Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code".
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
Draft public COVE documentation for user-facing feature branches by comparing against dev, fetching relevant live public docs pages, and producing a concise copy-paste markdown draft in .public-docs.
Read a React Doctor review file, let the user choose a rule type to work on, then apply fixes sequentially with confirmation at each step. Use this skill whenever the user wants to fix React Doctor issues, work through a review file, or asks to resolve a specific rule type or section of react doctor output.
Run React Doctor against a path and write a single markdown checklist grouped by rule type. Use this skill whenever the user wants to scan and review React issues, run react doctor, or get a prioritized list of React problems ready for fixing.
Resolve yarn audit --groups dependencies findings in Yarn workspaces, especially when dependency versions drift across packages or a transitive vulnerability requires a targeted upgrade or resolutions entry. Use when Codex needs to investigate or fix dependency audit issues and should use syncpack when version…
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
★not rated 55 todayA
tokens not measured
originalApache-2.0
Analyze or improve CDC Open Viz algorithms for correctness, edge cases, complexity, and maintainability; use for requests about algorithm improvements, optimization, data-flow hardening, or choosing small/medium/large algorithmic fixes.
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: