Marketplace for trusted AI agent skills

Skill Detail

Run Claude Code with spec-driven quality gates via Pilot Shell

Wrap Claude Code sessions in a spec, approval, and verification workflow before risky implementation work lands.

Templates & WorkflowsClaude Code
Templates & Workflows Claude Code Security Reviewed
⭐ 1.6k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill run-claude-code-with-spec-driven-quality-gates-via-pilot-shell Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
Claude Code, curl, bash, macOS/Linux/WSL2
Install & setup
Install with curl -fsSL https://raw.githubusercontent.com/maxritter/pilot-shell/main/install.sh | bash, then enter a project and run pilot or ccp to start a spec-driven Claude Code session.
Author
Max Ritter
Publisher
Individual
Last updated
Apr 17, 2026
Quick brief

Use Pilot Shell when Claude Code work needs a spec, approval gate, and verification loop before edits land. Invoke it instead of vanilla Claude Code when the task is planned implementation with enforced checkpoints, not quick ad hoc prompting. The scope boundary is clear enough to publish: this is a Claude Code workflow harness for spec-driven sessions, not a generic coding agent platform or IDE listing.