Create continuation notes that another model, provider, or agent can resume without relying on hidden context or exact tool names. Use when the user asks to hand off work between Claude, ChatGPT, Gemini, Codex, local agents, or another MCP-enabled assistant.
Adapt skills, workflows, prompts, and tool instructions so they work across Claude, ChatGPT, Gemini, Codex, local agents, and other MCP-enabled systems. Use when the user wants cross-model compatibility or asks to make instructions vendor-neutral.
Route tasks to available MCP or agent tools by capability rather than exact local tool names. Use when an agent has tools from Gemini, ChatGPT, Claude, Codex, or another MCP server and must decide which available tool capability to use.
Portable operating rules for any capable AI agent regardless of model provider or tool implementation. Use when the user wants a general agent behavior layer that works across Claude, ChatGPT, Gemini, Codex, local agents, or other tool-enabled assistants.
Retire, preserve, explain, or replace old skills without silently deleting useful history. Use when the user asks to deprecate a skill, replace a skill, audit stale skills, or understand why a skill should no longer be used.
Architecture review skill for evaluating codebase design, module boundaries, coupling, test seams, domain language, and simplification opportunities. Use when the user asks to improve architecture, zoom out, reduce complexity, untangle code, or review a design.
Code review skill for finding bugs, regressions, risky behavior, missing tests, and maintainability problems in diffs, pull requests, or local changes. Use when the user asks for review, scrutinize, audit, inspect, or feedback on code.
Disciplined diagnosis loop for bugs, failing tests, crashes, incorrect behavior, and performance regressions. Use when the user asks to debug, investigate, diagnose, find root cause, or provides an error log, stack trace, flaky behavior, or regression.
Test-driven development workflow for implementing features or fixing bugs through red-green-refactor. Use when the user asks to build, change, or fix behavior and the codebase has a practical automated test surface.
Design, implement, harden, and review production-grade user interfaces for web apps, dashboards, SaaS products, admin tools, forms, and responsive frontend components. Use when building or improving UI/UX, translating Figma or requirements into code, styling React/Vue/Svelte/HTML views, reviewing frontend quality…
Analyze and document the UX/UI of a project against the full UX/UI body of knowledge, or design the UX/UI for a new project from scratch. Use when the user wants to know "how is this project's UX/UI", to audit/review/evaluate an existing interface, to produce a UX/UI assessment report, or to design UX/UI for a new…
Manage draft skills that are not ready to ship yet. Use when the user asks to prototype, sketch, test, evaluate, or promote an experimental skill from in-progress into a stable skill bucket.
Design, organize, document, validate, or refactor MCP tools so they fit a skills/workflows/tools architecture. Use when the user asks to create tools, convert skills into tools, expose Python functions through MCP, map tools to skills, or maintain an mcp-tools folder.
Manage a skill repository: create, classify, improve, deprecate, or reorganize agent skills with clean buckets, clear SKILL.md metadata, progressive disclosure, and installable structure. Use when the user asks to make skills, organize skills, compare skill quality, or maintain a skills repo.
Create and edit Obsidian JSON Canvas .canvas files with nodes, edges, groups, colors, links, files, and spatial layouts. Use when the user asks for an Obsidian canvas, visual map, knowledge graph, board, flow, or .canvas file.
Create and edit Obsidian flavored Markdown notes with wikilinks, embeds, callouts, properties, tags, comments, highlights, footnotes, Mermaid, and Obsidian-specific syntax. Use when working with Obsidian .md notes, vault content, wikilinks, callouts, frontmatter, tags, or embeds.
Safely bridge Obsidian Markdown notes and Notion pages while preserving source-of-truth, tags, links, page IDs, URLs, and metadata. Use when the user asks to sync, publish, migrate, convert, summarize, or organize knowledge between Obsidian, Notion, local memory, or RAG indexes.
Operate across an Obsidian vault: organize notes, maintain links, normalize tags and properties, create indexes, update maps of content, and preserve vault conventions. Use when the user asks to clean, organize, connect, refactor, or maintain an Obsidian vault.
Manage personal-only skills and private agent preferences that should not be promoted into public or team skill buckets. Use when the user asks to add personal rules, local setup guidance, private workflows, preferences, or machine-specific instructions.
Apply Boomz's personal working preferences for Thai-first explanations, practical Markdown deliverables, AI skill creation, automation design, project planning, and Codex collaboration. Use when tailoring outputs, plans, reports, templates, or personal workflows for Boomz.
Coordinate a private daily personal agent workflow across calendar, email, chat, Notion, Obsidian, memory, finance watchlists, issue trackers, and user-run handoffs. Use when the user asks for daily planning, personal briefings, inbox triage, meeting prep, cross-workspace action lists, or a combined personal…
Design Codex automations, scheduled research jobs, recurring reports, reminders, monitors, thread follow-ups, and workspace jobs. Use when the user asks to set up, improve, schedule, template, audit, or design an automation, monitor, reminder, or recurring Markdown report.
Planning interview skill that asks sharp questions before execution and turns decisions into durable project docs, domain language, PRDs, or ADR notes. Use when the user has an idea, feature, plan, product change, or unclear request that needs alignment before implementation.
Create a compact continuation document for another agent or future session. Use when the user asks to hand off, summarize current work, continue later, create context, or preserve progress across sessions.