spec-driven — spec-driven install for AI agents spec-driven, Coherence-Network, community, spec-driven install for AI agents, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Development Agents requiring precise implementation of specifications, adhering to strict guidelines and modifying only listed files. spec-driven is a development approach that involves reading and implementing specifications precisely, without adding extra features or refactoring adjacent code.

Features

Implements specifications according to the 'Files to Create/Modify' section
Modifies only listed files, as referenced in the spec
Does not change tests, focusing on fixing implementation instead
Follows a strict 'read the spec' and 'implement only what it says' approach
Supports adherence to constraints, such as not adding docs or READMEs unless required
Enforces a disciplined development workflow, reducing unnecessary changes

# Core Topics

seeker71 seeker71
[0]
[0]
Updated: 3/3/2026

Agent Capability Analysis

The spec-driven skill by seeker71 is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for spec-driven install for AI agents.

Ideal Agent Persona

Ideal for Development Agents requiring precise implementation of specifications, adhering to strict guidelines and modifying only listed files.

Core Value

Empowers agents to accurately implement specifications by following strict guidelines, modifying only listed files, and preserving existing tests, ensuring compliance with protocols like MD file references and task specifications.

Capabilities Granted for spec-driven

Implementing feature updates according to spec
Modifying listed files without altering tests
Adhering to strict implementation guidelines for development projects

! Prerequisites & Limits

  • Requires access to spec files (e.g., specs/NNN-feature-name.md)
  • Limited to modifying files listed in the spec's 'Files to Create/Modify' section
  • No addition of docs, READMEs, or refactors unless specified
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

spec-driven

Install spec-driven, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Spec-Driven Implementation

Quick Start

  1. Read the specspecs/NNN-feature-name.md or the spec referenced in the task
  2. Implement only what it says — no extra features, no adjacent refactors
  3. Modify only listed files — see "Files to Create/Modify" in the spec
  4. Do not change tests — fix implementation, not tests

Constraints

  • Only modify files listed in the spec's "Files to Create/Modify" section
  • Do not add docs, READMEs, or refactors unless the spec requires them
  • Only escalate with needs_decision when truly stuck after research; prefer fixing in-scope
  • Follow API Contract and Data Model from the spec exactly

Spec Format Reference

Specs follow specs/TEMPLATE.md:

  • Purpose, Requirements, API Contract, Data Model
  • Files to Create/Modify (the allowed set)
  • Acceptance Tests, Out of Scope, Decision Gates

When Tests Fail

Fix the implementation. Do NOT modify tests to make them pass.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is spec-driven?

Ideal for Development Agents requiring precise implementation of specifications, adhering to strict guidelines and modifying only listed files. spec-driven is a development approach that involves reading and implementing specifications precisely, without adding extra features or refactoring adjacent code.

How do I install spec-driven?

Run the command: npx killer-skills add seeker71/Coherence-Network/spec-driven. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for spec-driven?

Key use cases include: Implementing feature updates according to spec, Modifying listed files without altering tests, Adhering to strict implementation guidelines for development projects.

Which IDEs are compatible with spec-driven?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for spec-driven?

Requires access to spec files (e.g., specs/NNN-feature-name.md). Limited to modifying files listed in the spec's 'Files to Create/Modify' section. No addition of docs, READMEs, or refactors unless specified.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add seeker71/Coherence-Network/spec-driven. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use spec-driven immediately in the current project.

Related Skills

Looking for an alternative to spec-driven or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI