skills.rest
Kat4X
Kat4XCOMMUNITY
Explore all skills by this author →
GitHub

workflow-kit

Standardize AI-assisted software changes into Markdown artifacts with spec, plan, tasks, and verification files.

Updated May 27, 2026
Search Tags:#specification#verification#ai development#task planning#change management#scope control#markdown workflow
One-click install
npx skills add https://github.com/Kat4X/spec-kit --skill workflow-kit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workflow-kit
Source: https://github.com/Kat4X/spec-kit/tree/main/skill-drafts/workflow-kit
Command: npx skills add https://github.com/Kat4X/spec-kit --skill workflow-kit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prevents AI-driven development from going off-track by externalizing intent, scope, tasks, and verification into Markdown files so progress doesn’t disappear into chat memory.

Core Features & Use Cases

  • Artifact-first change workflow: moves work through specify → plan → tasks → implement → verify using persistent files.
  • Managed edit scope: enforces clear boundaries (what can change, what can’t) before implementation.
  • Spec/implementation separation: treats incorrect intent as a spec update and incorrect code as an implementation-fix task.

Quick Start

Ask the AI to produce a complete change workspace under ai/specs/YYYYMMDD_HHMM_change-name, including spec.md, plan.md, scope.md, tasks.md, and verification.md, while strictly keeping implementation details out of spec.md and only allowing edits inside the scope.

Frequently Asked Questions about workflow-kit

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

FAQPage Schema
How do I manage AI-assisted development scope so changes don't go off-track?▼

Externalize intent and boundaries into a persistent scope.md file before implementation to manage AI-assisted development scope. This enforces clear edit boundaries, preventing unbounded changes from disappearing into chat memory.

What is the Markdown workflow for standardizing iterative AI software changes?▼

The Markdown workflow for iterative AI software changes moves work through specify, plan, tasks, implement, and verify stages using persistent files. This creates verifiable artifacts for bounded changes, replacing transient chat memory.

How do I separate incorrect intent from incorrect code in AI task planning?▼

Treat incorrect intent as a spec.md update and incorrect code as an implementation-fix task to separate them during AI task planning. This maintains clear rules for updating specifications versus fixing code.

How do I generate a complete change workspace for AI task verification?▼

Ask the AI to create a directory containing spec.md, plan.md, scope.md, tasks.md, and verification.md to generate a complete change workspace for AI task verification. This ensures implementation details stay out of the spec.

Does this artifact-first workflow require any dependencies to manage change control?▼

No dependencies are required to use this artifact-first workflow for change control. It relies entirely on generating and managing standard Markdown files to externalize task verification and scope boundaries.

Related Skills

Explore More Software Engineering Skills→
oaustegardoaustegard
137

versioning-skills

Initialize Git repositories and commit changes for skill directories.

Community
Basic
corticalstackcorticalstack
1

validate-plan

Validate implementation plans against code changes and verification outcomes.

Community
Intermediate
m19803261706m19803261706

cx-fix

Investigate, fix, test, and commit code changes with conventional commits.

Community
Intermediate
LeandroBenjaminLLeandroBenjaminL

sdd-archive

Automate SDD cycle closure by merging delta specifications into main project specifications.

Community
Advanced