, or, with no PR, reviews the current branch or working tree and writes deep-review.local.md. Use only when the user asks for a deep or multi-model review or runs /deep-pr-review.

deep-claude-code-review

Claude-only variant of deep-pr-review: several independent Claude Code subagents review the same change at the highest effort available, findings merged by agreement. Reviews a GitHub PR URL and posts inline comments after per-comment confirmation, or, with no PR, reviews the current branch or working tree and writes deep-review.local.md. Use only when the user asks for a Claude-only deep review or runs /deep-claude-code-review.

fix-design-implementation-discrepancies

Use only when the user invokes `/fix-design-implementation-discrepancies <PR number or link>`. Reviews a PR against the living design and schema docs, asks how each discrepancy should be resolved, then makes the chosen minimal fixes.

address-pr-comments-sequential

Address unresolved GitHub PR review comments one at a time.

teach-me

Teach a concept or topic the user wants to learn, one bite at a time.

AI & Automation Listed

writing-whip

Kill all AI writing tropes and behaviours at the source: generation. Focus on quelling behaviour-driven triggers. Load before writing, especially for anything longer than a paragraph and re-check output against it, extremely important for communications, documentation, outbound, client-facing copy and for your own replies to the user.

prose-honesty

Judge every sentence a coding agent writes that is not language syntax -- comments, docstrings, READMEs, design docs, ADRs, PR and commit bodies -- against one bar: does a reader who arrives next year, having never seen this change, need it? Load before writing or editing any such text, and re-check the output against it before handing back.

Data & Documents Listed

simplify-english

Simplify Markdown to plain English.

fastapi

FastAPI best practices and conventions. Use when working with FastAPI APIs and Pydantic models for them. Keeps FastAPI code clean and up to date with the latest features and patterns, updated with new versions. Write new code or refactor and update old code.

AI & Automation Listed

sqlmodel

Use when writing or reviewing Python code with SQLModel, especially models, sessions, queries, FastAPI integration, relationships, link models, creates, updates, and deletes.

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always