Hunt a diff for correctness bugs and regressions, and report them without editing. Use when reviewing a change before it is finalized, or when asked to find bugs, pressure-test, or hunt regressions. NOT FOR ideas and plans (do-redteam), readability (do-simplify), or feedback already left on a PR…
Generate an ARCHITECTURE.md file for a codebase following matklad's principles. Use when asked to "write an architecture doc", "create ARCHITECTURE.md", "document the architecture", "explain the codebase structure", "write a codemap", or when onboarding contributors to a project. Based on…
Behavioral testing methodology — test what users experience, not how code is structured. Use when writing tests, reviewing test quality, planning test strategy for new features, or when existing tests are brittle/verbose/coupled to implementation details. Triggers: writing tests, TDD, test review, "tests keep…
Physics-based reasoning framework (Musk methodology) that deconstructs a problem to irreducible fundamental truths, classifies every element as hard constraint, soft constraint, or assumption, then reconstructs the optimal solution from fundamentals alone. USE WHEN first principles, fundamental truths, challenge…
Simplify recently changed code for clarity, reuse, quality, and efficiency without changing behavior. Use after writing or modifying code, during a cleanup pass, or when do-work asks for a simplify pass. NOT FOR bugs (do-debug), correctness hunts (do-adversarial-review), over-engineering scores (ponytail-review), or…
End-of-session cleanup pass for Swift code. Use this skill whenever the user asks to "clean up", "polish", "tidy", "refactor", or "review" Swift work at the end of a coding session, or when they invoke this skill by name. Performs a holistic review of files modified during the session — simplification, type-driven…
End-of-session cleanup pass for TypeScript, React, and web code. Use this skill whenever the user asks to "clean up", "polish", "tidy", "refactor", or "review" web/frontend work at the end of a coding session, or when they invoke this skill by name. Performs a holistic review of files modified during the session …
Write high-signal code comments for humans and coding agents. Use when adding inline comments, docstrings, API comments, or local rationale near code. Triggers on: "write better comments", "comment this", "document why", "agent-friendly comments", "explain this code with comments", "docstring".
The 23 Gang of Four object-oriented design patterns (Gamma, Helm, Johnson, Vlissides, 1994) distilled as a practical field guide, not a catalog. Use when naming a shape in code review, choosing between competing designs, deciding whether to introduce indirection, or auditing for over-abstraction. Each pattern…
Build accessible, themeable UI components, and when asked, capture the project's brand into DESIGN.md plus a live style-guide page. Use when building buttons, dialogs, forms, cards, or any reusable UI; also when standing up DESIGN.md, a style guide, or documenting existing tokens. Covers component API design, design…
Patterns for building lightweight, zero-dependency TypeScript tools and libraries. Use when building new CLI tools, libraries, or utilities from scratch. Use when refactoring existing TypeScript projects to remove unnecessary dependencies. Use when writing fetch wrappers, CLI parsers, loggers, config merging, string…
Build native macOS desktop applications in Swift using AppKit and SwiftUI. Use when building or modifying macOS .app bundles, NSDocument-based apps, menu bar apps, preferences windows, NSWindow/NSToolbar/NSSplitView layouts, NSMenu/NSStatusItem, Core Data/SwiftData/GRDB persistence, drag-and-drop, undo/redo…
Teaches agents to write modern CSS using native features instead of legacy hacks, workarounds, and JavaScript. Covers layout, animation, color, typography, selectors, and workflow patterns with 64 old-vs-modern comparisons. The agent should always prefer modern CSS approaches, warn about browser compatibility for…
Prevent unnecessary React useEffect usage by steering code toward derived state, event handlers, memoization, key-based resets, useSyncExternalStore, and framework or query-library data APIs. Use when writing or reviewing React/Next.js components, refactoring effect-heavy code, or when a change introduces useEffect…
Type-driven design principle: transform unstructured data into structured types at system boundaries, making illegal states unrepresentable. Use when writing or reviewing code that validates input, designs data types, defines function signatures, handles errors, or models domain logic. Use when you see validation…
Systematically refactor TypeScript codebases for readability, type safety, and AI-friendliness. Use when asked to "refactor this", "clean up this code", "make this codebase better", "improve code quality", or when inheriting a messy TypeScript project. Covers assessment, prioritization, and safe incremental…
Audits AI instruction sets for over-prompting. Applies six tests to each rule, then classifies it as CUT, RESOLVE, MERGE, EVALUATE, SHARPEN, MOVE, or KEEP. USE WHEN BPE, bitter pill, audit setup, trim instructions, simplify setup, or clean up CLAUDE.md. NOT FOR attacking an idea's logic (use do-redteam).
Routes independent work through the harness's subagent tool: background execution, role briefs, worktree isolation, and coordinator-managed synthesis. USE WHEN parallel execution, agent team, swarm, spawn agents, fan out, divide and conquer, multi-agent, coordinate agents, custom agents.
Recipe diagrams: convert any recipe into a high-resolution Cooking for Engineers-style PNG process-flow table with aligned ingredient streams, preparation branches, joins, temperatures, timings, and finish steps. Use when the user asks for a recipe diagram.
Commit local changes as a Conventional Commit. Use when the user says commit, push, ship, or open a PR, or when a do- hand-off names do-commit with a mode (commit, cp, cpp, land). Never pushes unless the mode or the user asks. NOT FOR sync, conflicts, or undo (do-git-safe-pr-workflow), stacked PRs (do-gh-stack), or…
★not rated 2
changed 8d agoA101 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: