Building a feature from approved plans is easier when the plans stay accurate. This skill helps you implement a feature based on two documents: PRODUCT.md and TECH.md. These specs are checked into the repository under a ticket folder like specs/APP-1234.
You keep the specs and code aligned as you work. All changes go into the same pull request. This makes review simple because the PR shows the feature that will actually ship. Update the specs immediately when decisions change during implementation.
Before starting, make sure the specs are approved. Then plan, code, test, and verify against the specs. Use optional tracking documents only for complex features. The goal is a coherent feature with up-to-date documentation.
Global
mkdir -p ~/.claude/skills/implement-specsProject
mkdir -p .claude/skills/implement-specsSource Repository
Find Skillsvercel-labs/skills
Find and install the perfect skill to extend your AI agent
Microsoft Foundrymicrosoft/azure-skills
Build, deploy, and improve AI agents on Microsoft Foundry from start to finish
Azure Aimicrosoft/azure-skills
Search, transcribe, and analyze with Azure AI tools for smarter apps
Azure Hosted Copilot Sdkmicrosoft/azure-skills
Build, deploy, and manage your Copilot SDK apps on Azure with ease
Triagemattpocock/skills
Triage issues with a state machine driven by clear roles and agent briefs
Handoffmattpocock/skills
Hand off your work to another AI agent with a clear summary
Image Editagentspace-so/runcomfy-agent-skills
Smart router picks the best AI model for your image editing needs
Agentspaceagentspace-so/skills
See your AI agent's live folder from any browser instantly