directline-chat
DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.
- License 许可
- MIT
- 最近更新
- 2026-11-05
- Stars
- ★ 490
- Forks
- 102
01 前言 Front Matter
- agent
- copilot-studio-test
- context
- fork
- description
- DEPRECATED: Use /copilot-studio:chat-with-agent instead — it auto-detects DirectLine vs M365 mode. This skill is kept for backwards compatibility only.
- allowed-tools
- Bash(node *directline-chat.bundle.js *), Bash(node *manage-agent.bundle.js detect-mode *), Read, Glob, Grep
- argument-hint
- <utterance to send>
- user-invocable
- false
02 资源文件 3
- 参考文档agents/openai.yaml87 B
- 参考文档mocking.md1.4 KB
- 参考文档tests.md2.2 KB
03 SKILL.md 正文
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.
04 同仓库更多 Skills
validate
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.
test-auth
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.
run-tests-kit
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.
run-eval
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.
new-topic
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.
manage-agent
Push/pull Copilot Studio agent content via the VS Code extension's LanguageServerHost LSP binary. Handles authentication (interactive browser login for push/pull, device code flow for chat token), sync push, sync pull, clone, and diff operations.