abpai
@abpai
Public Skills
agent-kanban
by abpai
Operate the agent-kanban board via its stdio MCP server (preferred) or the kanban CLI — supports local (SQLite), Linear, and Jira providers.
bun-expert
by abpai
Expert guidance for JavaScript/TypeScript development with the Bun runtime. Covers project setup, package management, HTTP servers, built-in APIs, testing, bundling, and migration from Node.js. Use when starting Bun projects, using Bun APIs (Bun.serve, sql/SQL, s3, redis, Bun.$), migrating from Node.js, or troubleshooting Bun-specific behavior.
dead-code-eliminator
by abpai
Audit a codebase for dead code — unreachable functions, unused imports, orphaned classes, unreachable branches, and stale feature flags — by tracing live call paths from all entry points. Also audits correctness (do implementations match their claimed purpose?) and algorithmic soundness. Produces an ASCII call graph and a categorized dead code report. Use when a codebase has gone through many iterations, a large refactor has landed, a feature was removed but its support code may remain, or the user asks to "find dead code", "clean up unused code", "audit what's actually used", or "find orphaned functions".
socratic-code-owner
by abpai
Quizzes the developer on code, architecture, or plans that an AI agent just built or proposed — one question at a time, with ASCII diagram corrections. Use after any significant implementation, PR, refactor, or architectural plan to ensure the human code owner has a bulletproof mental model of the system. Triggers include phrases like "quiz me", "do I understand this", "walk me through what you built", "onboard me", or "code owner briefing".
vibe-kanban
by abpai
Manage work in Vibe Kanban (VK), the shared source of truth for agent tasks. Use when checking assigned work, creating/updating tasks, running heartbeat checks, scanning @mentions, or producing daily standup summaries. Triggers: "check the board", "what's on my plate", "create/update task", "heartbeat", "standup summary".
agent-browser
by abpai
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
code-review-and-commit
by abpai
Review uncommitted Git changes for correctness, quality, and project convention alignment, then apply fixes and prepare a safe, atomic commit plan. Use when users ask to review code before committing, improve local changes, split work into logical conventional commits, or execute git add/git commit with clear staging boundaries.
beautiful-mermaid
by abpai
Render Mermaid diagrams as SVG and PNG using the Beautiful Mermaid library. Use when the user asks to render a Mermaid diagram.
code-simplifier
by abpai
Simplify and refactor code for clarity, consistency, and maintainability while preserving exact behavior. Use when code was just added or modified and needs readability-focused cleanup without changing outputs, side effects, or external interfaces.
slidev
by abpai
Create and present web-based slides for developers using Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, or teaching materials.
project-memory
by abpai
Always-on project memory workflow. At the start of every task, read .agents/LEARNINGS.md; while working, update it with mistakes, corrections, successful and failed patterns, and project-specific preferences.
codex
by abpai
Run Codex CLI for code analysis and automated edits. Use when users ask to run codex exec/codex resume, continue a prior Codex session, or delegate software engineering work to OpenAI Codex.
cli-design-expert
by abpai
"Design or review command-line interfaces for usability and automation: help text, args/flags, stdout vs stderr, exit codes, TTY behavior, config precedence, and safe handling of secrets and destructive actions."