Teams App Developer
MicrosoftOfficialPublished by Microsoft
- Skill
- Tool integration
- Software development
- MIT
- Medium risk
AutoGineer summary
Written by AutoGineer from the skill’s own files, not by the author
The teams-app-developer skill provides a structured framework for managing the lifecycle of Microsoft 365 agents and Teams applications. It leverages the ATK CLI to handle project scaffolding, local testing via the Agents Playground, cloud provisioning on Azure, and troubleshooting. The skill includes specialized guidance for migrating Slack bots to Teams, including converting Block Kit UI to Adaptive Cards, and provides access to an extensive library of micro-expert documentation for cross-platform development.
What it does
- Scaffolds new Microsoft 365 agents and Teams applications from templates.
- Facilitates local testing using the Agents Playground or Teams-specific environments.
- Automates Azure resource provisioning and cloud deployment workflows.
- Provides diagnostic procedures for common authentication and configuration errors.
- Supports migration of Slack bots to the Teams platform.
- Manages project configuration and environment variables for ATK-based projects.
When to use it
- When starting a new Teams app, bot, or Declarative Agent project.
- When you need to test an agent locally before deploying to the cloud.
- When migrating existing Slack bots to the Microsoft Teams ecosystem.
- When troubleshooting deployment or authentication issues in a Teams project.
- When you need to provision Azure infrastructure for a Teams application.
Advantages
- Streamlines the development lifecycle with standardized CLI commands.
- Reduces development time by offering a local testing playground.
- Provides expert-level guidance for complex cross-platform migrations.
- Ensures consistent configuration management across development environments.
- Includes robust error-handling protocols for common platform-specific pitfalls.
Usage examples
- “Create a new Teams bot project using the default template.”
- The agent will initialize a new project folder, configure the necessary YAML files, and guide you through the initial setup using the ATK CLI.
- “How do I migrate my Slack bot to Microsoft Teams?”
- The agent will initiate the slack-to-teams workflow, providing access to cross-platform bridging experts and guidance on converting UI components.
- “My Teams bot is returning a 401 error, how do I fix it?”
- The agent will trigger the troubleshooting workflow, checking your environment variables, tunnel status, and authentication configuration.
Install
Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/microsoft/teams-app-developer/downloadUnzip it into the cross-client skills folder of your project:
mkdir -p .agents/skills && unzip teams-app-developer.zip -d .agents/skills
Documentation by Microsoft
Microsoft 365 Agents Toolkit Skill
Build Microsoft 365 agents and Teams apps using the ATK CLI.
AI Behavior Guidelines
Testing Strategy: Recommend Agents Playground first (faster, no M365 needed). Use Teams workflow only if user explicitly requests it.
Environment Variables: NEVER hardcode secrets or make up placeholder values. Always ask users for real values.
Error Handling: Read error messages carefully. Check
env/.env.local,.localConfigs, andatk auth list. Common pitfalls:AADSTS7000229→aadApp/createmissinggenerateServicePrincipal: truein YAML — add it and re-provisionMissing
TENANT_IDin.localConfigs→ SDK uses wrong token authority → 401 from Bot Connector401 persists after auth fix → devtunnel URL may be blacklisted — create a fresh tunnel
See troubleshoot/troubleshoot.md for full diagnostic steps
Long-Running Commands — WAIT for completion:
atk new,atk provision,atk deploycan take several minutesAlways wait for completion before running the next step (timeout 120000ms+)
Local Service Startup — Hangs terminal (expected):
npm run dev,npm start,python app.py,devtunnel host, etc. will hang — the process keeps running indefinitelyALWAYS run as a background process (
isBackground=true) — NEVER useisBackground=falsefor these commandsDo NOT wait for it to "finish" — verify startup by checking output for "listening on port" or tunnel URL
If errors appear, read logs, diagnose, fix, restart
Use a NEW terminal to launch Agents Playground or open Teams sideloading URL
Monitor App Logs: Periodically check background terminal output for runtime errors. If the app crashes, read the error, fix the root cause, and restart.
Telemetry Tagging: Before running any
atkCLI commands, set the session environment variable so all CLI invocations are tagged as skill-initiated:export ATK_CLI_SKILL=trueRun this once at the start of the session. All subsequent
atkcommands in the same terminal will inherit it.
ATK CLI Setup
atk --version # Must be > 1.1.5-betaIf ATK is not found or version is too old:
npm i -g @microsoft/m365agentstoolkit-cli@betaCLI Global Options
| Option | Meaning | Recommendation |
|---|---|---|
-i | Interactive mode | Always use -i false in automation to avoid hanging |
-f | Project folder | Default to be current directory, used when specifying a custom folder. When scaffolding a new project, this is the parent folder where the project folder will be created under. |
-h | Command help | Use atk <command> -h for quick syntax checks |
Sub-Skills
| Sub-Skill | When to Use | Reference |
|---|---|---|
| create-project | Scaffold new project from template, choose template, atk new | create-project/create-project.md |
| test-playground | Test locally with Agents Playground, agentsplayground, quick testing | test-playground/test-playground.md |
| test-teams | Run on Teams, devtunnel, sideload, Teams testing, test in Copilot | test-teams/test-teams.md |
| provision-deploy | Provision Azure resources, deploy to cloud, atk provision, atk deploy | provision-deploy/provision-deploy.md |
| troubleshoot | Fix errors, 401, port conflicts, YAML errors, stale bots | troubleshoot/troubleshoot.md |
| slack-to-teams | Migrate Slack bot to Teams, cross-platform bridging, Block Kit to Adaptive Cards | slack-to-teams/SKILL.md |
MANDATORY: Before executing any workflow, read the corresponding sub-skill document.
Shared References
manifest-and-yaml.md — Project files, YAML config, env vars, .localConfigs flow
commands.md — ATK CLI commands: package, validate, share, collaborate
templates.md — Complete template catalog with language support
experts/ — 100+ micro-expert files: Teams SDK, Slack SDK, cross-platform bridging, deploy, AI models, security, language conversion
docs/ — Platform comparison guides: UI, messaging, identity, infrastructure, feature gaps
Workflow Chains
Match user intent to the smallest valid workflow.
| User Intent | Workflow (read in order) |
|---|---|
| Build new app from scratch | create-project → test-playground |
| Test existing project locally | test-playground (recommended) or test-teams |
| Deploy to Azure | provision-deploy |
| Fix broken bot | troubleshoot → re-test |
| Migrate Slack bot to Teams | slack-to-teams |
MANDATORY: Before executing any slack-to-teams workflow, read slack-to-teams/SKILL.md first. The sub-skill contains a routed expert system with 100+ micro-expert files for cross-platform bot development.
ATK Project Context Resolution
Resolve config values only when missing. If a value is already known in the session, reuse it.
Step 1: Detect ATK Project
If m365agentstoolkit*.yml exists in the current folder, treat it as an ATK project and parse configuration.
Step 2: Resolve Common Configuration
Resolve variables referenced in m365agentstoolkit*.yml. Common variables:
AZURE_OPENAI_API_KEY
AZURE_OPENAI_ENDPOINT
AZURE_OPENAI_DEPLOYMENT_NAME
Step 3: Collect Missing Values
If required values are missing, ask the user for only the missing ones.
Refer to manifest-and-yaml.md for full config-file details.
Files
- ATTRIBUTION.mdAdded by AutoGineer906 B
- LICENSELicence file added by AutoGineer1.1 KiB
- SKILL.md7.6 KiB
- create-project/create-project.md8.1 KiB
- docs/README.md2.8 KiB
- docs/advanced-features.md7.0 KiB
- docs/feature-gaps.md46.3 KiB
- docs/files-and-links.md4.2 KiB
- docs/identity-and-auth.md4.3 KiB
- docs/infrastructure.md6.7 KiB
- docs/interactive-responses.md4.4 KiB
- docs/messaging-and-commands.md4.5 KiB
- docs/middleware-and-handlers.md4.4 KiB
- docs/ui-components.md6.9 KiB
- docs/workflows.md14.4 KiB
- experts/README.md8.6 KiB
- experts/_expert-ts.md2.2 KiB
- experts/analyzer.md14.0 KiB
- experts/bridge/app-distribution-packaging-ts.md14.2 KiB
- experts/bridge/channel-ops-graph-ts.md15.4 KiB
- experts/bridge/commands-slash-text-ts.md18.5 KiB
- experts/bridge/cross-platform-advisor-ts.md36.4 KiB
- experts/bridge/cross-platform-architecture-ts.md8.3 KiB
- experts/bridge/events-activities-ts.md22.4 KiB
- experts/bridge/files-upload-download-ts.md17.2 KiB
- experts/bridge/identity-oauth-bridge-ts.md19.8 KiB
- experts/bridge/index.md13.0 KiB
- experts/bridge/infra-compute-ts.md14.6 KiB
- experts/bridge/infra-observability-ts.md14.0 KiB
- experts/bridge/infra-secrets-config-ts.md13.2 KiB
- experts/bridge/infra-storage-ts.md14.3 KiB
- experts/bridge/interactive-responses-ts.md19.6 KiB
- experts/bridge/link-unfurl-preview-ts.md17.1 KiB
- experts/bridge/middleware-handlers-ts.md15.4 KiB
- experts/bridge/python-cross-platform.md9.3 KiB
- experts/bridge/rate-limiting-resilience-ts.md17.6 KiB
- experts/bridge/rest-only-integration-ts.md8.4 KiB
- experts/bridge/scheduling-deferred-send-ts.md17.8 KiB
- experts/bridge/shortcuts-extensions-ts.md17.5 KiB
- experts/bridge/transport-socketmode-https-ts.md14.3 KiB
- experts/bridge/ui-app-home-personal-tab-ts.md14.5 KiB
- experts/bridge/ui-block-kit-adaptive-cards-ts.md21.5 KiB
- experts/bridge/ui-legacy-attachments-cards-ts.md11.2 KiB
- experts/bridge/ui-modals-dialogs-ts.md21.4 KiB
- experts/bridge/workflow.composable-platform-ts.md13.7 KiB
- experts/bridge/workflows-automation-ts.md14.3 KiB
- experts/builder.md11.1 KiB
- experts/convert/bulk-conversion-strategy-ts.md12.8 KiB
- experts/convert/dependency-mapping-ts.md8.3 KiB
- experts/convert/index.md3.5 KiB
- experts/convert/java-to-ts-ts.md20.6 KiB
- experts/convert/js-to-ts-ts.md6.2 KiB
- experts/convert/json-serialization-ts.md11.0 KiB
- experts/convert/kotlin-to-ts-ts.md11.2 KiB
- experts/convert/ruby-to-ts-ts.md9.7 KiB
- experts/convert/type-mapping-ts.md10.1 KiB
- experts/deploy/aws-bot-deploy-ts.md14.6 KiB
- experts/deploy/aws-cli-reference-ts.md52.4 KiB
- experts/deploy/azure-bot-deploy-ts.md15.4 KiB
- experts/deploy/azure-cli-reference-ts.md16.9 KiB
- experts/deploy/index.md4.6 KiB
- experts/fallback.md2.1 KiB
- experts/index.md18.9 KiB
- experts/models/anthropic-ts.md7.8 KiB
- experts/models/bedrock-ts.md9.9 KiB
- experts/models/foundry-cloud-ts.md8.1 KiB
- experts/models/foundry-local-ts.md10.6 KiB
- experts/models/index.md5.8 KiB
- experts/models/openai-azure-openai-ts.md8.3 KiB
- experts/models/oss-openai-compatible-ts.md10.7 KiB
- experts/models/transformers-js-ts.md11.6 KiB
- experts/prompt-engineer.md14.7 KiB
- experts/researcher.md2.8 KiB
- experts/security/index.md1.2 KiB
- experts/security/input-validation-ts.md13.8 KiB
- experts/security/secrets-ts.md13.9 KiB
- experts/slack/bolt-assistant-ts.md9.9 KiB
- experts/slack/bolt-events-ts.md9.3 KiB
- experts/slack/bolt-java.md8.9 KiB
- experts/slack/bolt-oauth-distribution-ts.md10.9 KiB
- experts/slack/bolt-python.md9.5 KiB
- experts/slack/cli.app-management.md7.9 KiB
- experts/slack/cli.datastore-env.md8.6 KiB
- experts/slack/cli.getting-started.md8.0 KiB
- experts/slack/cli.local-dev-deploy.md8.4 KiB
- experts/slack/cli.manifest-triggers.md9.9 KiB
- experts/slack/index.md8.9 KiB
- experts/slack/runtime.ack-rules-ts.md9.8 KiB
- experts/slack/runtime.bolt-foundations-ts.md10.7 KiB
- experts/slack/runtime.shortcuts-ts.md11.0 KiB
- experts/slack/runtime.slash-commands-ts.md11.6 KiB
- experts/slack/runtime.socket-mode-ts.md9.5 KiB
- experts/slack/ui.block-kit-ts.md11.5 KiB
- experts/slack/ui.modals-lifecycle-ts.md13.3 KiB
- experts/slack/web-api-proactive-ts.md11.0 KiB
- experts/slack/workflow.slack-automations-ts.md10.2 KiB
- experts/teams/a2a.client-basics-ts.md9.7 KiB
- experts/teams/a2a.orchestrator-patterns-ts.md12.7 KiB
- experts/teams/a2a.server-basics-ts.md11.4 KiB
- experts/teams/ai.chatprompt-basics-ts.md8.1 KiB
- experts/teams/ai.citations-feedback-ts.md6.9 KiB
- experts/teams/ai.conversational-query-ts.md14.2 KiB
- experts/teams/ai.function-calling-design-ts.md9.0 KiB
- experts/teams/ai.function-calling-implementation-ts.md7.7 KiB
- experts/teams/ai.memory-localmemory-ts.md7.3 KiB
- experts/teams/ai.model-setup-ts.md6.6 KiB
- experts/teams/ai.rag-retrieval-ts.md7.4 KiB
- experts/teams/ai.rag-vectorstores-ts.md8.5 KiB
- experts/teams/ai.streaming-ts.md6.9 KiB
- experts/teams/auth.oauth-sso-ts.md10.1 KiB
- experts/teams/compat.botbuilder-interop-ts.md14.6 KiB
- experts/teams/dev.debug-test-ts.md14.1 KiB
- experts/teams/graph.usergraph-appgraph-ts.md9.0 KiB
- experts/teams/index.md9.8 KiB
- experts/teams/mcp.client-basics-ts.md9.5 KiB
- experts/teams/mcp.expose-chatprompt-tools-ts.md9.5 KiB
- experts/teams/mcp.security-ts.md10.4 KiB
- experts/teams/mcp.server-basics-ts.md9.9 KiB
- experts/teams/project.scaffold-files-ts.md12.2 KiB
- experts/teams/runtime.app-init-ts.md10.9 KiB
- experts/teams/runtime.manifest-ts.md12.3 KiB
- experts/teams/runtime.proactive-messaging-ts.md12.6 KiB
- experts/teams/runtime.routing-handlers-ts.md12.3 KiB
- experts/teams/state.storage-patterns-ts.md9.4 KiB
- experts/teams/teams-dotnet.md8.2 KiB
- experts/teams/teams-python.md8.3 KiB
- experts/teams/ui.adaptive-cards-ts.md12.9 KiB
- experts/teams/ui.dialogs-task-modules-ts.md15.1 KiB
- experts/teams/ui.message-extensions-ts.md15.6 KiB
- experts/teams/workflow.approvals-inline-ts.md12.4 KiB
- experts/teams/workflow.message-native-records-ts.md10.6 KiB
- experts/teams/workflow.sharepoint-lists-ts.md9.0 KiB
- experts/teams/workflow.state-driven-events-ts.md12.2 KiB
- experts/teams/workflow.triggers-compose-ts.md10.3 KiB
- experts/update-experts.md10.0 KiB
- provision-deploy/provision-deploy.md4.3 KiB
- test-playground/playground-cli.md4.6 KiB
- test-playground/playground.md4.5 KiB
- test-playground/test-playground.md1.1 KiB
- test-teams/test-teams.md4.9 KiB
- toolkit/README.md4.2 KiB
- toolkit/commands.md2.6 KiB
- toolkit/environments.md12.6 KiB
- toolkit/lifecycle-cli.md17.6 KiB
- toolkit/manifest-and-yaml.md6.0 KiB
- toolkit/playground.md7.6 KiB
- toolkit/publish.md9.3 KiB
- toolkit/templates.md6.7 KiB
- troubleshoot/troubleshoot.md20.2 KiB
experts/teams/ai.conversational-query-ts.md
ai.conversational-query-ts
purpose
Enable natural language retrieval over structured workflow state — translating user questions like "Who is on break?" or "Show PTO for March" into list/datastore queries and rendering results as interactive message-backed cards.
rules
NL queries go through AI function calling, not regex parsing. Define tool/function schemas that accept structured parameters (status filter, date range, person). The LLM translates the user's natural language into function calls with the right parameters. This handles the infinite variation of how users phrase queries.
Define focused query functions, not a generic "search" function. Create specific functions:
queryPtoRequests(status?, dateRange?, requester?),queryBreakStatus(teamId?),queryEquipmentBookings(item?, dateRange?). Specific schemas give the LLM better guidance than a single catch-all. learn.microsoft.com -- Function callingMap function parameters to OData
$filterexpressions. Each function parameter translates to a filter clause:status: "pending"→fields/Status eq 'Pending',dateRange: { start, end }→fields/StartDate ge '2024-03-01' and fields/StartDate le '2024-03-31'. Build filters programmatically from the AI's structured output.Return structured data to the LLM, not raw JSON. Format query results as a readable table or summary before passing back to the model. The LLM then generates a natural language response that can include counts, trends, and highlights. Don't dump raw Graph API responses into the prompt.
Render query results as Adaptive Cards, not plain text. After the LLM generates a summary, also render the actual records as interactive cards. The text answer provides context; the cards provide actionable records. Users get both "You have 3 pending PTO requests" and the cards to act on them.
Support aggregate queries with server-side computation. For "average break duration" or "how many PTO days used this quarter," compute aggregates in the function implementation (sum, count, average over fetched records). Return the computed result to the LLM for natural language rendering.
Use
$topand$skipfor pagination. When queries may return many results, default to$top=10. If the user asks "show all," paginate and summarize: "Showing 10 of 47 results. Say 'show more' to see the next page." Track pagination state per conversation.Include a
queryWorkflowRecordsfunction for cross-workflow queries. In addition to workflow-specific functions, provide a general function that queries across all workflow lists. The LLM uses this when the user asks something like "what's overdue?" without specifying a workflow type.Ground AI responses in actual data. Always include the source record count and date range in the response. "Based on 12 PTO requests from March 1-31..." prevents hallucination about records that don't exist.
Cache frequent queries for low-latency responses. Queries like "who is on break right now?" are likely repeated frequently. Cache results for 30-60 seconds to avoid hitting Graph API limits on every message.
patterns
Define query functions for ChatPrompt
import { ChatPrompt } from "@anthropic-ai/sdk"; // or teams-ai equivalent
const queryFunctions = [
{
name: "queryPtoRequests",
description: "Query PTO/time-off requests. Use when the user asks about PTO, time off, vacation, leave, or days off.",
parameters: {
type: "object",
properties: {
status: {
type: "string",
enum: ["Pending", "Approved", "Rejected", "All"],
description: "Filter by request status. Default: All",
},
requester: {
type: "string",
description: "Filter by requester name (partial match). Omit for all requesters.",
},
month: {
type: "string",
description: "Filter by month, e.g. '2024-03' for March 2024. Omit for all dates.",
},
},
},
},
{
name: "queryBreakStatus",
description: "Query who is currently on break or break history. Use when the user asks about breaks, availability, or who is away.",
parameters: {
type: "object",
properties: {
currentOnly: {
type: "boolean",
description: "True to show only active breaks. False for break history.",
},
dateRange: {
type: "object",
properties: {
start: { type: "string", description: "ISO date" },
end: { type: "string", description: "ISO date" },
},
},
},
},
},
{
name: "queryEquipmentBookings",
description: "Query equipment reservations and availability. Use when the user asks about bookings, reservations, equipment, or availability.",
parameters: {
type: "object",
properties: {
item: { type: "string", description: "Equipment name or type to filter" },
status: { type: "string", enum: ["Active", "Returned", "Overdue", "All"] },
dateRange: {
type: "object",
properties: {
start: { type: "string" },
end: { type: "string" },
},
},
},
},
},
];Implement query function with OData filter building
async function queryPtoRequests(
graphClient: Client,
siteId: string,
listId: string,
params: { status?: string; requester?: string; month?: string }
): Promise<{ records: any[]; summary: string }> {
const filters: string[] = [];
if (params.status && params.status !== "All") {
filters.push(`fields/Status eq '${params.status}'`);
}
if (params.month) {
const start = `${params.month}-01`;
const endDate = new Date(
parseInt(params.month.split("-")[0]),
parseInt(params.month.split("-")[1]),
0
);
const end = endDate.toISOString().split("T")[0];
filters.push(`fields/StartDate ge '${start}' and fields/StartDate le '${end}'`);
}
let query = graphClient
.api(`/sites/${siteId}/lists/${listId}/items`)
.expand("fields")
.top(20)
.orderby("fields/StartDate desc");
if (filters.length > 0) {
query = query.filter(filters.join(" and "));
}
const response = await query.get();
const records = response.value.map((item: any) => ({
id: item.id,
requester: item.fields.Title,
startDate: item.fields.StartDate,
endDate: item.fields.EndDate,
status: item.fields.Status,
hoursRequested: item.fields.HoursRequested,
}));
// Filter requester client-side (OData doesn't support contains on all field types)
const filtered = params.requester
? records.filter((r: any) =>
r.requester.toLowerCase().includes(params.requester!.toLowerCase())
)
: records;
// Build summary for LLM
const summary = [
`Found ${filtered.length} PTO request(s).`,
params.status && params.status !== "All" ? `Status: ${params.status}.` : "",
params.month ? `Month: ${params.month}.` : "",
`Total hours: ${filtered.reduce((sum: number, r: any) => sum + (r.hoursRequested || 0), 0)}.`,
]
.filter(Boolean)
.join(" ");
return { records: filtered, summary };
}Wire functions into the message handler
app.message(async (ctx) => {
const userMessage = ctx.activity.text ?? "";
// Send to LLM with function definitions
const response = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{
role: "system",
content:
"You are a workflow assistant. Answer questions about PTO, breaks, equipment, and other workflow records. " +
"Always use the provided functions to query real data. Never make up record counts or details.",
},
{ role: "user", content: userMessage },
],
tools: queryFunctions.map((f) => ({ type: "function", function: f })),
});
const choice = response.choices[0];
if (choice.message.tool_calls?.length) {
const toolCall = choice.message.tool_calls[0];
const args = JSON.parse(toolCall.function.arguments);
// Execute the query
let result: { records: any[]; summary: string };
switch (toolCall.function.name) {
case "queryPtoRequests":
result = await queryPtoRequests(graphClient, siteId, ptoListId, args);
break;
case "queryBreakStatus":
result = await queryBreakStatus(graphClient, siteId, breakListId, args);
break;
case "queryEquipmentBookings":
result = await queryEquipmentBookings(graphClient, siteId, equipListId, args);
break;
default:
result = { records: [], summary: "Unknown query type." };
}
// Send result back to LLM for natural language response
const followUp = await openai.chat.completions.create({
model: "gpt-4o",
messages: [
{ role: "system", content: "Summarize the query results naturally. Include counts and key details." },
{ role: "user", content: userMessage },
choice.message,
{
role: "tool",
tool_call_id: toolCall.id,
content: result.summary,
},
],
});
const textResponse = followUp.choices[0].message.content ?? "";
// Send text summary + record cards
await ctx.send(textResponse);
if (result.records.length > 0 && result.records.length <= 5) {
// Inline cards for small result sets
for (const record of result.records) {
await ctx.send({
attachments: [{
contentType: "application/vnd.microsoft.card.adaptive",
content: buildRecordCard(record),
}],
});
}
} else if (result.records.length > 5) {
// Summary card for large result sets
await ctx.send({
attachments: [{
contentType: "application/vnd.microsoft.card.adaptive",
content: buildRecordListCard(result.records.slice(0, 10)),
}],
});
}
} else {
// No function call — direct response
await ctx.send(choice.message.content ?? "I couldn't find relevant records for that query.");
}
});Aggregate query example
async function queryBreakStatus(
graphClient: Client,
siteId: string,
listId: string,
params: { currentOnly?: boolean; dateRange?: { start: string; end: string } }
): Promise<{ records: any[]; summary: string }> {
const filters: string[] = [];
if (params.currentOnly) {
filters.push("fields/Status eq 'Active'");
}
if (params.dateRange) {
filters.push(
`fields/StartTime ge '${params.dateRange.start}' and fields/StartTime le '${params.dateRange.end}'`
);
}
let query = graphClient
.api(`/sites/${siteId}/lists/${listId}/items`)
.expand("fields")
.top(50);
if (filters.length) query = query.filter(filters.join(" and "));
const response = await query.get();
const records = response.value.map((item: any) => item.fields);
// Compute aggregates
const activeBreaks = records.filter((r: any) => r.Status === "Active");
const completedBreaks = records.filter((r: any) => r.Status === "Ended");
const avgDuration =
completedBreaks.length > 0
? completedBreaks.reduce((sum: number, r: any) => sum + (r.DurationMinutes || 0), 0) /
completedBreaks.length
: 0;
const summary = [
`Currently on break: ${activeBreaks.length} people.`,
activeBreaks.map((r: any) => r.EmployeeName).join(", ") || "None.",
completedBreaks.length > 0
? `Average break duration today: ${avgDuration.toFixed(1)} minutes.`
: "",
]
.filter(Boolean)
.join(" ");
return { records, summary };
}pitfalls
LLM may call the wrong function. Provide clear, non-overlapping descriptions. "Who is available?" could match breaks or equipment. Use
descriptionfields to disambiguate and add examples in the system prompt.OData
$filterdoesn't supportcontains()on all column types. SharePoint Lists OData implementation is limited compared to full OData.contains()works on text columns but not choice or person columns. Fall back to client-side filtering when needed.Don't pass raw Graph API responses to the LLM. They contain metadata,
@odataannotations, and nested objects that waste tokens and confuse the model. Extract only the fields you need into a clean summary string.Pagination state must be conversation-scoped. If user A asks "show more" in a channel, it should continue user A's query, not user B's. Key pagination state on
(conversationId, userId).Token limits on large result sets. If a query returns 50 records, the summary string passed to the LLM might be too long. Summarize with counts and top-N details rather than listing every record.
Cache invalidation matters for "right now" queries. "Who is on break?" expects real-time accuracy. Cache TTL should be short (30s max) for current-state queries. Historical queries can cache longer.
references
instructions
Use this expert when implementing natural language retrieval over structured workflow data. Covers AI function calling design for query translation, OData filter building from function parameters, aggregate computation, result rendering as cards, and pagination. Pair with workflow.sharepoint-lists-ts.md for the underlying data store, ai.function-calling-design-ts.md for function schema best practices, ai.function-calling-implementation-ts.md for execution patterns, and workflow.message-native-records-ts.md for rendering results as interactive record cards.
research
Deep Research prompt:
"Write a micro expert on natural language querying over structured workflow state in Microsoft Teams (TypeScript). Cover: AI function calling to translate NL to SharePoint List OData queries, function schema design for PTO/break/equipment queries, OData filter building, aggregate computation (averages, counts, trends), result rendering as Adaptive Cards, pagination, caching, and grounding AI responses in actual data. Include complete patterns from user message through LLM function call through query execution through card rendering."
Requirements and compatibility
Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta
“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.
Needs: Needs an API key, Needs Python, Needs Node.js
Security
What our scanner noticed· Medium risk
- Possible data-exfiltration endpoints
- Instructions that use the network
- Downloads piped into a shell
A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.
Attribution and licence
- Published by
- Microsoft
- Publisher
- Microsoft (Official)
- Source
- microsoft/skills · .github/plugins/microsoft-365-agents-toolkit/skills/teams-app-developer · commit 0696600
- Licence
- MIT License (redistribution allowed)
- LICENSE (added by AutoGineer from LICENSE)
- ATTRIBUTION.md (written by AutoGineer)
- Synced
AutoGineer is not affiliated with or endorsed by Microsoft.
Download ZIP
The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download teams-app-developer.zip