This skill should be used when the user wants to analyze AI workflow opportunities, run a workflow audit, find automation candidates, or says "where can AI help". Scans memory and conversation history, interviews the user about their work, then produces a prioritized opportunity report with structured workflow candidates ready for the Deconstruct step. This is Step 1 of the AI Workflow Framework.
This skill should be used when the user has an approved Design Spec and wants to build platform artifacts for their AI workflow. It offers a build path choice, researches integration availability, generates platform-appropriate artifacts (prompts, skills, agents, configs), and writes them to the right locations for the user's platform. Also use when the user says "continue my workflow" and the workflow manifest shows Step 4 (Build) is next. This is Step 4 (Build) of the AI Workflow Framework.
This skill should be used when the user wants to deconstruct a workflow, break down a business process, capture requirements for an AI workflow, or define a goal for an agent system. Step 2 is the PRD for the workflow — it captures what the workflow must do, the rules it must follow, and the edge cases it must handle, in clear requirements language suitable for the Design step or any AI model to consume. Supports two paths: step-driven (you know how the work gets done) and goal-driven (you know what "done" looks like and want an agent system to determine the path). Produces a structured Workflow Requirements document. Also use when the user says "continue my workflow" and the workflow manifest shows Step 2 (Deconstruct) is next. This is Step 2 of the AI Workflow Framework.
This skill should be used when the user has a Workflow Requirements document and wants to design an AI workflow. It gathers architecture decisions, assesses workflow autonomy level, chooses an orchestration mechanism and involvement mode, classifies steps, maps building blocks, identifies skill candidates, configures agents, and produces a Design Spec for approval. Supports both step-driven and goal-driven Workflow Requirements. Also use when the user says "continue my workflow" and the workflow manifest shows Step 3 (Design) is next. This is Step 3 (Design) of the AI Workflow Framework.
Evaluate a running AI workflow for quality, relevance, and evolution opportunities. Use when the user wants to review how a deployed workflow is performing, check if it needs tuning, or assess whether it should graduate to a more capable orchestration mechanism. Also use when the user says "continue my workflow" and the workflow manifest shows Step 7 (Improve) is next, or the manifest next_review date has arrived. This is Step 7 (Improve) of the AI Workflow Framework.
This skill should be used when the user wants to generate or refresh their AI Registry — the REGISTRY.md index of skills, agents, workflows, business processes, and apps at the workspace root. Triggers when the user asks to "update my registry", "regenerate the index", "what have I built", "show my AI inventory", after creating skills or agents, or when another framework skill's closing step calls for a registry refresh. Also handles the optional Notion mirror: "register this skill/agent/workflow/process in Notion", "add this to my Notion registry", "update this workflow in Notion", "mirror my registry to Notion", "what's in my Notion registry". Also use to repair a stale or hand-edited REGISTRY.md, or to migrate from a Notion-based registry.
This skill should be used when the user wants to name a workflow, write workflow descriptions, standardize workflow documentation, add a workflow to the AI Registry, or structure workflow entries. Generates consistent, outcome-focused names and descriptions for business workflows and records them in the workflow's manifest (workflow.yaml).
This skill should be used when the user has built and tested workflow artifacts and wants a Run Guide for deploying and operating their AI workflow. It generates a plain-language guide with setup steps, deployment patterns, and sharing instructions — tailored to the user's platform and build path. Also use when the user says "continue my workflow" and the workflow manifest shows Step 6 (Run) is next. This is Step 6 (Run) of the AI Workflow Framework.