$ loading_
Preview local channel message flow fixtures to inspect conversation flow behavior.
Overall risk is low: the skill is open-source, widely adopted, and does not request additional secrets or declare external hosts. The main caveat is that the description indicates real message sends/edits/deletes to a Telegram target when used in the corresponding repo/environment.
The material explicitly states 'no required secrets/environment variables,' and does not ask the user to provide new API keys, tokens, or other sensitive credentials. The README mentions an optional account id and Telegram target only; no direct credential abuse risk is evidenced in the provided material.
The README clearly states that it performs real sends/edits/deletes against the configured channel target, and currently only `--channel telegram` is implemented. This means message content may be sent out to a Telegram target during use, but this is within the declared functionality and no unknown or unrelated endpoints are indicated.
The system's objective checks mark this as `prompt-only`, and the material does not show the skill itself requesting extra system privileges or exposing general command execution. The Node command in the README appears to be a repo-internal development usage example rather than independent execution capability requested by the skill.
The description says it is used to preview local channel message flow fixtures, and there is no stated broad read/write access to local files, databases, or other resources. The material does not indicate data access beyond the message preview/sending scenario or any obvious over-privilege.
The source is an open-source GitHub repository, the system marks it as `open-source`, and community adoption is very high (about 377k stars), all of which are strong risk-reducing signals. Although the license is unspecified and maintenance status is unknown, the supply-chain risk is overall low due to auditable source code and strong community signals.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "channel-message-flows" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/channel-message-flows/SKILL.md 2. Save it as ~/.claude/skills/channel-message-flows/SKILL.md 3. Reload skills and tell me it's ready
Load the local channel message flow fixture and preview each message in sequence, showing sender, timestamp, and status changes.
A chronological preview of the message flow for checking UI and flow correctness.
Preview this local message flow fixture and focus on whether failed send, retry success, and read states transition as expected.
A preview highlighting abnormal nodes and state transitions to help find flow issues.
Preview two local channel message flow fixtures separately and summarize differences in message order, state changes, and rendering.
A visual comparison and difference summary of two message flows for version review.
Use this from the OpenClaw repo root to send canned channel preview flows while iterating on message UX. These are real sends/edits/deletes against the configured channel target.
Native Telegram sendMessageDraft tool progress, then a final answer:
node --import tsx scripts/dev/channel-message-flows.ts \
--channel telegram \
--target <telegram-chat-id> \
--flow working-final \
--duration-ms 20000
Thinking preview, then a final answer:
node --import tsx scripts/dev/channel-message-flows.ts \
--channel telegram \
--target <telegram-chat-id> \
--flow thinking-final
--account <accountId>: Telegram account id when not using the default.--thread-id <id>: Telegram forum topic/message thread id.--delay-ms <ms>: Override preview update cadence.--duration-ms <ms>: Simulated working duration for working-final.--final-text <text>: Override the durable final message.--target is the numeric Telegram chat id.working-final exercises native Telegram sendMessageDraft with static Working status and sample tool progress.thinking-final exercises formatted Thinking reasoning preview clearing before the final answer.--channel telegram is implemented for now.Transcribe audio into text or speaker-separated transcripts with OpenAI APIs.
Automate web page workflows, login checks, tab handling, and recovery steps.
Generate concept, architecture, flow, and whiteboard diagrams in multiple formats.
Helps maintainers triage, clean up, and resolve OpenClaw secret scanning alerts.
Investigate test memory growth, heap leaks, and OOM root causes.
Run, debug, monitor, and summarize OpenClaw release CI workflows.
Check feature flags, compare channels, and debug inconsistent release behavior.
Expose local Flowise chatflows as MCP tools for listing and execution.
Manage instantKOM messaging resources and analytics through type-safe AI tool calls.
Configure and manage agents, skills, prompts, and integrations in the editor.
Build Zoom Team Chat integrations, bots, and interactive messaging experiences.
Run Flow type checks and fix React type errors quickly.