Fast single-pass spec-and-execute loop that mirrors Kiro 0.12's Quick Plan Mode. Generates requirements, design, and task list in one pass (no approval gates), then executes tasks in parallel where dependencies allow. Use when you want spec-driven rigor without the three-gate approval workflow — spikes, small features, or well-understood tasks where speed beats review overhead.
Auto-detects the current project's technology stack and hot-loads context-appropriate skills at session start using Claude Code's SessionStart hook with reloadSkills: true. Detects Node.js/TypeScript, Next.js, Python, Rust, Go, Ruby, and monorepo layouts. Emits a .claude/dynamic-context.md with the detected stack and recommended skill list, then signals Claude Code to reload skills before the first agent turn.
Migrate Gemini CLI workflows to a new AI coding tool (Claude Code, Antigravity CLI, or Codex CLI). Scans shell config, scripts, and CI pipelines for gemini calls, maps each to an equivalent command in the target tool, rewrites config files, and validates the migration. Use when Gemini CLI free-tier access ends June 18 2026 or when switching AI coding CLIs.
Spec-driven development agent for AWS Kiro. Captures feature requirements, generates EARS-notation specifications, produces architectural designs, sequences implementation tasks, and validates the final code against the spec checklist. Use when you want rigorous, maintainable feature builds instead of vibe-coded prototypes.
Scaffold, configure, and deploy custom AI agents with the Google Antigravity 2.0 SDK and agy CLI. Handles auth, AGENTS.md setup, skill installation, MCP server connections, parallel subagent workflows, and Managed Agents API calls. Use when the user wants to build or extend agents on the Antigravity 2.0 platform launched at Google I/O 2026.
Track brand mentions, URL citations, and share-of-voice across the 2026 AI search surface — ChatGPT (with browsing), Perplexity, Claude (with search), Google Gemini, Google AI Overviews, Bing Copilot, You.com, Phind, and Microsoft Copilot. Polls a configurable query set per engine on a schedule; logs whether your brand was mentioned, whether your URL was cited, who your competitors were, and how all of that moved week over week. Outputs share-of-voice dashboards, weekly delta reports, competitor matrices, and citation-gap analysis (queries where you SHOULD be cited but aren't). Closes the single biggest gap in legacy SEO platforms — Visibly AI / Semrush / Ahrefs / Moz / Conductor all under-cover this surface in 2026, even though AI Overviews now answer 30%+ of informational queries with zero clicks. TRIGGER on "AI citation tracking", "share of voice AI", "ChatGPT citations", "Perplexity citations", "AI Overview tracking", "brand mentions in AI", "LLM visibility", "GEO tracking", "AEO measurement", "AI search
Detect content cannibalization on a site — multiple URLs ranking (or impressing) for the same query, splitting click-through, diluting authority, and confusing Google about which URL is canonical for the intent. Pulls GSC query × page data, identifies cannibalized clusters (≥ 2 pages with ≥ 50 impressions for the same query within position 1-50), classifies the underlying issue (true duplicate / intent overlap / template confusion / accidental same H1 / variant page leakage), and recommends one of five resolutions: consolidate-and-301, canonicalize, differentiate-intent, noindex-the-weaker, or update-internal-links-to-disambiguate. Generates the actual redirect rules, canonical tags, content briefs for differentiation, and a recovery model showing expected click consolidation. TRIGGER on "cannibalization", "content cannibalization", "keyword cannibalization", "ranking conflicts", "multiple pages for same query", "consolidate content", "GSC cannibalization".
Pull and analyze Google Search Console data via the GSC API. Produces: weekly query × page performance with WoW/MoM/YoY deltas, top movers report (winners + losers ranked by absolute click change), click-loss attribution (lost rank? lost impressions? lost CTR?), query-page mismatch detection (page ranking for the wrong query), branded-vs-nonbranded split, position-bucket analysis (top 3, 4-10, 11-20, 21+), country / device / search-type segmentation, and the URL Inspection findings for sample URLs (indexed? canonical correct? mobile-friendly? Core Web Vitals?). All output is YOUR data in YOUR DB — no vendor lock-in. Matches the GSC integration that Visibly AI / Semrush / Ahrefs gate behind monthly subscriptions. TRIGGER on "GSC", "Google Search Console", "Search Console API", "rank tracking", "SEO position changes", "click loss", "impression loss", "top movers", "indexing report", "query analysis".