LLM & Agents

Diagnose errors and failing tests in Laravel + React applications. Use when encountering bugs, exceptions,stack traces, 500 errors, TypeErrors, failing Pest/Vitest tests, or unexpected behavior. EXCLUSIVE to debugger agent.

Convex AI Integration - OpenAI, actions, streaming, and AI patterns with database integration

Deployment procedures, health checks, and rollback strategies. Use this skill when deploying applications, performing health checks, managing releases, or handling deployment failures. Provides systematic deployment workflows, verification scripts, and troubleshooting guides. Complements the devops-automation agent.

Self-improving learning system that detects friction signals and proposes rule updates. This skill should be used when Claude needs to learn from mistakes, when users repeatedly correct behavior, when tool failures indicate missing knowledge, or when reviewing learning candidates via /coach commands.

Performs interactive rebases with smart commit management and conflict resolution. Use when rebasing branches, cleaning up commit history, resolving conflicts, or when the user mentions "rebase", "interactive rebase", "squash commits", or wants to update their branch with latest changes from main/develop.

Use this skill when the user wants to create Angular applications, generate Angular components/services/modules, or automate Angular development workflows. Handles scaffolding complete Angular apps with routing and guards, generating individual Angular artifacts, setting up project structure, and initializing git repositories with Angular best practices.

Semantic search infrastructure for Obsidian vaults using vector embeddings. Covers embedding models, chunking strategies, similarity search, and incremental indexing.

A clear description of what this skill does and when Claude should use it. Include trigger phrases like "when asked to...", "use when...", or specific keywords that should activate this skill.

Validates and coordinates batch study guide operations (both separate and merge modes).Ensures file availability, template compatibility, and source-only policy before launching agents.**CRITICAL AUTOMATION**: Prevents batch processing errors by validating all prerequisites.

Orchestrates automated service-based website generation with local SEO optimization. Creates 200+ service+location pages using parallel agents, Unsplash images via Jina AI, NextJS with dynamic routing, and PostgreSQL database. Use when building service business websites (plumbers, electricians, pressure washing, HVAC, etc.) targeting multiple locations.

Access pattern library extracted from existing templates for reuse when creating new templates. Use when creating .md files for commands, agents, skills or when generating CLAUDE.md, README.md, or settings.json. Provides templatable patterns and quick-start presets.

This skill should be used when the user asks to "start parallel implementation", "orchestrate tasks", "run ultraplan", "launch ultrathink workflow", "parallel subagent execution", "plan and implement feature", "coordinate implementation across phases", "run 100 agents", "massive parallel work", or needs guidance on orchestrating multi-phase implementation workflows with parallel Task invocations.

MinIO S3-compatible object storage API. Use this skill for file upload, download, bucket management, and pre-signed URL generation.

Generate task (T####) and report (R####) IDs with rich metadata tracking. Stores creation date, source document, type, and notes for every ID. State in .claude/state/task-streams/id-generator.json (gitignored). Auto-initializes. (project, gitignored)

GraphRAG-powered code intelligence providing agentic reasoning tools (agentic_context, agentic_impact, agentic_architecture, agentic_quality) that return synthesized ANSWERS about code relationships, dependencies, architecture, and quality metrics. Uses knowledge graph + vector embeddings for relationship-aware code understanding. Replaces mcp-semantic-search.

Validate Claude Code plugin structure, manifests, frontmatter, and dependencies. Use when user mentions "validate plugin", "check plugin health", "plugin broken", "plugin not loading", "plugin errors", "plugin.json invalid", "agent not working", "check plugin structure", or reports plugin-related issues.

Systematic development skill for H2 Tank Designer frontend and mock server. Use when building, testing, or modifying the H2 Tank Designer project. Enforces TDD, RTM-driven development, and phased validation. Ensures agent stays on track with specifications, validates against 189 requirements, and follows best practices for Next.js, React, TypeScript, and Three.js development.

Configures Claude Code permissions via natural language for CLI tools (git, gcloud, aws, kubectl, maven, gradle, npm, docker), project types (Rust, Java, TypeScript, Python), and file patterns. Use when asked to "configure permissions", "enable git", "allow docker", "setup project permissions", "apply permission profile", or "make files editable". Auto-detects project types and researches unknown tools.

Always search before starting any work across all coding agent session histories (Claude Code, Codex, Cursor, Gemini CLI, Aider, ChatGPT) to find whatever we've discussed before.

Empirica epistemic self-assessment framework for AI agents. Use when you need to assess your knowledge state, track learning, measure calibration, or ensure genuine metacognitive reasoning. Provides 13-vector epistemic assessment (KNOW, DO, CONTEXT, CLARITY, COHERENCE, SIGNAL, DENSITY, STATE, CHANGE, COMPLETION, IMPACT, ENGAGEMENT, UNCERTAINTY). Use for preflight assessment before tasks, postflight validation after completion, continuous epistemic tracking during complex work, or session handoff reports for multi-session/multi-agent coordination (98% token reduction).