From outputai
Orchestrates the full planning process for creating new Output.ai workflows, including architecture, steps, prompts, evaluators, and testing strategy using specialized subagents.
How this skill is triggered — by the user, by Claude, or both
Slash command
/outputai:output-plan-workflowopusThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Your task is to generate a comprehensive Output.ai workflow implementation plan in markdown format.
Your task is to generate a comprehensive Output.ai workflow implementation plan in markdown format.
The plan will be displayed to the user who can then decide what to do with it.
Please respond with only the final version of the plan.
Use the todo tool to track your progress through the plan creation process.
Generate detailed specifications for implementation of a new workflow.
All plan outputs go to: .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md
<process_flow>
Analyze the arguments provided to the command:
{ $ARGUMENTS }
Ensure they have provided:
If not, ask the user for the missing information.
EXECUTE: Claude Skill: `output-meta-pre-flight`Take the time to gather all the context you need to create a comprehensive plan.
Clarify scope boundaries and technical considerations by asking numbered questions as needed to ensure clear requirements before proceeding.
<clarification_areas> - in_scope: what is included - out_of_scope: what is excluded (optional) - functionality specifics - UI/UX requirements - integration points <llm_provider> - Ask which LLM provider the user wants to use (anthropic, openai, or vertex) - Default to anthropic if the user has no preference - All prompt files in the workflow must use the same provider unless the user explicitly requests otherwise - Record the chosen provider so it flows through to prompt engineering (step 6) and implementation </llm_provider> </clarification_areas>
<decision_tree> IF clarification_needed: ASK numbered_questions WAIT for_user_response ELSE: PROCEED schema_definition </decision_tree>
Design the workflow with clear single purpose steps and sound orchestration logic.
<thought_process>
</thought_process>
<step_output> Output Draft Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Design the individual steps called by the workflow with clear boundaries.
<thought_process>
<step_output> Output Updated Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Determine if the workflow requires quality assessment, validation, or content evaluation.
<decision_tree> IF workflow_outputs_need_quality_scoring: DESIGN evaluator functions IF workflow_has_llm_generated_content: CONSIDER content evaluation (factual accuracy, relevance, tone) IF workflow_requires_validation_with_confidence: DESIGN validation evaluators ELSE: SKIP evaluator design (note in plan: "No evaluators needed") </decision_tree>
<thought_process>
@outputai/evals be appropriate for dataset-driven verification?
</thought_process><step_output> Output Updated Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Review the draft plan and make any necessary changes.
<thought_process>
<decision_tree> IF changes_needed: UPDATE draft_plan ELSE: PROCEED to step 6 </decision_tree>
<step_output> Output Reviewed Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
If any of the steps use an LLM, design the prompts for the steps.
<decision_tree> IF step_uses_llm: USE prompt_step_template ELSE: SKIP to step 7 </decision_tree>
<step_output> Output Updated Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Design the testing strategy for the workflow.
<thought_process>
output workflow test?<step_output> Output Updated Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Generate the complete plan in markdown format.
Note that every implementation should start with running the cli command npx output workflow generate --skeleton to create the workflow directory structure.
<file_template>
# Workflow Requirements Document> Workflow: [WORKFLOW_NAME]
> Created: [CURRENT_DATE]
- Overview
- Spec Scope
- Out of Scope
- Workflow Design
- Step Design
- Evaluator Design (if applicable)
- Prompt Design
- Testing Strategy
- Implementation Phases
<step_output> Output Final Plan: to .outputai/plans/YYYY_MM_DD_<workflow_name>_<task_name>/PLAN.md </step_output>
Verify the plan is complete and ready for implementation.
EXECUTE: Claude Skill: `output-meta-post-flight`Then instruct the user to:
/output-build-workflow <plan_file_path> <workflow_name> <workflow_directory></process_flow>
---- START ----
Workflow Description and Additional Instructions:
$ARGUMENTS
npx claudepluginhub growthxai/output --plugin outputaiImplements an Output SDK workflow from a plan document. Invoke when the user asks to build a workflow from an existing plan or after `output-plan-workflow` has produced a plan.
Composes valid looplia v0.7.0 workflow YAML/Markdown files from skill recommendations and user preferences. Final step for /build commands, workflow creation, or automation pipelines.
Designs multi-step agentic workflows with analyze-plan-validate-execute-verify to prevent irreversible mistakes in LLM agents.