AI & ML

tomevault-io Bundle

Use Playwright MCP to explore a feature, analyze existing tests, and generate/update E2E tests. Prioritizes user journey scenarios over individual element tests. Use when this capability is needed.

tomevault-io Bundle

Review JSON entities pushed to an EntityStore corpus (a git branch, a PR, or an explicit file set) against the LATEST entity.schema.json AND the EntityStore vision guardrails — schema validity, provenance honesty, anti-authority PROHIBITED-field enforcement, navigation reference-anchor discipline, scribe/enricher role boundaries + lazy-materialization, volatile-not-frozen integration fields, identity-as-revisable (v6 identity_assertions), referential integrity, and corroboration thinness. Diff-scoped and vision-aware — complements (does not replace) cb_engine `wiki_audit`, which is corpus-wide. Use when reviewing a company-brain PR/branch that adds or changes entity JSON, gating a backfill/scribe output before merge, or wiring a CI check on entity changes. Do NOT use for code review, schema design, or non-entity JSON. Use when this capability is needed.

tomevault-io Bundle

Adapt and debug existing or new models for vLLM on Ascend NPU. Implement in /vllm-workspace/vllm and /vllm-workspace/vllm-ascend, validate via direct vllm serve from /workspace, and deliver one signed commit in the current repo. Use when this capability is needed.

tomevault-io Bundle

Poll oz-workspace for @mentions and post agent responses back to rooms. Use when this capability is needed.

tomevault-io Bundle

Strategic guidance for adding WebMCP to web applications. Use when the user wants to make their web app AI-accessible, create LLM tools for their UI, or enable browser automation through MCP. Focuses on design principles, tool architecture, and testing workflow. Use when this capability is needed.

tomevault-io Bundle

AGENTS.md Authoring Skill

tomevault-io Bundle

Learn from Conversation

tomevault-io Bundle

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains. Use when this capability is needed.

tomevault-io Bundle

Agent Conventions

tomevault-io Bundle

Create a git commit for AI-generated/modified documentation files. Use after generating or updating AI documentation. Use when this capability is needed.

tomevault-io Bundle

Get the informative summary of a file, especially for code files. Use when needing to understand the purpose and functionality of a specific file. Use when this capability is needed.

tomevault-io Bundle

---

tomevault-io Bundle

Build AI-native products with agency-control tradeoffs, calibration loops, and eval strategies. Use when building AI agents, LLM features, or products where AI handles user tasks autonomously. Part of the Modern Product Operating Model collection. Use when this capability is needed.

tomevault-io Bundle

MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, adding authentication, creating interactive UIs, hardening MCP security, or debugging MCP integrations. Use when this capability is needed.

tomevault-io Bundle

Structured TODO commit workflow using JJ (Jujutsu). Use to plan tasks as empty commits with [task:*] flags, track progress through status transitions, manage parallel task DAGs with dependency checking. Enforces completion discipline. Enables to divide work between Planners and Workers. **Requires the working-with-jj skill** Use when this capability is needed.

tomevault-io Bundle

💻 MacBook Optimizer

tomevault-io Bundle

抖音无水印视频下载和文案提取工具. 从抖音分享链接获取无水印视频下载链接, 下载视频, 提取视频中的语音文案并自动保存到文件. 适用场景包括获取抖音视频信息, 下载无水印视频, 批量提取视频文案. 当用户需要处理抖音视频链接或提取视频内容时触发. Use when this capability is needed.

tomevault-io Bundle

Use when creating a castle, fortress, keep, walls, towers, or battlements in Unreal Engine with primitive shapes. Use this skill to inspect the Unreal CLI help, create the sample castle workflow, and verify the result by listing actors.

tomevault-io Bundle

Agent skill for app-store - invoke with $agent-app-store Use when this capability is needed.

tomevault-io Bundle

Advanced Hive Mind collective intelligence system for queen-led multi-agent coordination with consensus mechanisms and persistent memory Use when this capability is needed.

tomevault-io Bundle

Bug-fixing workflow that starts by writing a failing test to reproduce the bug, then uses subagents to propose fixes and verifies with passing tests. Use when a user reports a bug, asks to fix a bug, or wants a regression test first. Use when this capability is needed.

tomevault-io Bundle

Optimize prompts for Roo Code Architect mode with GPT-5.2 and high reasoning, specifically for investment management systems in European and APAC financial services Use when this capability is needed.

tomevault-io Bundle

Empirically evaluate and optimise a Claude Code sub-agent via a blinded head-to-head against the production baseline, then pick its model on data. Use when tuning a sub-agent's prompt, choosing or re-checking its model (e.g. a new model release), proving an agent change before committing, or testing whether a specialist beats native Explore. To author a new agent first, read AUTHORING.md. Use when this capability is needed.

tomevault-io Bundle

Deterministic compiled graphs for OpenClaw (importer, runtime, MCP tools) Use when this capability is needed.

tomevault-io Bundle

Agent-to-agent protocol for social coordination, crypto payments, and P2P mesh. Use when this capability is needed.

tomevault-io Bundle

Answer questions about Tactical RMM (TRMM) — an open-source remote monitoring and management platform. Covers architecture, installation, agent deployment (Windows/Linux/macOS), MeshCentral integration, scripting (PowerShell/Python/Bash/Deno), script variables, custom fields, keystore, automated checks, tasks, automation policies, maintenance mode, alerting, email/SMS notifications, webhooks, REST API, global settings, overrides, permissions, Django admin, URL actions, user interface, software management, web terminal, management commands, reporting (Enterprise), SSO (Enterprise), third-party integrations (Bitdefender, Zammad), SNMP checks, BitLocker key retrieval, remote background sessions, and troubleshooting FAQ. Use when this capability is needed.

tomevault-io Bundle

Evaluate JavaScript at bundle time and inline results. Use when optimizing compile-time code generation, embedding files, inlining environment variables, or executing code during the bundling process. Use when this capability is needed.

tomevault-io Bundle

Anthropic Messages API (Claude API) for integrations, streaming, prompt caching, tool use, vision. Use for chatbots, assistants, or encountering rate limits, 429 errors. Use when this capability is needed.

tomevault-io Bundle

Run Playwright E2E tests as smoke; summarize results. Use when asked to "run E2E", "smoke test", or "check E2E". Use when this capability is needed.

tomevault-io Bundle

Replit Prompt Generator

tomevault-io Bundle

Routes human-facing artifacts to Notion via the Notion MCP and notion plugin. Determines what gets pushed to Notion (architecture decisions, ADRs, project status, retrospectives, board materials, weekly summaries, customer-facing docs) and what stays local (lessons, session transcripts, operator-model, curator reports, ephemeral plans, code review notes, skill files). Use when a task produces a human-facing artifact, when Brandon says "push this to Notion" or "save this for the team", or at the end of a /ship run that generated documentation worth sharing. Always asks Brandon to confirm target page or database with one-line preview before pushing. Never pushes secrets, API keys, internal financial numbers, or PII without explicit per-push approval. Coordinates with notion plugin for slash commands and Notion MCP for raw operations. Use when this capability is needed.

tomevault-io Bundle

Git worktree management for isolated parallel prompt execution. Use when creating isolated environments for prompt comparison or managing worktree lifecycle. Provides creation, cleanup, and orphan detection scripts. Use when this capability is needed.

tomevault-io Bundle

Compress LLM responses to pure signal — Rocky's early notation style. Drop articles, filler, hedging. Best for pipelines and coding. Use when this capability is needed.

tomevault-io Bundle

Build command-line interfaces with async-first design, composable commands, and proper output formatting. Use when creating CLI tools, commands, or interactive terminal applications. Use when this capability is needed.

tomevault-io Bundle

Manage Git commits using conventional commit format with atomic staging. Always generate plain git commands before running them and offer to let the user run them manually. Use when this capability is needed.

tomevault-io Bundle

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", "scoped hooks", "frontmatter hooks", "hook in skill", "hook in agent", "agent hook type", "async hooks", "once handler", "statusMessage", "hook decision control", "TeammateIdle hook", "TaskCompleted hook", or mentions hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure, Stop, SubagentStop, SubagentStart, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification, TeammateIdle, TaskCompleted). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API. Use when this capability is needed.