microsoft/skills/directline-chat
skills/directline-chat/SKILL.md
DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.
$ install --global
skillsauthnpx skillsauth add microsoft/skills-for-copilot-studio skills/directline-chatInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 30, 2026, 7:04 AM12.7s1 file scanned
SKILL.md
- user-invocable:
- false
- description:
- DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.
- argument-hint:
- <utterance to send>
- allowed-tools:
- Bash(node *directline-chat.bundle.js *), Bash(node *manage-agent.bundle.js detect-mode *), Read, Glob, Grep
- context:
- fork
- agent:
- copilot-studio-test
DirectLine Chat (Deprecated)
This skill has been merged into /copilot-studio:chat-with-agent, which now auto-detects the agent's authentication mode and uses DirectLine automatically for no-auth and manual-auth agents.
Use /copilot-studio:chat-with-agent instead. It handles both DirectLine and Copilot Studio SDK modes in a single skill.
If you are here because the caller explicitly provided a DirectLine secret or token endpoint URL, you may proceed with the instructions below. Otherwise, redirect to /copilot-studio:chat-with-agent.
Direct Usage (when caller provides explicit DirectLine credentials)
Token endpoint mode
node ${CLAUDE_SKILL_DIR}/../../scripts/directline-chat.bundle.js \
--token-endpoint "<url>" "<utterance>"
DirectLine secret mode
node ${CLAUDE_SKILL_DIR}/../../scripts/directline-chat.bundle.js \
--directline-secret "<secret>" "<utterance>"
Multi-turn
node ${CLAUDE_SKILL_DIR}/../../scripts/directline-chat.bundle.js \
--token-endpoint "<url>" "<follow-up>" \
--conversation-id <id> --directline-token "<token>"
Always pass --directline-token when resuming. DirectLine tokens are bound to the conversation. They expire after ~30 min.
Output format
Same as /copilot-studio:chat-with-agent Phase 1a — see that skill for full documentation of JSON output, sign-in flow, and error handling.
Related Skills
microsoft/skills/validate
testing
VerifiedTrustedCommunity
Validate Copilot Studio agent YAML files using the LSP binary's full diagnostics (YAML structure, Power Fx, schema, cross-file references). Use when the user asks to check, validate, or verify YAML files.
192SKILL.mdUpdated Apr 30, 2026
microsoft/skills/test-auth
development
VerifiedTrustedCommunity
Authenticate for Copilot Studio evaluation API and SDK chat. Caches a token that is shared across run-eval and chat-sdk skills. Run this before any eval or SDK chat workflow. Requires an App Registration with MakerOperations and Copilots.Invoke permissions.
192SKILL.mdUpdated Apr 30, 2026
microsoft/skills/run-tests-kit
development
VerifiedTrustedCommunity
Run a batch test suite via the Copilot Studio Kit (Dataverse API). Uses the Power CAT Copilot Studio Kit to execute test cases against a published agent and produces pass/fail results with latencies. Requires the Kit installed in the environment, an App Registration with Dataverse permissions, and a published agent.
192SKILL.mdUpdated Apr 30, 2026
microsoft/skills/run-eval
development
VerifiedTrustedCommunity
Run evaluations against a Copilot Studio agent via the Power Platform Evaluation API. Works on DRAFT agents — no publish step required. Lists test sets, starts a run, polls until complete, fetches results, and proposes YAML fixes for failures. Use when the user wants to test agent changes without publishing.
192SKILL.mdUpdated Apr 30, 2026