Claude Skills by notque

AI sprite generation: portraits, idle loops, animated sheets via Codex/Nano Banana. Per-row generation, animation presets, video-to-sprite, identity lock. Use for generated character art.

CPU-only motion data processing pipeline for game animation: BVH import, contact detection, root decomposition, motion blending, FABRIK IK. No GPU required.

Phaser 3 2D game dev: scenes, physics, tilemaps, sprites, polish.

Audit cron scripts for reliability and safety.

Deterministic API endpoint validation with pass/fail reporting.

Fish shell configuration and PATH management.

Generate headless Claude Code cron jobs with safety.

Kubernetes debugging for pod failures and networking.

Kubernetes security: RBAC, PodSecurity, network policies.

Service health monitoring: Discover, Check, Report in 3 phases.

Safely start, supervise, and terminate shell processes: background jobs, PID capture, signals, traps, cleanup verification.

A/B test agent variants for quality and token cost.

Scaffold vexjoy-agent operator .md files: frontmatter, routing block, operator context, reference loading table, phase/gate workflow.

Evaluate agents and skills for quality and standards compliance.

Background memory consolidation and learning graduation — overnight knowledge lifecycle.

Classify user requests and route to the correct agent + skill. Primary entry point for all delegated work.

Detect documentation drift against filesystem state.

Query and display structured decision traces from routing, agent selection, and skill execution.

Generate project-specific CLAUDE.md from repo analysis.

Generate rich self-contained HTML artifacts instead of markdown. Auto-detects artifact shape (spec, code-review, prototype, report, editor, data-viz, diagram, deck) and loads shape-specific patterns. Bundles Birchline design system with 4 theme presets. Use for "make HTML", "as HTML", "HTML artifact", or auto-injected by router when output benefits from rich visualization.

Verify VexJoy Agent installation, diagnose issues, and guide first-time setup.

Manually teach error pattern and solution to learning database.

Analyze agent/skill reference depth and generate missing domain-specific reference files.

Learning system interface: stats, search, graduate learnings. Backed by learning.db (SQLite + FTS5).

Maintain /do routing tables when skills or agents change.

DAG-based multi-skill orchestration with dependency resolution.

Create and iteratively improve skills through eval-driven validation.

Evaluate skills: trigger testing, A/B benchmarks, structure validation, head-to-head bake-offs.

Closed-loop toolkit self-improvement: discover gaps, diagnose, propose, critique, build, test, evolve.

Interactive guide to workflow system: agents, skills, routing, execution patterns.

Multi-agent consultation for architecture decisions.

Polling, retry, and backoff patterns.

Feature lifecycle: design, plan, implement, validate, release. Phase-gated workflow.

Post-mortem diagnostic analysis of failed workflows.

Triage GitHub notifications and report actions needed.

Collaborative coding with enforced micro-steps and user-paced control.

Planning lifecycle umbrella: spec, pre-plan ambiguity resolution, file-backed planning, plan validation, plan-lifecycle management, and session pause/resume. Use for "write spec", "define requirements", "before we plan", "discuss ambiguities", "create plan", "task plan", "working memory", "check plan", "validate plan", "is this plan ready", "list plans", "plan status", "complete plan", "pause", "save progress", "session handoff", "resume", "continue work", or "where did I leave off".

Capture forward-looking idea as a seed for future feature design.

Pull request lifecycle: commit, codex review, sync, review, fix, status, cleanup, and PR mining. Use when user wants to commit changes, get a second-opinion code review from Codex, push changes, create a PR, check PR status, fix review comments, clean up branches after merge, or mine tribal knowledge from PR reviews. Use for "commit my changes", "codex review", "push my changes", "create a PR", "pr status", "fix PR comments", "clean up branches", "mine PRs", or "address feedback".

Tracked lightweight execution with composable rigor flags: --trivial, --discuss, --research, --full. Covers zero-ceremony inline fixes (≤3 edits) through contained multi-file changes.

Read-only exploration, inspection, and reporting without modifications.

Question-only debugging: guide users to find root causes themselves.

Fresh-subagent-per-task execution with two-stage review gates.

Defense-in-depth verification before declaring any task complete.

Anti-rationalization enforcement for maximum-rigor task execution.

Mandatory rules for agents in git worktree isolation.

Proactive architecture improvement: find shallow modules, propose deepening opportunities, design conversation.

Statistical rule discovery from Go codebase patterns.

Systematic codebase exploration and architecture mapping.

Decision-first data analysis with statistical rigor gates.