Automate LittlePea end-to-end autopilot workflows from spec to QA.
npx skills add https://github.com/daudaudinang/vibecode --skill lp-cook
Please help me install this Agent Skill. Skill: lp-cook Source: https://github.com/daudaudinang/vibecode/tree/main/.agents/skills/lp-cook Command: npx skills add https://github.com/daudaudinang/vibecode --skill lp-cook
Automates end-to-end autopilot workflows for LittlePea to execute the full pipeline from spec to QA.
Trigger the full canonical autopilot by saying 'lp-cook, start the full spec → plan → review → implement → QA pipeline'.
High-intent search queries and answers about installing and using this skill.
To automate an end-to-end pipeline from specification to QA, you need a canonical orchestration workflow that directs the sequence of planning, review, implementation, and verification. This autopilot pipeline maintains state tracking and artifact generation while applying safe guardrails for deterministic execution.
A canonical autopilot workflow orchestrates the full development lifecycle sequence: spec, plan, review, implement, review, and QA. It directs this canonical sequence with deterministic execution, state tracking, and human gates at blockers to ensure safe and reliable delivery.
Executing a full spec to QA pipeline with human gates requires triggering an autopilot orchestration that directs the canonical sequence. The workflow maintains state and artifacts, pausing for human-in-the-loop review only when blockers are encountered during implementation.
Yes, deterministic execution and state tracking are supported for feature delivery automation. The autopilot pipeline maintains state and generates artifacts throughout the specification, planning, review, implementation, and QA phases, enabling deterministic retries and safe guardrails.
The best way to orchestrate a development pipeline with safe guardrails is using a canonical autopilot that directs the sequence from spec to QA. It enforces safe guardrails by maintaining state, generating artifacts, and enabling deterministic retries with human gates at blockers.
Human-in-the-loop gates are used in an automated workflow pipeline to provide safe guardrails at blockers during the canonical sequence. While the autopilot handles deterministic execution from spec to QA, these human gates ensure safe intervention when the workflow encounters blockers.
babywormOrchestrate the RTL design pipeline from specification to verification.
PantaniOrchestrate a four-agent pipeline for tdmcp Connectors Directory submissions.
leeoveryValidate and route discussion artifacts into standalone specifications.
ellisapotheosisOrchestrate SPARC-driven multi-agent software development across specification, architecture, refinement, and completion.
