REvoDesign

Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.

Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.

Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.

Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.

Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.

Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.

Make frontend output look intentional, not AI-generated. Use for any UI work — components, pages, layouts.

Diagnose and fix tests that pass sometimes and fail other times. Use when CI is red intermittently.

Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.

Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.

Design the three states every data UI forgets. Use for any component that fetches or lists data.

Write safe, reversible database migrations for this repo's conventions. Use for any schema change.

Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.

Write a PR description a reviewer can approve fast. Use when opening any pull request.

Enforce REvoDesign Qt/PyMOL conventions. Use when touching Qt imports, threading, UI loading, PyMOL API calls, or i18n strings. Catch the mistakes that cause SIGABRT or silent breakage across Qt5/Qt6.

Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.

Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.

Rosetta/RosettaPy and sidechain-solver conventions for REvoDesign. Use when writing Rosetta tasks, adding sidechain solvers, configuring nodes, or touching the scoring/design pipeline. RosettaPy source: https://github.com/YaoYinYing/RosettaPy.

Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.

Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.

Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.

Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.

Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.

Review SQLite + SQLAlchemy queries in the REvoDesign server for correctness, safety, concurrency, and performance. Stronger and more specific than the generic loopkit sql-review — targets the actual patterns in server/pssm_gremlin/pssm_gremlin.py.

Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.

Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.

REvoDesign UI, config, and workflow conventions. Use when adding UI widgets, config keys, shortcuts, menu items, ValueDialog forms, or running the test suite.

Use when starting any conversation in a loopkit-enabled project — establishes how to find and use loopkit's skills, requiring skill invocation before ANY response including clarifying questions.

Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. Requires running the verification command in THIS turn and reading its output before any success claim.

Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.