From outputai
Performs pre-flight validation for Output SDK workflows, enforcing conventions like ES modules and wrappers, gathering requirements, and passing quality gates before execution.
How this skill is triggered — by the user, by Claude, or both
Slash command
/outputai:output-meta-pre-flightThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
- **CRITICAL**: For any step that specifies a subagent in the `subagent=""` XML attribute, you MUST use the specified subagent to perform the instructions for that step
subagent="" XML attribute, you MUST use the specified subagent to perform the instructions for that stepEnsure you have a deep understanding of the Output SDK and its capabilities. If not, use Claude Skill: output-meta-project-context and read it carefully.
Before proceeding with any workflow operation, verify:
.js extension for ESM modulesovermind restart workeryarn g:workflow-doc after modificationsWhen information is not explicitly provided, apply these defaults:
gpt-5 unless specified otherwiseOnly stop to ask for clarification on:
Before proceeding past pre-flight:
.outputai/plans directory does not exist, create it.npx claudepluginhub growthxai/output --plugin outputaiValidates Output SDK workflow operations post-execution: audits step completion, enforces conventions like TypeScript imports and Temporal activities, checks plan quality, and verifies deliverables.
Authors a reusable, deterministic agent orchestration workflow as a self-contained .mjs script for Claude Code's Workflow tool, with structured phases, fan-out, and verification.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.