agentleFS
AtmoskunAtmoskun/claude-skills/skills/organizer-transcript/SKILL.md

organizer-transcript

Skill0 starsChanged 9 months agoMITView on GitHub

Earnings Transcript Organizer - Organize FactSet/Callstreet transcript PDFs from Downloads into company folders

  • Reads credentials

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Auto-refreshes browser: when new transcripts are organized

    line 32
  2. Distinctive:

    Search by ticker or company name

    line 36
  3. Distinctive:

    When user asks to analyze a company:

    line 77
  4. Very specific:

    Read the transcript PDFs from Downloads/Earnings Transcripts/{Company} ({TICKER})/

    line 78
  5. Distinctive:

    Start browser at http://localhost:8008

    line 85
  6. Distinctive:

    Add comments → Save to Obsidian

    line 88

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Earnings Transcript Organizer

Organizes earnings call transcript PDFs from Downloads into structured company folders. Includes a web browser for viewing transcripts, generating analysis prompts, and running AI analysis with Obsidian integration.

Project Location

~/.claude\skills\organizer-transcript

When to Use This Skill

  • User wants to organize transcript files
  • User mentions earnings transcripts or call transcripts
  • User wants to clean up downloaded PDFs
  • User says "organize transcripts" or "transcript organizer"
  • User wants to browse transcripts or generate analysis prompts
  • User wants to analyze earnings with Claude or Gemini
  • User says "analyze [TICKER]" or "transcript analysis"

What It Does

1. Organizer

  • Scans Downloads folder for transcript PDFs
  • Extracts company name and ticker from filename
  • Creates company folders: {Company Name} ({TICKER})
  • Moves PDFs into appropriate folders
  • Updates job registry with run stats
  • Auto-refreshes browser when new transcripts are organized

2. Browser (http://localhost:8008)

  • Browse all 600+ companies with transcripts
  • Search by ticker or company name
  • Recently added transcripts appear first with "NEW" badge
  • Select quarters and generate analysis prompts
  • Direct AI Analysis - Analyze with Gemini 2.5 Pro (button in browser)
  • Obsidian Integration - Analyses saved to Obsidian Vault/研究/财报分析/
  • Save company-specific notes and follow-up questions
  • Track analysis history with AI responses and comments

3. Claude Analysis (Direct in Claude Code)

For Claude Opus 4.5 analysis, use this skill directly:

/organizer-transcript analyze TICKER Q1 2025 Q4 2024

Claude Code will read the PDFs and provide analysis - no API key needed!

Key Files

FilePurpose
organize_transcripts.pyMain organizer script
browser/app.pyFastAPI browser backend (port 8008)
browser/indexer.pyTranscript indexer
browser/obsidian.pyObsidian vault writer
browser/ai_provider.pyAI provider abstraction
browser/data/Notes, history, recent additions
browser/.envAPI keys (Gemini configured)

Commands

Organize Transcripts

python "~/.claude/skills/organizer-transcript/organize_transcripts.py"

Start Browser

cd "~/.claude/skills/organizer-transcript/browser" && python app.py

Then open http://localhost:8008

Direct Claude Analysis

When user asks to analyze a company:

  1. Read the transcript PDFs from Downloads/Earnings Transcripts/{Company} ({TICKER})/
  2. Apply the analysis prompt template
  3. Provide structured analysis directly in conversation

Workflow Options

Option A: Web Browser (Gemini)

  1. Start browser at http://localhost:8008
  2. Select company and quarters
  3. Click "Analyze with Gemini 2.5 Pro"
  4. Add comments → Save to Obsidian

Option B: Claude Code (Claude Opus 4.5)

  1. User: "analyze WOSG Q2 2026 vs Q4 2025"
  2. Claude Code reads PDFs directly
  3. Returns structured analysis
  4. User can save to Obsidian via browser

Browser Features

FeatureDescription
Company SearchSearch by ticker or name
Recently AddedNew transcripts appear first with green badge
Company NotesSave background notes per company
Follow-up QuestionsTrack questions for next quarter's analysis
Analysis HistoryStore AI responses and your comments
Quick Select"Latest 2 Quarters" or "All Earnings" buttons
Direct AI AnalysisGemini 2.5 Pro button (1-2 min)
Obsidian SaveAuto-saves to 研究/财报分析/{TICKER}/
Open in ObsidianClick to open analysis in Obsidian app

Obsidian Integration

Analyses are saved to:

~/Documents\Obsidian Vault\研究\财报分析\
└── {TICKER}/
    ├── 2026-02-04 1630 TICKER Q2 2026 vs Q4 2025 Analysis.md
    └── _TICKER Notes.md

Each analysis file includes:

  • YAML frontmatter with tags
  • AI analysis content
  • User comments
  • Follow-up questions (auto-extracted)
  • Source transcript references

API Configuration

API keys in browser/.env:

GOOGLE_API_KEY=...  # For Gemini (configured)
ANTHROPIC_API_KEY=... # For Claude API (optional)

Note: Claude analysis via Claude Code doesn't need an API key!

Input

Transcript PDFs in Downloads matching patterns:

  • CORRECTED TRANSCRIPT_*.pdf
  • TRANSCRIPT_*.pdf
  • CALLSTREET REPORT_*.pdf
  • *earnings call*.pdf

Output

  • Organized folders at ~/Downloads\Earnings Transcripts\{Company} ({Ticker})\
  • Analysis files in ~/Documents\Obsidian Vault\研究\财报分析\

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.