spec-review

Creates and optimizes Claude Code skills following Anthropic's official best practices with emphasis on agent parallelization and script-first determinism

Two-phase convergence harness for high-assurance review of a changeset (PR or working-tree diff). Phase 1 loops iterative multi-reviewer fix->re-review until a round finds zero actionable issues; Phase 2 runs a Gemini-primary adversarial cross-examination (Gemini finds -> Claude judges -> Gemini counters), fixing every confirmed finding. Soft-depends on pr-review-toolkit and adversarial-review plugins with documented fallbacks.

Creates and customizes Claude Code statusline scripts from composable items

Color-coded context window usage bar for Claude Code statusline and /context-bar command

Creates polished, narrated product demo videos using Remotion with AI-crafted storytelling, real app screenshots, animated phone mockups, brand-aligned styling, TTS voiceover, and background music.

Plugin-first publishing for Claude Code skills. Auto-assembles and syncs plugins from plugin-manifest.json files. Also supports bare skills and individual repos

Prevents context window overflow by delegating token-heavy reads to isolated sub-agents that return distilled summaries. Auto-detects when ralph-loop is needed. Covers: documentation sites, code audits, dependency research, large PR reviews, competitive analysis, security advisories.

4-tier adaptive statusline with icons for folder, git branch, and context usage

Persistent brain for Claude Code sessions using Obsidian. Auto-logs sessions, captures curated insights, enables project-scoped context resume, and provides fast cross-project search via tags and metadata.

Interactive Figma UI design skill with brainstorming, progress tracking, and design-to-code bridging via Figma MCP