udecodeOfficial·16 Agent Skills Included

dotai

Shared AI agent skills for coding, reviews, and backlog automation

Automates core software workflows for AI coding agents: test-driven development, PR feedback resolution, Linear backlog execution, and parallel worktree orchestration. Eliminates manual triage of review comments, vague goals, stale docs, and AI-sounding prose. Includes goal tracking, video transcripts, annotated walkthroughs, and cleanup tools so agents finish verifiable work faster.

1,154|81

↗

npx skills add udecode/dotai --all -g -y

Available:

Gives the AI agent concise behavioral rules: use the GitHub CLI for GitHub interactions, keep all output extremely concise, list unresolved questions after each plan, and validate skills before committing edits.

All Skills in This Repository (16)

Pure Emerald Level Indicators

📦 In Repo

udecode

linear-backlog

Executes a scoped Linear backlog as maximal safe parallel batches via orchestrator child threads.

walkthrough

Create annotated visual walkthroughs from real final-state screenshots and rendered artifacts.

unslop

Draft, audit, and edit prose to remove AI-writing patterns while preserving facts and voice.

sync-vision

Sync root VISION.md from changed project docs, plans, and rules.

test-driven-development

Enforces test-first development by writing failing tests, implementing minimal code, and refactoring.

executing-plans

Execute implementation plans in batches with verification and review checkpoints.

brainstorming

Translate rough ideas into structured design documents through collaborative questioning.

writing-plans

Generate implementation plans with file paths, code samples, and tests.

dispatching-parallel-agents

Dispatch parallel Claude agents to investigate and fix independent failures concurrently.

using-skills

Enforce mandatory skill discovery, validation, and usage before user tasks.

writing-skills

Generate MDC-based Claude rules and skills from failure patterns.

reviewing-pr

Automate GitHub pull request reviews with severity-rated feedback.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install dotai?▼

Run `npx skills add udecode/dotai --all -g -y` in your terminal to install every skill in this suite globally.

What does dotai do for coding agents?▼

It gives your AI agent reusable workflows for TDD, PR feedback resolution, Linear backlog execution, goal tracking, and parallel worktree orchestration.

Can AI resolve GitHub PR review comments automatically?▼

Yes. The resolve-pr-feedback skill fetches review threads, fixes valid feedback, replies with evidence, and resolves threads using the GitHub CLI.

Does dotai work with Claude Code and Codex?▼

Yes. All skills follow the standard SKILL.md format and run in Claude Code, Codex, Cursor, and other compatible agents.

Can dotai remove AI-sounding writing from docs?▼

Yes. The unslop skill audits and edits prose to remove AI-writing patterns while preserving facts, voice, and technical accuracy.