agentleFS
MicrosoftKnown publishermicrosoft/skills-for-copilot-studio/skills/add-node/SKILL.md

add-node

Skill486 starsChanged 8 months agoMITView on GitHub

Add or modify a node in an existing Copilot Studio topic. Use when the user asks to add a question, message, condition, variable, or other node to a topic. Do NOT use this for generative answers or knowledge search — use /add-generative-answers instead.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Add a new node to an existing Copilot Studio topic, or modify an existing one.

    line 12
  2. Distinctive:

    NEVER hardcode an agent name.

    line 24
  3. Distinctive:

    If modifying an existing node, which node to modify

    line 29
  4. Distinctive:

    All required properties from the schema

    line 40
  5. Very specific:

    When the agent has GenerativeActionsEnabled: true:

    line 60
  6. Distinctive:

    Prefer AutomaticTaskInput over Question nodes for collecting user info (the orchestrator handles prompting automatically).

    line 62
  7. Distinctive:

    Prefer topic outputs over SendActivity for returning results.

    line 64
  8. Distinctive:

    Do NOT use SendActivity to show final outputs unless it's a precise mid-flow message.

    line 65
  9. Distinctive:

    Unique IDs: Use random 6-8 alphanumeric characters.

    line 89
  10. Distinctive:

    Verify the node type exists in the schema before generating.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Add Node to Topic

Add a new node to an existing Copilot Studio topic, or modify an existing one.

In Copilot Studio, the elements inside a topic's actions array are nodes (SendActivity, Question, ConditionGroup, etc.). These are different from actions (actions/*.mcs.yml), which are connector-based TaskDialogs. This skill handles nodes within topics.

For generative answers (SearchAndSummarizeContent, AnswerQuestionWithAI), use the /add-generative-answers skill instead — it has the specific patterns, follow-up ConditionGroup logic, and disambiguation guidance needed to set them up correctly.

Instructions

  1. Auto-discover the agent directory:
    Glob: **/agent.mcs.yml
    NEVER hardcode an agent name.
  2. Parse the arguments to identify:
    • The node type (SendActivity, Question, SetVariable, ConditionGroup, etc.)
    • The target topic file
    • If modifying an existing node, which node to modify
  3. Look up the node schema:
    node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve <NodeType>
  4. Read the existing topic file to understand its current structure.
  5. Generate or modify the node with:
    • A unique ID (format: <nodeType>_<6-8 random alphanumeric>)
    • All required properties from the schema
    • Appropriate default values
  6. Determine the correct insertion point in the actions array and present the plan to the user before writing.

Common Node Types

NodePurposeKey Properties
SendActivitySend messagekind, id, activity
QuestionAsk user inputkind, id, variable, prompt, entity
SetVariableSet/compute valuekind, id, variable, value
SetTextVariableSet text with interpolation (YAML-only, no canvas)kind, id, variable, value
ConditionGroupBranching logickind, id, conditions
BeginDialogCall another topickind, id, dialog
EndDialogEnd topickind, id
CancelAllDialogsCancel all topicskind, id

Generative Orchestration Guidelines

When the agent has GenerativeActionsEnabled: true:

  • Prefer AutomaticTaskInput over Question nodes for collecting user info (the orchestrator handles prompting automatically).
  • Still use Question nodes when: conditional asks (ask X only if Y), or end-of-flow confirmations.
  • Prefer topic outputs over SendActivity for returning results.
  • Do NOT use SendActivity to show final outputs unless it's a precise mid-flow message.

Power Fx Quick Reference

  • Expressions start with =: condition: =System.FallbackCount < 3
  • String interpolation uses {}: activity: "Error: {System.Error.Message}"
  • Variable init on first assignment: variable: init:Topic.MyVar
  • Common: Text(), Now(), IsBlank(), !IsBlank()

Example: Adding a Question Node

- kind: Question
  id: question_k7xPm2
  variable: init:Topic.UserName
  prompt: What is your name?
  entity: StringPrebuiltEntity
  alwaysPrompt: true
  interruptionPolicy:
    allowInterruption: false

Important Notes

  • Unique IDs: Use random 6-8 alphanumeric characters. Duplicate IDs cause Copilot Studio errors.
  • Verify the node type exists in the schema before generating.
  • For ConditionGroup, include at least one condition item with its own unique ID.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.