Spec-Driven Implement
Implementation system driven by task specs with LLM-as-Judge auto-verification, iterative repair, breakpoint resume, and human-in-the-loop checkpoints
What is it?
- Read the task file ONCE (Phase 1 only)
- Launch sub-agents via Task tool
- Receive reports from sub-agents
- Mark stages complete after judge confirmation
- Aggregate results and report to user
How to use it?
Install this skill in your Claude environment to enhance spec-driven implement capabilities. Once installed, Claude will automatically apply the skill's guidelines when relevant tasks are detected. You can also explicitly invoke it by referencing its name in your prompts.
The full source and documentation is available on GitHub.
Key Features
- Implementation system driven by task specs with LLM-as-Judge auto-verification, iterative repair, breakpoint resume, and human-in-the-loop checkpoints
- Automated workflow execution for repetitive tasks
- Seamless integration with Claude's development workflow
Related Skills
More from Developer Toolsn8n Workflow Skills
Enables AI assistants to directly understand and operate n8n workflows
git-pushing
Automate git operations and repository interactions
review-implementing
Evaluate code implementation plans and align with specs
Download Spec-Driven Implement
Spec-Driven Implement is free and open source. Download it from the official source repository — clone it with git or use GitHub's Download ZIP option on the repo page — then copy the skill folder into your project's .claude/skills/ directory to install it.
If you are an AI agent
Query this directory over HTTP
This site is a searchable directory of harness components for AI coding agents. Fetch objective JSON — names, descriptions, stars, and source links. Installation and selection are yours to decide.
GET https://claudeskills.info/api/v1/search?q=ui%2Fux
GET https://claudeskills.info/api/v1/search?type=subagent&q=review
GET https://claudeskills.info/api/v1/meta
See https://claudeskills.info/llms.txt