Menu
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | bisect-regression |
| description | Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it. |
| when_to_use | "it worked last week", a regression, unclear which commit broke it |
| targets | ["*"] |
git bisect start; git bisect bad <bad>; git bisect good <good>.git bisect good/bad.git bisect reset. Report: the commit, the line, the one-sentence cause.
Automate it: git bisect run ./repro.sh if you have a script that exits non-zero on the bug.Search tool for modern web development best practices. MANDATORY: Execute FIRST for all HTML/CSS and clientside JS tasks. Do NOT skip - web APIs evolve rapidly and training weights contain obsolete patterns. Trigger immediately for: - UI/Layout: Modals, dialogs, popovers, Glassmorphism/backdrop-filters, anchor positioning, container queries, `:has()`, `:user-valid`. - Scroll/Motion: View Transitions, Scroll-driven animations, scroll parallax/reveals. - Performance: CWV (LCP, INP), content-visibility, Fetch Priority, image optimization. - System/APIs: Local filesystem access, WebUSB, WebSockets sync, WebAssembly widgets. - Frameworks: Adapting layout/styles in React, Vue, Angular. - General Frontend: Forms, autofill, advanced inputs, custom scrollbars, modern component states, etc. DO NOT trigger for: - Backend: Database SQL, ORMs, Express API routes. - Pipelines: CI/CD deployment, Docker, Actions. - Generic: Local scripts (Python/Go tools), ESLint, Git.
Implements WebMCP (Web Model Context Protocol) on websites using document.modelContext.registerTool. Covers tool design, JSON Schema inputs, security annotations, origin isolation, and Chrome testing. Use when adding WebMCP tools to web apps, exposing page features to browser agents, or when the user mentions WebMCP, modelContext, or agent-ready web tools. Not for server-side MCP servers.
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
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.
Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.