Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.
Use when reviewing ML system design docs, ML/AI project repos, design-doc PRs, RAG/LLM/foundation-model architectures, agentic AI workflows, or production ML readiness. Applies the ML System Design framework by Kravchenko and Babushkin to grade designs, compare docs with code, find critical gaps and low-hanging fruit, and give specific non-cringy praise.
Testing Gloomberb at every level: CLI commands for fast data/integration checks, OpenTUI's built-in test harness for component tests, and tmux for full end-to-end terminal TUI testing. Use this skill when you need to verify terminal TUI features, write OpenTUI regression tests, or smoke-test the terminal app. Do not use it for Electrobun/desktop-web-only visual or window chrome work unless tmux/OpenTUI coverage is explicitly needed.
Verify proofs, check theorem correctness, and solve satisfiability problems using Lean 4, Coq, and Z3 SMT solver. Use when the user asks to prove theorems, verify mathematical proofs, check logical satisfiability, or work with proof assistants.
Review a pull request for correctness, MATLAB/Octave behavior, EEGLAB data-structure consistency, GUI/history regressions, and repository convention compliance in sccn/eeglab.
Demo skill used to verify skill registry `pricing` metadata round-trips end-to-end.
Drive and debug the real keifu TUI autonomously via its remote-control debug server (--debug-listen) — launch headlessly, inject keys/mouse, dump the rendered screen as text, and inspect app state. Use this whenever a change affects TUI behavior, rendering, keybindings, mouse handling, focus, scrolling, or async loading states, when reproducing a user-reported UI bug, or when you need to confirm "does it actually work on screen" — cargo test alone cannot verify what the user sees. Reproduce the issue through this workflow before fixing, and re-verify after.
Effect-TS patterns for Testing. Use when working with testing in Effect-TS applications.
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.