Drives the vscode-inspector MCP against a live VS Code + GitLens instance and returns raw evidence (probe values, console/log excerpts, geometry, measurements) as text. Default executor for live-inspection driving so the Opus orchestrator only reasons over distilled results. Returns evidence; does NOT judge, fix, or…
Use to audit a component, file, or directory for WCAG 2.1 AA accessibility compliance. Detects ARIA anti-patterns, missing semantics, keyboard gaps, and color-only information. Safety-first — refuses to emit fixes that would create a new accessibility bug. Scope is always explicit; do not use for page-level flow or…
Use to audit a page, view, or composed flow for WCAG 2.1 AA compliance at the composition level - landmarks, heading hierarchy, tab order across components, focus handoff on modal open/close, live-region conflicts. Scope is page/view, NOT component internals. Safety-first - refuses to emit fixes that would create a…
Use to produce a leader-facing remediation proposal from one or more /a11y-audit outputs plus team and product context. Translates audit findings into sprint plans, staffing asks, customer-facing language, compliance rollups, and critical-path analysis. Refuses to fabricate numbers, owners, or commitments beyond the…
Use when reviewing or stress-testing a proposed technical approach, implementation plan, or architecture decision. Triggers when asked to review a plan, play devil's advocate, poke holes, or validate an approach before implementation begins.
Consolidate a feature branch's commits into the minimum number of valuable commits with no add-then-undo churn, verifying the final tree is byte-identical. Use whenever the user asks to clean up, consolidate, squash, restructure, or curate a branch's commits, wants "reviewable commits" before landing or opening a PR…
Use when formulating the best technical approach for a task — before writing implementation plans or code. Triggers on architecture decisions, complex features, refactors, or when the user asks how to approach something. Investigates current codebase, questions existing patterns, researches alternatives, and presents…
Use to gate a change set before merge — delegates bug-hunting to the built-in code-review skill, then layers goals.md alignment, cross-platform/consumer completeness, and validation-gap analysis into a merge verdict. For standards/checklist compliance use /review.
Scope a unit of work into a goals document — defines what and why, not how. Bridge between triage output and dev planning. Produces .work/dev/{identifier}/goals.md for /deep-planning to consume.
Use whenever any UI-bearing work touches a running instance — building or fixing a feature, ship-gating, auditing, OR debugging visible bugs (flaky behavior, intermittent rendering, "sometimes does X" reports, hover/focus/animation glitches, layout overflow). Adaptive depth from tactical fix-loop to ship-gate audit.…
Use for one-off / single-question inspection of the running GitLens extension — examining UI state, reading logs, checking feature flags, dispatching a command, or asking "what does the live DOM look like right now". Reference for vscode-inspector MCP primitives. For iterative debug-and-fix loops on UI bugs (sweep →…