supply-chain
Skill0 starsChanged 9 months agoMITView on GitHub
Supply Chain Cross-Reference - Extract and index company mentions from earnings transcripts to map supply chain relationships
9 other projects use a version of this.
Adopted by
Most recently taken up by
- mrhlaingbwardev/agentic-hacking-skillstheir own version, first seen Nov 8, 2026
- nimadorostkar/Claude-Skills-collectiontheir own version, first seen Oct 13, 2026
- nitinjain999/platform-skillstheir own version, first seen Oct 13, 2026
- padamson/playwright-rusttheir own version, first seen Oct 8, 2026
- daloopa/investingtheir own version, first seen Oct 8, 2026
- kapadias/nonnatheir own version, first seen Oct 1, 2026
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- daloopa/investing★ 488same name
- mrhlaingbwardev/agentic-hacking-skills★ 347same name
- padamson/playwright-rust★ 166same name
- nitinjain999/platform-skills★ 71same name
- nimadorostkar/Claude-Skills-collection★ 37same name
- thejefflarson/soundcheck★ 20same name
- poorvith-mp/skills-business★ 1same name
- conjure-3301/skills★ 0same name
- kapadias/nonna★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- 13fSkill
- info-lake-healthSkill
- calendarSkill
- chatgpt-organizerSkill
- chatgptSkill
- exploreSkill
- flashbackSkill
- GANSkill
- kbSkill
- learnSkill
- linkSkill
- meeting-backtestSkill
- meeting-transcriptSkill
- mocSkill
- notebooklmSkill
- organizer-transcriptSkill
- planSkill
- podcastSkill
- podwise-downloaderSkill
- portfolioSkill
- prompt-optimizerSkill
- researchSkill
- reviewSkill
- socratic-writerSkill
- substackSkill
- telegramSkill
- thesisSkill
- tradeSkill
- vault-healthSkill
- wechat-haoSkill
- x-bookmarksSkill
- xueqiuSkill
- youtube-downloaderSkill
The file
Files
Supply Chain Cross-Reference
Extracts company-to-company mentions from earnings call transcripts, building a mention index that maps who talks about whom. v0 scope: mention index only (who mentions whom + verbatim quote). No relationship classification yet.
Project Location
~/.claude\skills\supply-chain
When to Use This Skill
- User says
/supply-chain TICKER— show all mentions of/by a ticker - User says
/supply-chain scan— process new earnings transcripts - User says
/supply-chain stats— show database statistics - User asks about supply chain relationships or company mentions
- User wants to know which companies mention a specific ticker
Commands
/supply-chain TICKER
Show all mentions of a company across earnings transcripts.
What it does:
- Queries the mention database for the given ticker
- Shows two tables: "Mentioned By" (who talks about TICKER) and "Mentions" (who TICKER talks about)
- Includes verbatim quotes and speaker roles
Execution:
python "~/.claude/skills/supply-chain/mention_extractor.py" query TICKER/supply-chain scan
Process all new (unprocessed) earnings transcripts.
What it does:
- Scans
Downloads/Earnings Transcripts/for all PDF files - Skips already-processed transcripts
- Extracts text with pdfplumber, chunks by speaker turn
- Calls Gemini 2.0 Flash to extract company mentions
- Resolves entities via shared dictionary
- Stores in SQLite with verbatim quotes
Execution:
python "~/.claude/skills/supply-chain/mention_extractor.py" scan/supply-chain stats
Show database statistics: total mentions, transcripts processed, top mentioned companies.
Execution:
python "~/.claude/skills/supply-chain/mention_extractor.py" statsKey Files
| File | Purpose |
supply_chain_db.py | SQLite database layer (schema, CRUD) |
mention_extractor.py | Core pipeline: PDF -> chunks -> Gemini -> mentions |
supply_chain_obsidian.py | Generate Obsidian notes from mention database |
data/supply_chain.db | SQLite database (auto-created) |
Architecture
Downloads/Earnings Transcripts/
└── {Company} ({Ticker})/
└── *.pdf
│
▼
mention_extractor.py
├── pdfplumber (text extraction)
├── chunk_by_speaker (speaker turns, ~2000 tokens)
├── Gemini 2.0 Flash (mention extraction)
└── entity_resolver (dictionary lookup)
│
▼
supply_chain_db.py
└── data/supply_chain.db
│
▼
supply_chain_obsidian.py
└── Obsidian Vault/Supply Chain/{TICKER}_mentions.mdDependencies
pdfplumber— PDF text extractiongoogle-genai— Gemini API (new SDK)python-dotenv— Load API keys- Shared:
entity_resolver.py,entity_dictionary.yaml
v0 Scope (Mention Index)
Included:
- Extract explicit company name mentions from transcripts
- Verbatim quote context for each mention
- Speaker role (CEO/CFO/analyst/other)
- Entity resolution via dictionary
- Obsidian note generation with mention tables
Not yet included (future versions):
- Relationship classification (supplier/customer/competitor/partner)
- Sentiment analysis of mentions
- Time-series tracking of mention frequency
- Automatic entity dictionary expansion
- Cross-reference with 13F holdings data
Output
- Database:
~/.claude\skills\supply-chain\data\supply_chain.db - Obsidian notes:
~/Documents\Obsidian Vault\Supply Chain\{TICKER}_mentions.md
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
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.

