stympy/slack-huddle-transcript
slack-huddle-transcript/SKILL.md
Extract and format Slack huddle transcripts for analysis. Use this skill when processing Slack huddle transcript files (.vtt), when user mentions huddle transcript or Slack transcript, when user uploads a VTT file from Slack, or when user asks to summarize or analyze a Slack meeting/huddle. Handles VTT format transcripts with speaker identification, timestamps, and conversation merging.
$ install --global
skillsauthnpx skillsauth add stympy/skills slack-huddle-transcriptInstall 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 15, 2026, 3:16 AM49.1s2 files scanned
SKILL.md
- name:
- slack-huddle-transcript
- description:
- Extract and format Slack huddle transcripts for analysis. Use this skill when processing Slack huddle transcript files (.vtt), when user mentions huddle transcript or Slack transcript, when user uploads a VTT file from Slack, or when user asks to summarize or analyze a Slack meeting/huddle. Handles VTT format transcripts with speaker identification, timestamps, and conversation merging.
Slack Huddle Transcript Processor
Parse and format Slack huddle transcripts into clean, readable output for analysis.
Quick Start
python scripts/parse_transcript.py <transcript.vtt> --format markdown
Getting Transcripts from Slack
Method 1: Download from Slack UI (Recommended)
- Open the Slack channel where the huddle occurred
- Find the huddle thread (shows as "Huddle" with participants)
- Click the thread to expand it
- Look for "Transcript" attachment
- Click the download icon (⬇️) to save as
.vttfile
Method 2: Slack API
# List recent files to find transcript
curl -H "Authorization: Bearer $SLACK_TOKEN" \
"https://slack.com/api/files.list?types=transcript"
# Download specific file
curl -H "Authorization: Bearer $SLACK_TOKEN" \
"https://slack.com/api/files.info?file=FILE_ID"
Method 3: Copy-Paste Raw VTT
If user provides raw VTT content, save to file first:
cat > /tmp/transcript.vtt << 'EOF'
<paste VTT content here>
EOF
Script Usage
Basic parsing (markdown output)
python scripts/parse_transcript.py transcript.vtt
Output formats
# Markdown (default) - best for reading/sharing
python scripts/parse_transcript.py transcript.vtt --format markdown
# JSON - best for further processing
python scripts/parse_transcript.py transcript.vtt --format json
# Plain text - minimal formatting
python scripts/parse_transcript.py transcript.vtt --format plain
Options
--no-merge: Keep all entries separate (default merges consecutive same-speaker entries)--title "Meeting Name": Custom title for markdown output--output file.md: Write to file instead of stdout--stdin: Read VTT content from stdin
VTT Format Reference
Slack huddle transcripts use WebVTT format:
WEBVTT
00:00:01.000 --> 00:00:05.000
Alice: Hey everyone, let's get started.
00:00:05.500 --> 00:00:08.000
Bob: Sounds good, I have a few updates.
The script automatically:
- Extracts speaker names from the text
- Merges consecutive same-speaker entries
- Formats timestamps for readability
- Generates participant summary
Common Workflows
Summarize a huddle
python scripts/parse_transcript.py meeting.vtt > meeting.md
# Then analyze meeting.md for key points, action items, decisions
Extract action items
Parse to JSON for programmatic extraction:
python scripts/parse_transcript.py meeting.vtt --format json | \
jq '.entries[] | select(.text | contains("action") or contains("TODO"))'
Compare multiple huddles
for f in huddle_*.vtt; do
python scripts/parse_transcript.py "$f" --format json > "${f%.vtt}.json"
done
Related Skills
stympy/research
development
VerifiedTrustedCommunity
Deep research before planning. Launches parallel agents to search docs, web, and codebase, then synthesizes findings into actionable context.
1SKILL.mdUpdated Apr 23, 2026
stympy/write-a-prd
development
VerifiedTrustedCommunity
This skill will be invoked when the user wants to create a PRD. You should go through the steps below. You may skip steps if you don't consider them necessary. 1. Ask the user for a long, detailed description of the problem they want to solve and any potential ideas for solutions. 2. Explore the repo to verify their assertions and understand the current state of the codebase. 3. Interview the user relentlessly about every aspect of this plan until you reach a shared understanding. Walk down e
1SKILL.mdUpdated Apr 15, 2026
stympy/refactor-pass
development
VerifiedTrustedCommunity
--- name: refactor-pass description: Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior. --- # Refactor Pass ## Workflow 1. Review the changes just made and identify simplification opportunities. 2. Apply refactors to: - Remove dead code and dead paths. - Straighten logic flows. - Remove excessive parameters. - Remove premature optimizati
1SKILL.mdUpdated Apr 15, 2026
stympy/prd-to-issues
development
VerifiedTrustedCommunity
# PRD to Issues Break a PRD into independently-grabbable GitHub issues using vertical slices (tracer bullets). ## Process ### 1. Locate the PRD Ask the user for the PRD GitHub issue number (or URL). Fetch it with `gh issue view <number>`. Read and internalize the full PRD content (with all comments). ### 2. Explore the codebase Read the key modules and integration layers referenced in the PRD. Identify: - The distinct integration layers the feature touches (e.g. DB/schema, API/backend, UI
1SKILL.mdUpdated Apr 15, 2026