Agent skill
vllm-slack-summary
Generate slack summaries of vLLM CI SIG Slack channel activity for the RHAIIS midstream release team
Install this agent skill to your Project
npx add-skill https://github.com/opendatahub-io/ai-helpers/tree/main/helpers/skills/vllm-slack-summary
SKILL.md
vLLM slack Summary Skill
Automates generating slack summaries of the vLLM CI SIG Slack channel for the Red Hat AI Inference Server (RHAIIS) team.
Prerequisites
- slackdump installed and authenticated with vLLM workspace
- Install: https://github.com/rusq/slackdump
- Auth: Run
slackdump workspace add
Usage
./scripts/generate_transcript.py # Last 7 days (default)
./scripts/generate_transcript.py --days 14 # Custom date range
./scripts/generate_transcript.py --output-dir out # Custom output directory
Context
When summarizing the transcript, focus on:
- Breaking changes affecting the RHAIIS midstream build
- Hardware issues with H100, A100, MI300, or B200 GPUs
- CI/CD infrastructure changes impacting test reliability
- Dependencies changes in build requirements or Python packages
- Performance regressions that could affect RHAIIS
- Upstream releases and their stability status
Output
The skill creates vllm_slack_summary/ containing:
vllm_slack_summary/
├── slack_export/ # Raw Slack export
├── transcript.md # Markdown transcript
└── slack_summary_YYYY-MM-DD_to_YYYY-MM-DD.md # Summary report
After generating the transcript, analyze it and create a summary with:
- Executive Summary (2-3 sentences)
- Key Issues & Resolutions
- CI/CD Infrastructure Changes
- Action Items for Red Hat Team
Troubleshooting
| Issue | Solution |
|---|---|
| slackdump not found | Ensure slackdump is in PATH: which slackdump |
| Authentication failed | Run slackdump workspace add |
| No messages found | Check date range; channel may have no messages in that period |
Quick Reference
- Channel ID: C07R5PAL2L9 (vLLM CI SIG)
- Transcript:
vllm_slack_summary/transcript.md - Summary:
vllm_slack_summary/slack_summary_YYYY-MM-DD_to_YYYY-MM-DD.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
python-packaging-env-finder
Investigate environment variables that can be set when building Python wheels for a given project. Analyzes setup.py, CMake files, and other build configuration files to discover customizable build environment variables.
torchtalk-analyzer
Analyze PyTorch internals across Python, C++, and CUDA layers using the TorchTalk MCP server. Use when asked about how PyTorch operators work internally, where functions are implemented, what would break if code is modified, or finding tests for PyTorch operators.
ai-bug-fix-triage
Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix.
python-packaging-complexity
Analyze Python package build complexity by inspecting PyPI metadata. Evaluates compilation requirements, dependencies, distribution types, and provides recommendations for wheel building strategies.
coderabbit-review
Evaluate CodeRabbit PR comments and fix or reply
git-shallow-clone
Perform a shallow clone of a Git repository to a temporary location.
Didn't find tool you were looking for?