Skill-Agents

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.

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.

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.

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.

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, fixing accessibility or motion, refining interaction states, improving performance, or validating responsive layout and visual polish. Integrates with Skill-Agents frontend workflows and browser, Playwright, Figma, package, test, and validation MCP tools.

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.

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, 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.

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.

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 operating-system summary.

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.

Triage personal email, Slack/Discord messages, calendar events, and meeting context into action items, daily plans, meeting prep notes, draft replies, and issue/task drafts. Use when the user asks to summarize inboxes, prepare for meetings, extract follow-ups, plan the day, or turn messages into tasks.

Create clean Markdown reports, summaries, research briefs, project notes, RCA writeups, meeting summaries, decision records, and handoff documents. Use when the user asks to write, format, summarize, document, report, brief, or create a Markdown deliverable.

Improve vague, incomplete, ambiguous, risky, or poorly structured prompts into clear executable prompts for AI agents, coding assistants, automations, reports, research, or model-specific workflows. Use when the user asks to rewrite, clarify, optimize, score, translate, structure, or improve a prompt.

Research current news and create concise sourced daily briefings, market updates, AI news reports, Thailand news summaries, or scheduled news digests. Use when the user asks for daily news, current events, latest updates, recurring news reports, or news monitoring.

Research real AI-agent skill repositories, official docs, prompt libraries, SKILL.md patterns, AGENTS.md or CLAUDE.md conventions, and reusable workflow prompts. Use when creating, improving, auditing, comparing, templating, or monitoring AI agent skills and workflow repositories.

Explore and summarize an unfamiliar or existing project before planning, editing, onboarding, architecture review, migration, stack choice, or implementation. Use when the user asks to understand a repo, inspect architecture, map a codebase, discover project conventions, or prepare a project overview.