How do I install dotai?

Run these in Claude Code: npx -y skills add udecode/dotai --agent claude-code. Then prompt normally.

Does dotai auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

Plugin

dotai

Shared skills for coding agents. Skills are the main routing layer. This repo is the canonical source for reusable udecode workflows; downstream repos should link to these skills instead of copying long SKILL.md files around.

Boost this plugin

udecode@udecode

GitHub

Plugin Signal73/100Solid

maintained92

capable52

documented75

adopted65

Install

$ npx -y skills add udecode/dotai --agent claude-code

Stats

JavaScript Node Git GitHub Gemini

1,155

Stars

Forks

Active

Maintenance

JavaScript

Language

15d ago

Last commit

2y ago

Created

Repo: udecode/dotai

In this plugin

11 skills

See everything inside

What's inside

Skill(11 skills)

/agent-native-reviewerReview agent-native parity for skills, prompts, tools, commands, generated mirrors, repo workflows, and user-facing actions./autogoalCreate, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair./hard-cutRemove a feature completely with no backward compatibility; delete surfaces, callers, tests, docs, fallbacks, stubs, and dead exports.

README

Read on GitHub

dotai

Shared skills for coding agents.

Skills are the main routing layer. This repo is the canonical source for reusable udecode workflows; downstream repos should link to these skills instead of copying long SKILL.md files around.

Included Skills

autogoal: durable goal lifecycle and seeded plan templates.
- Deps: Codex goal tools (get_goal, create_goal, update_goal); optional orchestrator when $orchestrator on is active.
agent-native-reviewer: review whether agents can discover, perform, and verify the same meaningful actions as maintainers/users across skills, prompts, commands, generated mirrors, repo workflows, and product actions.
- Deps: optional autogoal, sync-skills, sync-vision, resolve-pr-feedback, hard-cut, tdd, and diagnosing-bugs for routed follow-up work.
hard-cut: delete-first repo cleanup workflow.
linear-backlog: execute a scoped Linear queue as maximal safe parallel batches without asking for each next batch.
- Deps: orchestrator, autogoal, repo-local task, Linear read/write tools, Git and PR tooling.
orchestrator: route implementation through durable child threads and disposable worktrees targeting main.
- Deps: durable Codex thread and project tools; Git worktrees.
resolve-pr-feedback: GitHub PR review feedback closure with source-backed triage, proof, replies, and thread resolution.
- Deps: gh, jq; optional project-owned docs/plans/templates/resolve-pr-feedback.md.
sync-vision: keep project root VISION.md current from changed human/agent inputs.
- Deps: autogoal; optional project-owned docs/plans/templates/sync-vision.md.
tdd: test-first development loop.
unslop: draft, audit, and edit prose without AI-writing tells while preserving facts and voice.
- Deps: optional Node.js for file and repo audits plus preservation checks.
video-transcripts: generate XML transcripts for tracker video evidence.
- Deps: GEMINI_API_KEY or GOOGLE_API_KEY; curl, jq, file, and ffmpeg; optional gh for private GitHub attachments.
walkthrough: explain completed UI or rendered-output changes with concise annotated visuals from real final-state artifacts.
- Deps: Git and Node.js for diff receipts; a repo-approved screenshot tool; imagegen or another safe image editor for annotations.

Quick Start

Install with the skills CLI:

npx skills add udecode/dotai

Validate

Run after edits:

scripts/validate-skills

Editing Rules

Keep descriptions short and useful for routing.
Keep skill bodies operational, not essay-like.
Prefer helper scripts for repeatable command logic.
Do not include secrets, private hostnames, private account IDs, or private URLs.

File tree

FAQ

dotai is a Claude Code plugin with 11 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes agent-native-reviewer, autogoal, hard-cut. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is dotai?: Shared skills for coding agents. Skills are the main routing layer. This repo is the canonical source for reusable udecode workflows; downstream repos should link to these skills instead of copying long SKILL.md files around.
How do I install dotai?: Run these in Claude Code: npx -y skills add udecode/dotai --agent claude-code. Then prompt normally.
Does dotai auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is dotai free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Is this plugin yours?

Claim it with GitHub Submit a plugin Promote it

dotai

udecode@udecode

GitHub

Plugin Signal73/100Solid

maintained92

capable52

documented75

adopted65

dotai

Shared skills for coding agents.

Skills are the main routing layer. This repo is the canonical source for reusable udecode workflows; downstream repos should link to these skills instead of copying long SKILL.md files around.

Included Skills

autogoal: durable goal lifecycle and seeded plan templates.

Deps: Codex goal tools (get_goal, create_goal, update_goal); optional orchestrator when $orchestrator on is active.

agent-native-reviewer: review whether agents can discover, perform, and verify the same meaningful actions as maintainers/users across skills, prompts, commands, generated mirrors, repo workflows, and product actions.

Deps: optional autogoal, sync-skills, sync-vision, resolve-pr-feedback, hard-cut, tdd, and diagnosing-bugs for routed follow-up work.

hard-cut: delete-first repo cleanup workflow.

linear-backlog: execute a scoped Linear queue as maximal safe parallel batches without asking for each next batch.

Deps: orchestrator, autogoal, repo-local task, Linear read/write tools, Git and PR tooling.

orchestrator: route implementation through durable child threads and disposable worktrees targeting main.

Deps: durable Codex thread and project tools; Git worktrees.

resolve-pr-feedback: GitHub PR review feedback closure with source-backed triage, proof, replies, and thread resolution.

Deps: gh, jq; optional project-owned docs/plans/templates/resolve-pr-feedback.md.

sync-vision: keep project root VISION.md current from changed human/agent inputs.

Deps: autogoal; optional project-owned docs/plans/templates/sync-vision.md.

tdd: test-first development loop.

unslop: draft, audit, and edit prose without AI-writing tells while preserving facts and voice.

Deps: optional Node.js for file and repo audits plus preservation checks.

video-transcripts: generate XML transcripts for tracker video evidence.

Deps: GEMINI_API_KEY or GOOGLE_API_KEY; curl, jq, file, and ffmpeg; optional gh for private GitHub attachments.

walkthrough: explain completed UI or rendered-output changes with concise annotated visuals from real final-state artifacts.

Deps: Git and Node.js for diff receipts; a repo-approved screenshot tool; imagegen or another safe image editor for annotations.

Quick Start

Install with the skills CLI:

npx skills add udecode/dotai

Validate

Run after edits:

scripts/validate-skills

Editing Rules

Keep descriptions short and useful for routing.

Keep skill bodies operational, not essay-like.

Prefer helper scripts for repeatable command logic.

Do not include secrets, private hostnames, private account IDs, or private URLs.