---
title: "vibe-spec"
description: "vibe-spec is an Agent Plugin published by yuntan. It packages 8 skills. We fetched the plugin.json from GitHub on 2026-10-08 and checked it against the official Agent Plugins 1.0.0 schema."
canonical: https://agentpluginsdirectory.com/plugins/vibe-spec
last-updated: 2026-10-08
---

# vibe-spec
vibe-spec is an Agent Plugin published by yuntan. It packages 8 skills. We fetched the plugin.json from GitHub on 2026-10-08 and checked it against the official Agent Plugins 1.0.0 schema.
- Slug: vibe-spec
- Publisher: yuntan
- Repository: https://github.com/yuntan/vibe-spec
- Manifest: plugin.json
- Category (editorial): other
- Skills: 8 (build, code-review-and-quality, debugging-and-error-recovery, doubt-driven-development, incremental-implementation, planning-and-task-breakdown, spec, test-driven-development)
- MCP servers: 0
- Stars: 0
- Repository created: 2026-08-05
- Repository last pushed: 2026-08-24
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/vibe-spec
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What vibe-spec does, in the publisher's words

A Claude Code plugin for spec-driven development. Write the spec, then let the agent break it into tasks and build them. Tests first, one commit per task, reviewed as it goes.

Two commands, two phases:

All commands are user-invoked only. Claude will not enter a phase on its own.

- One gate, at the spec. Everything downstream is derived from it.
- Speed is the point. A gate that catches nothing is pure latency.
- Build the whole thing at once. Rollback is git revert, not your attention.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/yuntan/vibe-spec/HEAD/README.md

## Skills

- build: Break a spec into tasks and implement them incrementally, plan, build, test, verify, commit.
- code-review-and-quality: Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
- debugging-and-error-recovery: Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
- doubt-driven-development: Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be ch…
- incremental-implementation: Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
- planning-and-task-breakdown: Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
- spec: Write or update the specification under spec/, the first phase of the Spec -> Build workflow.
- test-driven-development: Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.