AI & ML

tomevault-io Bundle

Core technical documentation writing principles for voice, tone, structure, and LLM-friendly patterns. Use when writing or reviewing any documentation. Use when this capability is needed.

tomevault-io Bundle

Build, install, inspect, and debug term-llm Web UI widgets. Use when adding local widget apps, editing widget manifests, checking widget routes, or explaining how /chat/widgets works. Use when this capability is needed.

tomevault-io Bundle

Build conversational voice agents using Sarvam AI with LiveKit or Pipecat. Handles voice assistants, phone bots, IVR, and real-time conversational AI for Indian languages. Integrates Sarvam STT (Saaras v3), TTS (Bulbul v3), and LLM (Sarvam-30B) with low-latency streaming. Use when creating voice-enabled applications or real-time speech pipelines. Use when this capability is needed.

tomevault-io Bundle

Guide for the RAD (Rapid Application Development) model including defattr, entity definitions, identities, and test builder patterns. Use when working with the data model, creating entities, or understanding database schema. Use when this capability is needed.

tomevault-io Bundle

MCP server exposing spec2 as tools for Claude Code, Gemini CLI, and other MCP clients Use when this capability is needed.

tomevault-io Bundle

Audit a repo's tooling for coding agent self-verification. Use when the user wants to audit agent tooling, mentions "agent-dx", "agent developer experience", "what testing tools do I need", "set up verification for agents", "how can agents test this", or when onboarding to a new codebase and want to know what verification tools are missing. Use when this capability is needed.

tomevault-io Bundle

Git/PR gatekeeper that classifies change essence, recommends granularity, naming, and strategy. Use when PR preparation or commit strategy is needed. Use when this capability is needed.

tomevault-io Bundle

国際化（i18n）・ローカライズ（l10n）スペシャリスト。ハードコード文字列のt()関数化、Intl APIによる日付/通貨/数値フォーマット、翻訳キー構造管理、RTLレイアウト対応。多言語対応、i18nセットアップが必要な時に使用。 Use when this capability is needed.

tomevault-io Bundle

Investigate a network incident by correlating device events with camera footage and physical access logs. Use when the user reports a device going offline, a network anomaly, or wants to understand what caused an infrastructure event. Use when this capability is needed.

tomevault-io Bundle

Use when working with the concierge proxy — turn a vague user script ("I need the agent to help me do X") into a context contract, route it to the right skills/workflows, add backpressure (tests/evals/reviews/approvals), execute, and report. Use when a request is multi-step, durable, or human-in-the-loop and you'd otherwise hand-roll the orchestration; skip it for a single prompt → single answer.

tomevault-io Bundle

Persistent memory enhancement for AI agents. Store conversations, search memories with semantic retrieval, and recall context across sessions. Use this skill when you need to remember user preferences, past conversations, project context, or any information that should persist beyond the current session. Provides tiered access (abstract/overview/content) for efficient context management. Use when this capability is needed.

tomevault-io Bundle

Audits repositories for context bloat and unnecessary explanatory surface across copilot instructions, file instructions, skills, prompts, agents, MCP definitions, docs, templates, comments, and docstrings. Use when reducing context tax, pruning duplicate guidance, tightening broad scopes, or fixing stale verbose agent tooling. Use when this capability is needed.

tomevault-io Bundle

Enable browser automation capabilities using Playwright MCP server. This allows agents to interact with web pages, take screenshots, fill forms, and perform automated browser tasks through the Playwright automation framework. Use when this capability is needed.

tomevault-io Bundle

AI agent skills for working with the Lithent library. Use when this capability is needed.

tomevault-io Bundle

Create cross-agent compatible skills with SKILL.md format, supporting files, and scripts for Claude Code, Copilot, Cursor, Windsurf, and other AI coding assistants Use when this capability is needed.

tomevault-io Bundle

Run interactive CLI tools (claude code, aider, codex, dev servers, builds, REPLs, debuggers — anything PTY-based) inside durable sessions that survive across turns, agent restarts, and laptop closings. Use this skill when (1) you need to run anything interactive that takes more than a few seconds, (2) state must persist between turns (a build cache, an open editor, a paused debugger, an in-progress refactor), (3) the user wants to monitor or interject from their phone, (4) you want to run multiple parallel tool sessions you can return to later, or (5) the user explicitly asks for a "shmerm session", "durable session", "background session", or "session I can watch". Provides session lifecycle (run/list/attach/kill), a live web viewer with kill button, optional public tunnel, and an inbox channel for human interjections that arrive while you are working. Use when this capability is needed.

tomevault-io Bundle

AllBeads - Multi-Repo Agent Orchestration

tomevault-io Bundle

Use when the maintainer onboards a new AI coding agent (Aider, Gemini CLI, Windsurf, Cline, a new Claude/Cursor/Codex instance on a new machine, etc.) to contribute to the tinyhat repo under a bot identity. Covers machine-user provisioning, SSH key + host alias setup, adding the agent row to the private bot identity table in CLAUDE.local.md, and the `.gitignore` pattern for the agent's machine-local state.

tomevault-io Bundle

Expertise for using OpenCode (an open-source AI coding agent) and building client applications that interact with the OpenCode HTTP server. Use this skill when the user asks about OpenCode features, how to use it, or how to build tools/clients that integrate with the OpenCode server API. Use when this capability is needed.

tomevault-io Bundle

Test and validate agent skills against the Agent Skills Specification v1.0. Use before deploying skills to ensure spec compliance and catch structural issues. Use when this capability is needed.

tomevault-io Bundle

Analyze a code repository to understand architecture, key components, data flow, and extension points. Use when onboarding to an unfamiliar repo, preparing a hands-on profiling session, or extracting LLM-specific implementation details (attention/KV cache/scheduler/decoding) after determining the repo is LLM-related. Use when this capability is needed.

tomevault-io Bundle

Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents Use when this capability is needed.

tomevault-io Bundle

Use when the user asks to add, contribute, or create a new vLLM recipe in this repo (e.g. "add a recipe for Qwen/Qwen3-XYZ", "create a recipe for huggingface.co/org/model"). Walks through fetching HF metadata, authoring the YAML at models/<hf_org>/<hf_repo>.yaml, picking variants/strategies, validating, and committing.

tomevault-io Bundle

Expert in .faf (Foundational AI-context Format) files for persistent project context. Use when working with .faf files, project DNA, CLAUDE.md bi-sync, faf-cli commands, MCP server configuration, or AI-readiness scoring (0-100%). Updated for v2.8.0 Tool Visibility System. Use when this capability is needed.

tomevault-io Bundle

memories-mcp

tomevault-io Bundle

Generates a fun fact and writes it to C:/Users/Public/funfacts/funfact.txt via MCP filesystem tools

tomevault-io Bundle

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks. Use when this capability is needed.

tomevault-io Bundle

MCP Creator — FastMCP v3

tomevault-io Bundle

Agent-first workflow and design rails for building X07 programs with the released toolchain (no repo-only dependencies). Canonical execution is via `x07 run`. Use when this capability is needed.

tomevault-io Bundle

Use when the user wants to delegate a scoped subtask to the locally installed Gemini CLI or spend Gemini Code Assist / Google One AI Pro quota from the terminal, especially for small read-only investigations, summaries, MCP-assisted diagnostics, or Chrome debug tasks. Prefer non-interactive `gemini -p` runs and use `scripts/check_usage.mjs` instead of the interactive `/usage` panel.

tomevault-io Bundle

Agent Memory

tomevault-io Bundle

Crypto wallet API + CLI for AI agents. Single entry point for wallet analysis (portfolio, positions, history, PnL), on-chain trading (swap, bridge, send), off-chain signing (EIP-191, EIP-712), wallet management (create/import/backup), agent tokens + policies for autonomous trading, and partner integrations (0x, Bankr, Li.Fi, Moonpay, Uniswap, Vaults.fyi, Trails, Umbra, Somnia, Monad, Sendai). Use this skill for any crypto wallet, DeFi, or on-chain task. Deep docs load on demand from `capabilities/` and `partners/`. Use when this capability is needed.

tomevault-io Bundle

Diagnose and configure MemSearch memory behavior for the Claude Code plugin. Use when the user asks about MemSearch configuration, plugin summarization, PROJECT.md/USER.md maintenance, memory directories, index health, provider routing, prompt files, or migration/compatibility questions. Use when this capability is needed.

tomevault-io Bundle

This skill should be used when the user asks to "audit my memories", "sweep memories", "find memory-only rules", "what memories should be promoted to instructions", "review my Copilot memories", or any similar request to identify rules that live only in stored Copilot memories but are not yet documented in their personal copilot-instructions.md. It dumps the current memories from the agent's prompt context to a tempfile and runs a Python classifier that scores each memory against the instructions file for keyword and phrase overlap. Output is a list of memories classified as PROMOTE (memory-only, candidate for promotion), AMBIGUOUS (partial overlap, worth eyeballing), or PRESENT (already covered). Use when this capability is needed.

tomevault-io Bundle

Set up or update repository agent instruction files after installing skills. Use when a user wants AGENTS.md, CLAUDE.md, GEMINI.md, Copilot instructions, Cursor rules, or docs/agents/*.md configured according to the skills installed in the repo. Use when this capability is needed.

tomevault-io Bundle

Control smart home devices including lights, doors, and TV Use when this capability is needed.