claude-skills

Audit agents spawned in the current/last run against the agent-selection taxonomy

Run the Agent Diversity Review gate and emit the result table

Meta-analyze the effectiveness of a /loop arc — per-iteration metrics, LOC delta trend, saturation detection, and a keep/lengthen/delete recommendation.

Audit the rules/ directory for missing foundational principles; output gap list with priority and justification

Validate ~/.claude/settings.json hooks block — event names, file existence, executability, matcher syntax; --fix repairs common issues

Dedicated axe-core + Playwright accessibility agent. Navigates pages, runs WCAG 2.2 AA audits at 6 breakpoints, reports violations with fix suggestions, verifies remediation.

Pre-implementation architecture agent. Analyzes project structure, generates repo-map, designs task graph, identifies architectural seams and parallel workstreams.

Auto-generates changelogs from conventional commits. Parses git log since last tag, groups by type, writes user-outcome-focused CHANGELOG.md entries.

Simplifies code for clarity, consistency, and maintainability. Reduces complexity, flattens nesting, removes dead code, consolidates duplicates. Focuses on recently modified files.

Post-implementation verification agent. Runs Feature Completeness Engine, Zero Recommendations Gate, and visual verification. Only declares DONE when genuinely complete.

Deep web research, competitor scanning, technology evaluation, and implementation planning. Decomposes work into vertical slices, identifies parallel workstreams, tracks assumptions with confidence levels, and designs the critical path for minimum wall-clock time.

Captures and evolves user preferences with confidence levels. Maintains Voice of the Customer model with exact language, dissatisfaction and aspiration signals. Handles promotion/demotion, global vs project scoping, auto memory system, and Omi wearable data integration.

Meaning-first animation with 3-tier hierarchy. CSS scroll-driven (animation-timeline: scroll()), View Transitions API, @starting-style DOM-insert, container scroll-state queries, prefers-reduced-motion mandatory on all animations.

Establish project thesis before first code. Infer product type from domain/folder/README. Identify users, business model, pSEO strategy, AI-native dev approach. Maintain PROJECT_BRIEF.md as source of truth.

Supreme policy layer governing all Claude Code behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.

Sharp, punchy, anti-slop output. 2-sentence text responses, 100-160 char descriptions, 4-8 word headlines. Brian's personal voice — no preamble, no hedging, no AI slop.