transcript-search

casper-studios/casper-marketplace · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/casper-studios/casper-marketplace --skill transcript-search
0 commentsdiscussion
summary

Search and retrieve meeting transcripts from Fireflies.ai and Google Drive with full text and speaker attribution.

skill.md

Transcript Search

Overview

Search and retrieve meeting transcripts from Fireflies.ai and Google Drive with full text and speaker attribution.

Quick Decision Tree

Where are your transcripts?
├── Fireflies.ai (API)
│   └── references/fireflies.md
│   └── Script: scripts/fireflies_transcript_search.py
└── Google Drive (uploaded files)
    └── references/drive-transcripts.md
    └── Script: scripts/gdrive_transcript_search.py

Environment Setup

# For Fireflies
FIREFLIES_API_KEY=your_api_key

# For Google Drive
# OAuth credentials (mycreds.txt) - see google-workspace skill

Get Fireflies API key: https://app.fireflies.ai/integrations (Custom Integrations)

Common Usage

Search Fireflies by Company

python scripts/fireflies_transcript_search.py "Microsoft" --days-back 30

Get Full Transcript

python scripts/fireflies_transcript_search.py --id 01KCM2G0YX1GMPWYQ8GPAABBCK --content

Save Formatted Transcript

python scripts/fireflies_transcript_search.py --id abc123 --content --save transcript.md

Search Drive Transcripts

python scripts/gdrive_transcript_search.py "Acme Corp" --days 30

Output Formats

Search Results

  • Transcript ID, title, date, duration
  • AI-generated summary, keywords, action items
  • Speaker list with names

Full Transcript

  • Complete text with speaker labels
  • Timestamps for each sentence
  • Formatted markdown output

Cost

Service Cost
Fireflies API Free (with subscription)
Google Drive Free

Security Notes

Credential Handling

  • Store FIREFLIES_API_KEY in .env file (never commit to git)
  • Google OAuth credentials for Drive (see google-workspace skill)
  • Regenerate Fireflies API key via Custom Integrations if compromised
  • Never log or print API keys in script output

Data Privacy

  • Transcripts contain verbatim meeting conversations
  • Speaker names and voices are identifiable
  • Business discussions may include confidential information
  • Action items and summaries capture sensitive decisions
  • Avoid sharing full transcripts without authorization

Access Scopes

  • Fireflies API: Full access to transcripts user has access to
  • Google Drive: Access to uploaded transcript files
  • Transcripts inherit meeting participants' access permissions

Compliance Considerations

  • Recording Consent: Ensure all meeting participants consent to recording
  • Speaker Privacy: Transcripts identify speakers by name
  • Confidential Meetings: Some meetings should not be transcribed
  • GDPR: Meeting recordings containing EU participants require consent
  • Data Retention: Follow policies for transcript retention/deletion
  • Legal Holds: Transcripts may be subject to legal discovery
  • Client Confidentiality: Client meeting content is sensitive
  • Internal Use Only: Mark transcripts as confidential where appropriate

Troubleshooting

Common Issues

Issue: Transcript not found

Symptoms: "Transcript not found" error with known meeting Cause: Invalid transcript ID, no access, or not yet processed Solution:

  • Verify transcript ID from Fireflies dashboard
  • Check if recording is still processing (wait and retry)
  • Ensure API key has access to the transcript
  • Confirm meeting was actually recorded and transcribed

Issue: API unauthorized

Symptoms: 401 error or "invalid API key" Cause: API key expired, invalid, or not set Solution:

  • Regenerate API key at https://app.fireflies.ai/integrations
  • Verify FIREFLIES_API_KEY is set correctly in .env
  • Check for leading/trailing whitespace in key
  • Ensure Custom Integration is enabled in Fireflies

Issue: Empty search results

Symptoms: Search returns no transcripts despite existing meetings Cause: Search query too narrow, date range issue, or access restrictions Solution:

  • Broaden search query (fewer keywords)
  • Expand date range with --days-back parameter
  • Check if transcripts are shared with your account
  • Verify search is using correct field (title, participants, content)

Issue: Missing transcript content

Symptoms: Metadata returned but full content is empty Cause: Transcript still processing or content access restricted Solution:

  • Wait for transcript processing to complete (check Fireflies dashboard)
  • Use --content flag explicitly to request full transcript
  • Verify subscription tier includes API content access
  • Check if transcript has processing errors

Issue: Speaker attribution missing

Symptoms: Transcript text present but speakers not identified Cause: Low audio quality or speakers not enrolled Solution:

  • Speaker identification depends on audio quality
  • Enroll frequent speakers in Fireflies for better recognition
  • This is a Fireflies processing issue, not API issue
  • Re-upload recording if possible with better audio

Issue: Google Drive transcript search fails

Symptoms: Can't find transcripts stored in Drive Cause: OAuth issue, folder structure, or file format Solution:

  • Verify Google OAuth is working (see google-workspace skill)
  • Check transcripts are in searchable folder
  • Ensure transcripts are in readable format (txt, md, docx)
  • Search by exact filename if full-text search fails

Resources

  • references/fireflies.md - Fireflies.ai API guide
  • references/drive-transcripts.md - Drive transcript search

Integration Patterns

Transcript to Summary

Skills: transcript-search → content-generation Use case: Create meeting summaries and action item docs Flow:

  1. Retrieve full transcript from Fireflies
  2. Extract key discussion points and decisions
  3. Generate formatted summary document via content-generation

Transcript to Voice Agent

Skills: transcript-search → voice-agents Use case: Build context-aware voice agents Flow:

  1. Search for past meetings with client
  2. Extract relationship history and previous discussions
  3. Include context in voice agent prompt for personalized calls

Transcript to CRM

Skills: transcript-search → attio-crm Use case: Add meeting notes to CRM records Flow:

  1. Search transcripts for client meetings
  2. Extract summary, action items, and key quotes
  3. Create note on Attio company record with meeting details
how to use transcript-search

How to use transcript-search on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add transcript-search
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/casper-studios/casper-marketplace --skill transcript-search

The skills CLI fetches transcript-search from GitHub repository casper-studios/casper-marketplace and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/transcript-search

Reload or restart Cursor to activate transcript-search. Access the skill through slash commands (e.g., /transcript-search) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.849 reviews
  • Ganesh Mohane· Dec 24, 2024

    transcript-search reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Ama Rao· Dec 16, 2024

    transcript-search fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Dev Mensah· Dec 8, 2024

    I recommend transcript-search for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Neel Park· Dec 8, 2024

    We added transcript-search from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.

  • Chinedu Reddy· Nov 27, 2024

    transcript-search reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Ama Ghosh· Nov 27, 2024

    Keeps context tight: transcript-search is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Rahul Santra· Nov 15, 2024

    I recommend transcript-search for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Henry Martinez· Nov 15, 2024

    transcript-search has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Ama Nasser· Nov 7, 2024

    transcript-search is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Mei Wang· Nov 3, 2024

    Solid pick for teams standardizing on skills: transcript-search is focused, and the summary matches what you get after install.

showing 1-10 of 49

1 / 5