Catalogue › Copilot Studio

CopilotForge - Copilot Studio

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

Design and deliver low-code and enterprise agents with appropriate actions, data, ALM and lifecycle controls.

Layer: delivery
Lead role: Copilot Studio Architect
Plugin name: copilotforge-copilot-studio

Skill Status Lifecycle Description

conversation-design draft Deliver, Improve Designs how a Copilot Studio agent talks to people - greeting and AI disclosure, tone, clarifying questions, confirmations, error and fallback messages, escalation and live-agent hand-off with context, and ending a conversation well - so exchanges are short, honest and recoverable. Use when writing an agent's conversational behaviour, when users abandon or go round in loops, or when a hand-off to people needs designing.

dataverse-integration draft Deliver, Assure Designs how a Copilot Studio agent works with Dataverse - tables as knowledge for questions about business records, reads and writes through tools, and the agent's own configuration and conversation data - covering table and column selection, security roles, capacity questions and environment placement. Use when an agent must answer from or update Dataverse records, or when agent data storage needs planning.

multi-agent-design draft Envision, Deliver, Scale Designs Copilot Studio solutions in which agents work together - child agents, connected agents reused across teams and calls to agents on other Microsoft platforms - deciding when to split, how the parent routes and passes context, which identity each uses, who owns each and how failures are contained. Use when one agent has grown too broad, when teams want to reuse each other's agents, or when an agent must hand work to another.

power-automate-actions draft Deliver, Assure Designs Power Automate flows that a Copilot Studio agent calls as tools - when a flow is the right action, its input and output contract, response time within a conversation, the identity it runs under, error returns the agent can explain, solution packaging and flow ownership. Use when an agent needs a multi-step or cross-system action, when a flow called by an agent times out or fails silently, or when a maker wants to reuse an existing flow.

studio-actions-and-tools draft Deliver, Assure Designs the tools a Copilot Studio agent can call - connector actions, agent flows, prompts, custom connectors, REST APIs and MCP servers - with names and descriptions the orchestrator can use, typed inputs and outputs, read versus write, user confirmation, identity and failure behaviour. Use when an agent must do more than answer, when it calls the wrong tool or fills inputs badly, or when a write action needs safeguards.

studio-agent-design draft Envision, Deliver Turns an agreed agent brief into a Copilot Studio solution design - orchestration approach, topics, knowledge, tools and flows, authentication, channels, environment and solution packaging, and the run model - recording each design decision with the alternatives rejected. Use when a brief has chosen Copilot Studio, when a maker is about to build without a design, or when a growing agent needs its architecture reset.

studio-agent-lifecycle draft Launch, Measure, Scale, Improve Keeps the technical estate of Copilot Studio agents healthy from creation to retirement - owners and co-owners, orphaned, inactive or duplicate agents, periodic recertification, Microsoft platform changes, and retiring an agent with its flows, connections, environment variables and stored data. Use when the number of Studio agents is growing, when a maker leaves, or when an agent has gone unused for months.

studio-alm draft Mobilise, Deliver, Launch, Improve Sets application lifecycle management for Copilot Studio agents - solutions and publishers, environment variables and connection references, source control, pipelines between development, test and production, managed versus unmanaged imports, versioning, change control and rollback. Use when an agent must move beyond one environment, when changes are made directly in production, or when several makers work on the same agent.

studio-analytics draft Measure, Improve Uses Copilot Studio analytics and conversation records to improve a live agent - sessions, outcomes such as resolved, escalated and abandoned, unanswered questions, knowledge and tool use, satisfaction and recurring themes - through a regular improvement review at aggregate level that turns findings into prioritised fixes. Use when an agent is live and its owner asks how it is doing, when resolution falls, or when deciding what to fix next.

studio-authentication draft Deliver, Assure Designs how a Copilot Studio agent knows who the user is and whose identity it uses - the agent's authentication setting, Microsoft Entra sign-in or another identity provider, single sign-on per channel, end-user versus maker or service credentials for knowledge and tools, and anonymous use. Use when choosing an agent's authentication setting, when users are asked to sign in repeatedly, or when an action runs as the maker.

studio-connectors draft Deliver, Assure Chooses the connectors a Copilot Studio agent depends on - prebuilt, certified or custom - and governs their use in the agent through connection references, the account each connection runs under, data policy grouping, ownership of custom connectors and their change control. Use when a maker needs a connector the agent does not yet use, when a custom connector is proposed, or when a data policy blocks an agent.

studio-deployment draft Launch, Scale Publishes a released Copilot Studio agent to its channels - Teams and Microsoft 365 Copilot, websites, custom apps and others - configuring per-channel authentication, sharing to the approved audience, admin approval and availability, channel-specific behaviour and a staged rollout with a rollback route. Use when an agent has passed its release gate, when it is being added to a new channel, or when users cannot find or open it.

studio-environments draft Mobilise, Deliver, Scale Applies the organisation's environment strategy to Copilot Studio work - the concrete personal, team, test and production environments makers use, environment routing for new makers, Managed Environment and agent settings per zone, security groups, data policies and how agents move between zones. Use when makers start building agents, when agents pile up in the default environment, or when a team asks for its own development space.

studio-knowledge-architecture draft Deliver, Improve Designs the knowledge layer of a Copilot Studio agent - which ready sources to connect and by which knowledge type, how each is scoped, described and permission-trimmed, whether content is live or uploaded, how answers cite sources and how the layer is refreshed and owned. Use when connecting knowledge to a Studio agent, when answers come from the wrong source, or when a maker wants to upload copies of documents.

studio-testing-and-evaluation draft Deliver, Assure, Improve Plans layered testing of a Copilot Studio agent - topic paths, orchestration choices, knowledge answers, tool and flow calls, authentication per channel, failure handling and regression after change - using the authoring test tools, repeatable evaluation sets and owner-agreed thresholds in a test environment. Use when a Studio agent with tools, topics or several sources needs testing, or when a change must be regression-tested.

topics-and-orchestration draft Deliver, Improve Designs how a Copilot Studio agent decides what to do - which requests generative orchestration handles from the descriptions of knowledge, tools, topics and child agents, which need authored topics with fixed steps, and how triggers, variables, system topics and redirects fit together. Use when planning an agent's topics, when it picks the wrong topic or tool, or when authored topics keep multiplying.

Skill	Status	Lifecycle	Description
`conversation-design`	draft	Deliver, Improve	Designs how a Copilot Studio agent talks to people - greeting and AI disclosure, tone, clarifying questions, confirmations, error and fallback messages, escalation and live-agent hand-off with context, and ending a conversation well - so exchanges are short, honest and recoverable. Use when writing an agent's conversational behaviour, when users abandon or go round in loops, or when a hand-off to people needs designing.
`dataverse-integration`	draft	Deliver, Assure	Designs how a Copilot Studio agent works with Dataverse - tables as knowledge for questions about business records, reads and writes through tools, and the agent's own configuration and conversation data - covering table and column selection, security roles, capacity questions and environment placement. Use when an agent must answer from or update Dataverse records, or when agent data storage needs planning.
`multi-agent-design`	draft	Envision, Deliver, Scale	Designs Copilot Studio solutions in which agents work together - child agents, connected agents reused across teams and calls to agents on other Microsoft platforms - deciding when to split, how the parent routes and passes context, which identity each uses, who owns each and how failures are contained. Use when one agent has grown too broad, when teams want to reuse each other's agents, or when an agent must hand work to another.
`power-automate-actions`	draft	Deliver, Assure	Designs Power Automate flows that a Copilot Studio agent calls as tools - when a flow is the right action, its input and output contract, response time within a conversation, the identity it runs under, error returns the agent can explain, solution packaging and flow ownership. Use when an agent needs a multi-step or cross-system action, when a flow called by an agent times out or fails silently, or when a maker wants to reuse an existing flow.
`studio-actions-and-tools`	draft	Deliver, Assure	Designs the tools a Copilot Studio agent can call - connector actions, agent flows, prompts, custom connectors, REST APIs and MCP servers - with names and descriptions the orchestrator can use, typed inputs and outputs, read versus write, user confirmation, identity and failure behaviour. Use when an agent must do more than answer, when it calls the wrong tool or fills inputs badly, or when a write action needs safeguards.
`studio-agent-design`	draft	Envision, Deliver	Turns an agreed agent brief into a Copilot Studio solution design - orchestration approach, topics, knowledge, tools and flows, authentication, channels, environment and solution packaging, and the run model - recording each design decision with the alternatives rejected. Use when a brief has chosen Copilot Studio, when a maker is about to build without a design, or when a growing agent needs its architecture reset.
`studio-agent-lifecycle`	draft	Launch, Measure, Scale, Improve	Keeps the technical estate of Copilot Studio agents healthy from creation to retirement - owners and co-owners, orphaned, inactive or duplicate agents, periodic recertification, Microsoft platform changes, and retiring an agent with its flows, connections, environment variables and stored data. Use when the number of Studio agents is growing, when a maker leaves, or when an agent has gone unused for months.
`studio-alm`	draft	Mobilise, Deliver, Launch, Improve	Sets application lifecycle management for Copilot Studio agents - solutions and publishers, environment variables and connection references, source control, pipelines between development, test and production, managed versus unmanaged imports, versioning, change control and rollback. Use when an agent must move beyond one environment, when changes are made directly in production, or when several makers work on the same agent.
`studio-analytics`	draft	Measure, Improve	Uses Copilot Studio analytics and conversation records to improve a live agent - sessions, outcomes such as resolved, escalated and abandoned, unanswered questions, knowledge and tool use, satisfaction and recurring themes - through a regular improvement review at aggregate level that turns findings into prioritised fixes. Use when an agent is live and its owner asks how it is doing, when resolution falls, or when deciding what to fix next.
`studio-authentication`	draft	Deliver, Assure	Designs how a Copilot Studio agent knows who the user is and whose identity it uses - the agent's authentication setting, Microsoft Entra sign-in or another identity provider, single sign-on per channel, end-user versus maker or service credentials for knowledge and tools, and anonymous use. Use when choosing an agent's authentication setting, when users are asked to sign in repeatedly, or when an action runs as the maker.
`studio-connectors`	draft	Deliver, Assure	Chooses the connectors a Copilot Studio agent depends on - prebuilt, certified or custom - and governs their use in the agent through connection references, the account each connection runs under, data policy grouping, ownership of custom connectors and their change control. Use when a maker needs a connector the agent does not yet use, when a custom connector is proposed, or when a data policy blocks an agent.
`studio-deployment`	draft	Launch, Scale	Publishes a released Copilot Studio agent to its channels - Teams and Microsoft 365 Copilot, websites, custom apps and others - configuring per-channel authentication, sharing to the approved audience, admin approval and availability, channel-specific behaviour and a staged rollout with a rollback route. Use when an agent has passed its release gate, when it is being added to a new channel, or when users cannot find or open it.
`studio-environments`	draft	Mobilise, Deliver, Scale	Applies the organisation's environment strategy to Copilot Studio work - the concrete personal, team, test and production environments makers use, environment routing for new makers, Managed Environment and agent settings per zone, security groups, data policies and how agents move between zones. Use when makers start building agents, when agents pile up in the default environment, or when a team asks for its own development space.
`studio-knowledge-architecture`	draft	Deliver, Improve	Designs the knowledge layer of a Copilot Studio agent - which ready sources to connect and by which knowledge type, how each is scoped, described and permission-trimmed, whether content is live or uploaded, how answers cite sources and how the layer is refreshed and owned. Use when connecting knowledge to a Studio agent, when answers come from the wrong source, or when a maker wants to upload copies of documents.
`studio-testing-and-evaluation`	draft	Deliver, Assure, Improve	Plans layered testing of a Copilot Studio agent - topic paths, orchestration choices, knowledge answers, tool and flow calls, authentication per channel, failure handling and regression after change - using the authoring test tools, repeatable evaluation sets and owner-agreed thresholds in a test environment. Use when a Studio agent with tools, topics or several sources needs testing, or when a change must be regression-tested.
`topics-and-orchestration`	draft	Deliver, Improve	Designs how a Copilot Studio agent decides what to do - which requests generative orchestration handles from the descriptions of knowledge, tools, topics and child agents, which need authored topics with fixed steps, and how triggers, variables, system topics and redirects fit together. Use when planning an agent's topics, when it picks the wrong topic or tool, or when authored topics keep multiplying.

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.