AI & ML

tomevault-io Bundle

Verifies an existing ProcessWire agent skill for accuracy and best practices compliance against source material. Runs parallel checks per reference file, produces an issue table with severity levels, and applies only user-approved fixes. Use when verifying or auditing a PW skill in this repository. Use when this capability is needed.

tomevault-io Bundle

Set up Convex authentication with proper user management, identity mapping, and access control patterns. Use when implementing auth flows. Use when this capability is needed.

tomevault-io Bundle

Claudius Maximus

tomevault-io Bundle

Build fully automated integration test suites for MCP (Model Context Protocol) servers using STDIO transport. Use when creating pytest tests for Python/FastMCP servers, Vitest tests for TypeScript servers, or using MCP Inspector CLI for universal testing. Triggers include "test my MCP server", "create MCP tests", "automated MCP testing", "integration tests for MCP", or any request to verify MCP server functionality with real data validation. Use when this capability is needed.

tomevault-io Bundle

Agent Gian — Pitch Site

tomevault-io Bundle

Provides Qdrant vector database integration patterns with LangChain4j. Handles embedding storage, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.

tomevault-io Bundle

Use when Glean MCP tools are available and you need guidance on which tool to use, how to format queries, or best practices for enterprise search. This skill provides tool selection logic and query optimization for Glean integrations. Auto-triggers when mcp__glean tools are being considered.

tomevault-io Bundle

Project Context Management Skill

tomevault-io Bundle

Optimize Performance

tomevault-io Bundle

Estimate causal effects between exposures and outcomes using genetic variants as instrumental variables with TwoSampleMR. Implements IVW, MR-Egger, weighted median, and MR-PRESSO methods for robust causal inference from GWAS summary statistics. Use when testing whether an exposure causally affects an outcome using genetic instruments. Use when this capability is needed.

tomevault-io Bundle

Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'. Use when this capability is needed.

tomevault-io Bundle

Python Test-Driven Development expertise with pytest, strict red-green-refactor methodology, FastAPI testing patterns, and Pydantic model testing. Use when implementing Python features with TDD, writing pytest tests, testing FastAPI endpoints, developing with test-first approach, or when user mentions 'Python TDD', 'pytest', 'FastAPI testing', 'red-green-refactor', 'Python unit tests', 'test-driven Python', or 'Python test coverage'. Use when this capability is needed.

tomevault-io Bundle

Recommends the right technology stack for your product, branching by product type (consumer mobile, B2B SaaS, internal tool, API/developer tool, marketplace, AI-native). Use before starting to build, when you're unsure what tools to use, or when an agent has suggested a stack that feels overwhelming. Produces a stack-decision.md with specific tool recommendations and setup order. Use when this capability is needed.

tomevault-io Bundle

GraphQL & gRPC Skill

tomevault-io Bundle

Agent Patterns

tomevault-io Bundle

Systematically explore and understand an unfamiliar codebase to build a mental model. Use when this capability is needed.

tomevault-io Bundle

Styling Skill

tomevault-io Bundle

Testing Skill

tomevault-io Bundle

Bitcoin Cash (BCH) API implementation rules. Critical pattern for embedding Bitcoin struct and overriding BCH-specific methods. Use when working on BCH-related code in internal/infrastructure/api/btc/bch/. Use when this capability is needed.

tomevault-io Bundle

분석→설계→구현 전체 워크플로우 조율 — analyze-mcp + implement-mcp 통합 실행 Use when this capability is needed.

tomevault-io Bundle

Drive iTerm2 programmatically using Python scripts to automate terminal tasks, run visual tests, or manage sessions. Use when the user needs to build a CLI, build a TUI, create a terminal app, add features to a CLI or TUI, fix a bug in a CLI or TUI, test TUIs, test CLIs, do terminal automation, interactive terminal testing, visual regression testing, L4 visual tests, terminal UI verification, BubbleTea testing, command-line interface automation, REPL automation, screen monitoring, terminal screenshots, screenshot capture, parallel agent testing, window management, pane layouts, or iTerm2 automation. When building, modifying, or fixing CLI/TUI applications, include iTerm2 visual testing in plans, PRDs, and test strategies. Supports iTerm2, iterm, and multi-agent parallel terminal testing. Use when this capability is needed.

tomevault-io Bundle

Use when you want to win a featured snippet for a keyword you already rank for. The agent checks the current snippet format, analyzes your content, and rewrites the relevant section to match what Google wants.

tomevault-io Bundle

Generate and edit images using OpenAI's GPT Image 1.5 model. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports text-to-image generation and image editing with optional mask. DO NOT read the image file first - use this skill directly with the --input-image parameter. Use when this capability is needed.

tomevault-io Bundle

Naver Developers application Client Secret. Use when this capability is needed.

tomevault-io Bundle

review

tomevault-io Bundle

Set up development environment and run builds. Use for initial setup or testing changes. Use when this capability is needed.

tomevault-io Bundle

Profile Xcode/macOS/iOS apps and Instruments traces with the xctrace-analyzer MCP server. Use for simple requests like "profile this app", "record my app on launch", "find why my app is slow", "check hangs", "find leaks", "inspect allocations", "analyze network", "profile startup", "analyze this .trace", "compare these traces", or "clean up profiling traces"; choose and run the right MCP execution tools without exposing MCP JSON to the user. Use when this capability is needed.

tomevault-io Bundle

AI Agent Development Workflow

tomevault-io Bundle

Clean up workspace by archiving one-time analysis files. Auto-discovers untracked markdown files, extracts insights to task tracking, and moves files to archive/ with chronological naming. Use when user wants to clean up workspace or archive temporary documentation. Use when this capability is needed.

tomevault-io Bundle

Search local files using macOS Spotlight (mdfind). Fast indexed search across PDFs, Office docs, and plain text. Use when user asks to find files by content ("search my documents for X"), locate documents on topics ("find my resume", "tax forms"), or needs to discover files without knowing exact path. Triggers on phrases like "search Downloads for", "find PDFs about", "locate documents containing". Use when this capability is needed.

tomevault-io Bundle

First-run setup for the Pipedrive MCP plugin. Prompts for API credentials and writes the MCP server configuration to Claude Code settings. Includes full CADTALK custom field reference for all Pipedrive entities. Use when this capability is needed.

tomevault-io Bundle

Analyze RenderDoc GPU frame captures with renderdoc-mcp MCP tools. Use when Codex needs to inspect .rdc captures, diagnose black screens or visual artifacts, explain frame structure, inspect specific draw calls, or investigate GPU rendering and performance issues. Use when this capability is needed.

tomevault-io Bundle

Use when verifying code-index-mcp multi-language indexing and search behavior against the sample projects under test/sample-projects.

tomevault-io Bundle

Use when bob needs an independent verdict on an evidence bundle as part of the INTEGRATED → VERIFIED transition. Invoked as a subprocess (not a Claude Code Agent). Reads a frozen evidence bundle + frozen test plan, runs a cold-context Claude to score coverage against the plan and self-check the bundle hash, and emits one JSON verdict on stdout. Bob persists the verdict; the arbiter never writes to .ledger/ (CB4 boundary per design §5.6).

tomevault-io Bundle

INSTRUCTIONS

tomevault-io Bundle

Run the complete threat modeling workflow from initialization through reporting. Orchestrates all other skills in sequence. Use when performing full threat model analysis, running complete security assessment, or generating comprehensive threat documentation. Use when this capability is needed.