new-topic

Name: new-topic
Author: microsoft

372stars76forks

How to install new-topic?

microsoft/skills-for-copilot-studio/new-topic

$npx -y skills add microsoft/skills-for-copilot-studio --skill new-topic

Installs into the current project.

Summary

Create a new Copilot Studio topic YAML file. Use when the user asks to create a new topic, conversation flow, or dialog for their agent.

Files · 1

View on GitHub

SKILL.md

1	# Create New Topic
2
3	Generate a new Copilot Studio topic YAML file based on user requirements.
4
5	## Instructions
6
7	1. Auto-discover the agent directory:
8	```
9	Glob: **/agent.mcs.yml
10	```
11	If multiple agents found, ask which one. NEVER hardcode an agent name.
12
13	2. Check for matching templates in `${CLAUDE_SKILL_DIR}/../../templates/topics/` first:
14	- `greeting.topic.mcs.yml` — OnConversationStart greeting
15	- `fallback.topic.mcs.yml` — OnUnknownIntent fallback with escalation
16	- `arithmeticsum.topic.mcs.yml` — Topic with inputs/outputs and computation
17	- `question-topic.topic.mcs.yml` — Question with branching logic
18	- `search-topic.topic.mcs.yml` — Generative answers from knowledge
19	- `auth-topic.topic.mcs.yml` — Authentication flow
20	- `error-handler.topic.mcs.yml` — Error handling
21	- `disambiguation.topic.mcs.yml` — Multiple topics matched
22	If a template matches, use it as the starting point.
23
24	3. MANDATORY: Verify ALL `kind:` values against the schema before writing them:
25	```bash
26	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js kinds # List all valid kind values
27	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve AdaptiveDialog # Resolve trigger structure
28	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve <TriggerType> # Resolve specific trigger
29	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js search <ActionKind> # Verify an action kind exists
30	```
31	NEVER write a `kind:` value you haven't verified exists in the schema. This is the #1 source of hallucination errors. If `schema-lookup.bundle.js search <kind>` returns no results, the kind does NOT exist — do not use it.
32
33	4. Determine the trigger type from the user's description:
34	- `OnRecognizedIntent` — For topics triggered by user phrases (most common)
35	- `OnConversationStart` — For welcome/greeting topics
36	- `OnUnknownIntent` — For fallback topics
37	- `OnEscalate` — For escalation to human agent
38	- `OnError` — For error handling
39
40	5. Generate the topic YAML with:
41	- A `# Name:` comment at the top
42	- `kind: AdaptiveDialog`
43	- Appropriate `beginDialog` with correct trigger
44	- Unique IDs for ALL nodes (format: `<nodeType>_<6-8 random alphanumeric>`)
45	- If using a template, replace ALL `_REPLACE` placeholders with unique IDs
46
47	6. Check settings.mcs.yml for `GenerativeActionsEnabled`. Read the agent's `settings.mcs.yml` to check.
48
49	7. Save to the agent's `topics/<topic-name>.topic.mcs.yml` directory
50
51	8. MANDATORY: Validate the generated file after saving:
52
53	Step A: Schema validation — always run this first:
54	```bash
55	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js validate <saved-file.yml>
56	```
57
58	Step B: LSP-based validation — also run this if the agent has `.mcs/conn.json`:
59	Read `.mcs/conn.json` to get connection details, then:
60	```bash
61	node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js validate \
62	--workspace "<path-to-agent-folder>" \
63	--tenant-id "<tenantId>" \
64	--environment-id "<envId>" \
65	--environment-url "<envUrl>" \
66	--agent-mgmt-url "<mgmtUrl>"
67	```
68
69	Both validations are complementary: schema validation checks structural correctness (action kinds, property placement), while LSP validation checks Power Fx expressions, cross-file references, and environment-specific rules. If either fails, fix the issues before reporting success to the user.
70
71	## Generative Orchestration Guidelines
72
73	When the agent has `GenerativeActionsEnabled: true` in settings:
74
75	Use Topic Inputs (AutomaticTaskInput) instead of Question nodes to auto-collect user info.
76	Place `inputs` at the AdaptiveDialog root level (NOT inside `beginDialog`):
77	```yaml
78	kind: AdaptiveDialog
79	inputs: # <-- at AdaptiveDialog root, NOT inside beginDialog
80	- kind: AutomaticTaskInput
81	propertyName: userName
82	description: "The user's name"
83	entity: StringPrebuiltEntity
84	shouldPromptUser: true
85	beginDialog:
86	kind: OnRecognizedIntent
87	id: main
88	actions:
89	- ...
90	```
91	- The orchestrator auto-collects inputs based on the description — no explicit Question node needed.
92	- Still use Question nodes when: conditional asks (ask X only if Y), or end-of-flow confirmations.
93
94	Use Topic Outputs instead of SendActivity for final results.
95	Use `outputType` at the root level and `SetVariable` to set output values — do NOT use `TaskOutput` (which is only valid in `TaskDialog` connector actions):
96	```yaml
97	kind: AdaptiveDialog
98	inputs:
99	- ...
100	beginDialog:
101	kind:

People who liked this also viewed

6 picks

Type

hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026262k37k
request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026165k181k
analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026161k507
explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026161k507
ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026160k181k
scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026149k181k

new-topic

372stars76forks

View on GitHub

How to install new-topic?

microsoft/skills-for-copilot-studio/new-topic

$npx -y skills add microsoft/skills-for-copilot-studio --skill new-topic

Installs into the current project.

Summary

Create a new Copilot Studio topic YAML file. Use when the user asks to create a new topic, conversation flow, or dialog for their agent.

Files · 1

View on GitHub

SKILL.md

1	# Create New Topic
2
3	Generate a new Copilot Studio topic YAML file based on user requirements.
4
5	## Instructions
6
7	1. Auto-discover the agent directory:
8	```
9	Glob: **/agent.mcs.yml
10	```
11	If multiple agents found, ask which one. NEVER hardcode an agent name.
12
13	2. Check for matching templates in `${CLAUDE_SKILL_DIR}/../../templates/topics/` first:
14	- `greeting.topic.mcs.yml` — OnConversationStart greeting
15	- `fallback.topic.mcs.yml` — OnUnknownIntent fallback with escalation
16	- `arithmeticsum.topic.mcs.yml` — Topic with inputs/outputs and computation
17	- `question-topic.topic.mcs.yml` — Question with branching logic
18	- `search-topic.topic.mcs.yml` — Generative answers from knowledge
19	- `auth-topic.topic.mcs.yml` — Authentication flow
20	- `error-handler.topic.mcs.yml` — Error handling
21	- `disambiguation.topic.mcs.yml` — Multiple topics matched
22	If a template matches, use it as the starting point.
23
24	3. MANDATORY: Verify ALL `kind:` values against the schema before writing them:
25	```bash
26	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js kinds # List all valid kind values
27	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve AdaptiveDialog # Resolve trigger structure
28	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js resolve <TriggerType> # Resolve specific trigger
29	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js search <ActionKind> # Verify an action kind exists
30	```
31	NEVER write a `kind:` value you haven't verified exists in the schema. This is the #1 source of hallucination errors. If `schema-lookup.bundle.js search <kind>` returns no results, the kind does NOT exist — do not use it.
32
33	4. Determine the trigger type from the user's description:
34	- `OnRecognizedIntent` — For topics triggered by user phrases (most common)
35	- `OnConversationStart` — For welcome/greeting topics
36	- `OnUnknownIntent` — For fallback topics
37	- `OnEscalate` — For escalation to human agent
38	- `OnError` — For error handling
39
40	5. Generate the topic YAML with:
41	- A `# Name:` comment at the top
42	- `kind: AdaptiveDialog`
43	- Appropriate `beginDialog` with correct trigger
44	- Unique IDs for ALL nodes (format: `<nodeType>_<6-8 random alphanumeric>`)
45	- If using a template, replace ALL `_REPLACE` placeholders with unique IDs
46
47	6. Check settings.mcs.yml for `GenerativeActionsEnabled`. Read the agent's `settings.mcs.yml` to check.
48
49	7. Save to the agent's `topics/<topic-name>.topic.mcs.yml` directory
50
51	8. MANDATORY: Validate the generated file after saving:
52
53	Step A: Schema validation — always run this first:
54	```bash
55	node ${CLAUDE_SKILL_DIR}/../../scripts/schema-lookup.bundle.js validate <saved-file.yml>
56	```
57
58	Step B: LSP-based validation — also run this if the agent has `.mcs/conn.json`:
59	Read `.mcs/conn.json` to get connection details, then:
60	```bash
61	node ${CLAUDE_SKILL_DIR}/../../scripts/manage-agent.bundle.js validate \
62	--workspace "<path-to-agent-folder>" \
63	--tenant-id "<tenantId>" \
64	--environment-id "<envId>" \
65	--environment-url "<envUrl>" \
66	--agent-mgmt-url "<mgmtUrl>"
67	```
68
69	Both validations are complementary: schema validation checks structural correctness (action kinds, property placement), while LSP validation checks Power Fx expressions, cross-file references, and environment-specific rules. If either fails, fix the issues before reporting success to the user.
70
71	## Generative Orchestration Guidelines
72
73	When the agent has `GenerativeActionsEnabled: true` in settings:
74
75	Use Topic Inputs (AutomaticTaskInput) instead of Question nodes to auto-collect user info.
76	Place `inputs` at the AdaptiveDialog root level (NOT inside `beginDialog`):
77	```yaml
78	kind: AdaptiveDialog
79	inputs: # <-- at AdaptiveDialog root, NOT inside beginDialog
80	- kind: AutomaticTaskInput
81	propertyName: userName
82	description: "The user's name"
83	entity: StringPrebuiltEntity
84	shouldPromptUser: true
85	beginDialog:
86	kind: OnRecognizedIntent
87	id: main
88	actions:
89	- ...
90	```
91	- The orchestrator auto-collects inputs based on the description — no explicit Question node needed.
92	- Still use Question nodes when: conditional asks (ask X only if Y), or end-of-flow confirmations.
93
94	Use Topic Outputs instead of SendActivity for final results.
95	Use `outputType` at the root level and `SetVariable` to set output values — do NOT use `TaskOutput` (which is only valid in `TaskDialog` connector actions):
96	```yaml
97	kind: AdaptiveDialog
98	inputs:
99	- ...
100	beginDialog:
101	kind:

People who liked this also viewed

6 picks

Type