← Back to Skills Marketplace
260
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install meetingsummarizer
Description
Transcribe meetings with SenseAudio ASR speaker diarization, timestamps, and meeting-note extraction workflows. Use when users need meeting transcription, me...
Usage Guidance
This skill appears coherent for using SenseAudio to transcribe meetings. Before installing: 1) Only provide the SenseAudio API key (SENSEAUDIO_API_KEY); do not reuse highly privileged keys if you can issue a restricted key. 2) Confirm you trust https://senseaudio.cn and are comfortable sending audio/transcripts to that service (transcripts can contain sensitive data). 3) Be aware the skill will install Python packages requests and websockets (normal for this use). 4) If you want LLM-based summaries, provide a separate LLM credential as recommended; the skill will not assume other provider keys. If you want extra assurance, review your API key permissions/rotation policy and inspect network traffic or environment handling in your runtime before granting the key.
Capability Analysis
Type: OpenClaw Skill
Name: meetingsummarizer
Version: 1.0.2
The skill is a standard integration for the SenseAudio ASR service, providing meeting transcription and summarization capabilities. It uses the 'requests' and 'websockets' libraries to communicate with official endpoints (api.senseaudio.cn) and follows security best practices by handling API keys via environment variables and headers. The instructions in SKILL.md focus on local processing and data privacy, with no evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description, required binary (python3), required env var (SENSEAUDIO_API_KEY), and declared install packages (requests, websockets) match a Python-based client for SenseAudio ASR. Nothing requested appears unrelated to meeting transcription.
Instruction Scope
SKILL.md instructs the agent to read only the SENSEAUDIO_API_KEY, call SenseAudio HTTP and WebSocket endpoints, and perform local transcript summarization. It does not instruct reading unrelated files, other env vars, or posting data to third-party endpoints beyond the documented SenseAudio API.
Install Mechanism
Install spec only lists common Python packages (requests, websockets). There are no arbitrary URL downloads or archive extraction steps; risk from installation is low and proportional to a Python helper.
Credentials
Only a single credential (SENSEAUDIO_API_KEY) is required and used as the Bearer token for SenseAudio API calls; this is appropriate for the stated functionality and is explained in the docs.
Persistence & Privilege
Skill is not marked always:true, does not request system-wide config changes, and is instruction-only (no bundled code modifying other skills). Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install meetingsummarizer - After installation, invoke the skill by name or use
/meetingsummarizer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Version 1.0.2
- Clarified official SenseAudio ASR API usage and model constraints in documentation.
- Summarized rules and removed specific file path references from protocol guidance.
- No changes to code or functionality; documentation improvement only.
v1.0.1
Version 1.0.1
- Clarified ASR model, endpoint, and workflow rules for HTTP and WebSocket meeting transcription.
- Added precise credential usage instructions and strengthened security notes (never log or expose API keys).
- Specified that all default summarization and extraction must be done locally—external LLMs only if explicitly requested by the user.
- Documented output formats, error handling, and provider constraints for improved reliability and user transparency.
- Updated dependency and installation steps for Python helpers.
- Streamlined and clarified recommended patterns for action item and decision extraction based on transcripts.
v1.0.0
- Major update: Now supports full audio transcription with speaker identification, intelligent summaries, and action item extraction.
- Replaces previous script-based workflow; removed example-output.md and summarize.sh files.
- Added step-by-step API usage guide, complete code samples for Python integration, and advanced features like real-time transcription, sentiment analysis, and multi-language support.
- Requires SENSEAUDIO_API_KEY instead of ANTHROPIC_API_KEY.
- Expanded documentation with implementation, output formatting, and actionable meeting analytics.
Metadata
Frequently Asked Questions
What is Meeting Summarizer?
Transcribe meetings with SenseAudio ASR speaker diarization, timestamps, and meeting-note extraction workflows. Use when users need meeting transcription, me... It is an AI Agent Skill for Claude Code / OpenClaw, with 260 downloads so far.
How do I install Meeting Summarizer?
Run "/install meetingsummarizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Meeting Summarizer free?
Yes, Meeting Summarizer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Meeting Summarizer support?
Meeting Summarizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Meeting Summarizer?
It is built and maintained by scikkk (@scikkk); the current version is v1.0.2.
More Skills