skills.rest
aicodepro
aicodeproOFFICIAL
Explore all skills by this author →
GitHub

spec

Convert vague feature intent into a precise, executable specification and GitHub issue.

Updated Jun 22, 2026
Search Tags:#planning#specification#backlog#spec#ticketing#github issue#gstack
One-click install
npx skills add https://github.com/aicodepro/ai-agent-nexi --skill spec-aicodepro
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spec
Source: https://github.com/aicodepro/ai-agent-nexi/tree/main/agent/skills/gstack/spec
Command: npx skills add https://github.com/aicodepro/ai-agent-nexi --skill spec-aicodepro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Turning a rough idea or verbal request into a well-structured, backlog-ready specification is slow and inconsistent. This Skill guides the user through a five-phase process that transforms vague intent into a precise, executable spec, files it as a GitHub issue, and optionally spawns a Claude Code agent in a fresh worktree so /ship can close the source issue on merge. ## Core Features & Use Cases - Five-phase spec workflow: Walks the user from raw intent to a complete, executable specification with structured decision points. - GitHub issue filing: Files the resulting spec as an issue and integrates with /ship so the source issue closes automatically on merge. - Agent spawning: Optionally launches a Claude Code agent in a fresh git worktree to execute the spec. - Use Case: A user says "spec out the new onboarding flow" — the Skill interviews them with structured decision briefs, produces the spec, files it as a GitHub issue, and hands it off for implementation. ## Quick Start Ask the assistant to turn this feature idea into a spec and file it as a GitHub issue using the spec skill.

Frequently Asked Questions about spec

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn a feature idea into a GitHub issue?▼

Invoke the spec skill with your idea, and it walks you through a five-phase workflow that produces a precise specification and files it as a GitHub issue. The /ship command can then close the source issue automatically when the work merges.

How to write a backlog-ready engineering spec with AI?▼

The spec skill converts vague intent into an executable spec using structured decision briefs that clarify scope, tradeoffs, and requirements. It then files the result as an issue and can spawn a Claude Code agent in a fresh worktree to implement it.

Does the spec skill work in plan mode or headless sessions?▼

Yes, it detects plan mode, headless, spawned, and interactive session kinds in its preamble and adapts behavior accordingly. In headless sessions it blocks when a question cannot be answered; in spawned sessions it auto-chooses recommended options.

What happens if AskUserQuestion is unavailable during spec creation?▼

The skill falls back based on session kind: spawned sessions auto-choose the recommended option, headless sessions stop as blocked, and interactive sessions render the decision brief as prose and wait for a typed reply.

When should I not use the spec skill?▼

Skip it for trivial changes that need no specification, or when proactive skill invocation is disabled in gstack config. It is designed for backlog-worthy work items, not quick fixes or one-line changes.

Related Skills

Explore More Product & Management Skills→
robotics-playgroundrobotics-playground

bmad-product-brief-preview

Orchestrate structured discovery to draft an executive product brief.

Official
Advanced
Sassy-DogSassy-Dog

take-it

Ships GitHub issues in parallel via worktree sub-agents that open and merge PRs.

Official
Advanced
csackridercsackrider

agent-learn

Capture post-feature and post-incident learnings into PROJECT.md, ADRs, and Tech Specs.

Community
Advanced
automatedigitalautomatedigital
1

tasker

Automate ticket lifecycle from ideation to merged pull request across ticket trackers and GitHub.

Official
Advanced