Catalogue › Automation

CopilotForge - Automation

Use it in Copilot Cowork: download the Automation plugin for Copilot Cowork and upload it under Customize > Plugins > Upload plugin. How to install.

Combine AI with deterministic workflow automation where repeatability and integration matter.

Layer: delivery
Lead role: Automation Lead
Plugin name: copilotforge-automation

Skill Status Lifecycle Description

automation-assessment draft Discover, Envision, Deliver Assesses a process put forward for automation step by step - volume, stability, input structure, rules, exceptions and systems - and decides which steps suit a deterministic flow, which genuinely need an AI step, which need a desktop flow and which should stay human. Use when a team asks to automate a process, when an automation request already assumes AI, or when several automation candidates need consistent treatment.

automation-connector-governance draft Deliver, Assure, Launch, Improve Applies connector and data policy governance to individual automations in delivery - which connectors a flow may use in its environment, whose connections run it, custom connectors and AI services, and how a maker requests and justifies an exception. Use when a flow needs a connector its environment blocks, when production flows run on personal connections, or before an automation moves to production.

automation-monitoring draft Deliver, Launch, Measure, Improve Designs monitoring for an individual automation before hand-over - run failures, missing runs against expected volume, exception queue ageing, AI step quality signals such as low confidence and human override rates, connection expiry - and routes each alert to a named owner. Use when an automation is about to go live, when flows stop without anyone noticing, or when an owner asks what to watch.

automation-process-design draft Envision, Deliver Redesigns a business process before it is automated - removing waste, standardising inputs, writing down decision rules, defining exceptions and owners - and produces a future-state design that marks each step as human, flow, AI or desktop flow. Use when an assessment says a process is not ready to automate, when teams run the same process differently, or before build starts on any automation with AI steps.

automation-value draft Measure, Scale, Improve Measures the value an automation delivers against its baseline - cycle time, handling effort, errors and rework, throughput - net of human review, exception handling, run cost and support, and reports it to the process owner without counting runs as value. Use when an automation goes live, when a sponsor asks what an automation saved, or when deciding whether to extend, fix or retire it.

desktop-automation draft Deliver, Assure, Improve Decides when desktop flows that drive a user interface are justified for legacy systems with no connector or API, and sets the conditions for using them with care - attended or unattended runs, machines, credentials, fragile selectors, AI on screen content, ownership and an exit plan. Use when a step can only be done through a screen, when desktop flows keep breaking after updates, or when unattended runs are proposed.

exception-handling draft Deliver, Assure, Improve Designs how an automation with AI steps handles what goes wrong - transient failures and retries, permanent technical faults, business exceptions, invalid or low-confidence AI output, content filtering and partial runs - so every failure is caught, routed to an owner and recoverable. Use when building an automation, when flows fail silently or leave half-finished work, or when exception queues grow without an owner.

flow-design-patterns draft Deliver, Assure, Improve Sets the build patterns for robust Power Automate cloud flows that include AI steps - triggers, solution-aware structure, connection references, environment variables, structured AI outputs validated before use, idempotency, concurrency and error scopes. Use when a maker starts building an approved automation design, when a flow with an AI step is fragile, or when the CoE needs standard flow patterns.

human-in-the-loop draft Deliver, Assure, Improve Designs the human approval and review steps inside an automation - where a person checks AI output before it takes effect, what they see, how long they have, who covers absence, and how to stop reviews becoming rubber stamps. Use when an automated flow acts on AI output, when approvals sit unanswered or are approved without reading, or when a reviewer asks what checks an automation needs.

Skill	Status	Lifecycle	Description
`automation-assessment`	draft	Discover, Envision, Deliver	Assesses a process put forward for automation step by step - volume, stability, input structure, rules, exceptions and systems - and decides which steps suit a deterministic flow, which genuinely need an AI step, which need a desktop flow and which should stay human. Use when a team asks to automate a process, when an automation request already assumes AI, or when several automation candidates need consistent treatment.
`automation-connector-governance`	draft	Deliver, Assure, Launch, Improve	Applies connector and data policy governance to individual automations in delivery - which connectors a flow may use in its environment, whose connections run it, custom connectors and AI services, and how a maker requests and justifies an exception. Use when a flow needs a connector its environment blocks, when production flows run on personal connections, or before an automation moves to production.
`automation-monitoring`	draft	Deliver, Launch, Measure, Improve	Designs monitoring for an individual automation before hand-over - run failures, missing runs against expected volume, exception queue ageing, AI step quality signals such as low confidence and human override rates, connection expiry - and routes each alert to a named owner. Use when an automation is about to go live, when flows stop without anyone noticing, or when an owner asks what to watch.
`automation-process-design`	draft	Envision, Deliver	Redesigns a business process before it is automated - removing waste, standardising inputs, writing down decision rules, defining exceptions and owners - and produces a future-state design that marks each step as human, flow, AI or desktop flow. Use when an assessment says a process is not ready to automate, when teams run the same process differently, or before build starts on any automation with AI steps.
`automation-value`	draft	Measure, Scale, Improve	Measures the value an automation delivers against its baseline - cycle time, handling effort, errors and rework, throughput - net of human review, exception handling, run cost and support, and reports it to the process owner without counting runs as value. Use when an automation goes live, when a sponsor asks what an automation saved, or when deciding whether to extend, fix or retire it.
`desktop-automation`	draft	Deliver, Assure, Improve	Decides when desktop flows that drive a user interface are justified for legacy systems with no connector or API, and sets the conditions for using them with care - attended or unattended runs, machines, credentials, fragile selectors, AI on screen content, ownership and an exit plan. Use when a step can only be done through a screen, when desktop flows keep breaking after updates, or when unattended runs are proposed.
`exception-handling`	draft	Deliver, Assure, Improve	Designs how an automation with AI steps handles what goes wrong - transient failures and retries, permanent technical faults, business exceptions, invalid or low-confidence AI output, content filtering and partial runs - so every failure is caught, routed to an owner and recoverable. Use when building an automation, when flows fail silently or leave half-finished work, or when exception queues grow without an owner.
`flow-design-patterns`	draft	Deliver, Assure, Improve	Sets the build patterns for robust Power Automate cloud flows that include AI steps - triggers, solution-aware structure, connection references, environment variables, structured AI outputs validated before use, idempotency, concurrency and error scopes. Use when a maker starts building an approved automation design, when a flow with an AI step is fragile, or when the CoE needs standard flow patterns.
`human-in-the-loop`	draft	Deliver, Assure, Improve	Designs the human approval and review steps inside an automation - where a person checks AI output before it takes effect, what they see, how long they have, who covers absence, and how to stop reviews becoming rubber stamps. Use when an automated flow acts on AI output, when approvals sit unanswered or are approved without reading, or when a reviewer asks what checks an automation needs.

Credit

Created by Simon Foote as part of CopilotForge. Content is licensed under CC BY 4.0; keep the credit in each skill's license and authors fields when you share or adapt it. See NOTICE.md in the repository.