trader-copycat

1# trader-copycat
2 
3Copying an investor starts with what they are legally required to show: a
413F-HR, filed with the SEC every quarter by any investment manager with over
5$100 million in US-listed stocks and other 13(f) securities. This skill reads
6it straight from SEC EDGAR, rebuilds the portfolio, and turns it into target
7weights for your own account.
8 
9Tool in this folder (standard library Python, no keys):
10 
11```bash
12python3 "${CLAUDE_SKILL_DIR}/edgar13f.py" --help
13```
14 
15SEC asks every program to identify itself with a name and email. Set it once
16in `trader/config.json` (`"sec_user_agent": "Your Name you@example.com"`, with
17the user's real name and email) or `export SEC_USER_AGENT=...`. The tool
18refuses to call SEC without it and says how to fix it. Ask the user for it;
19never invent one.
20 
21## What it writes
22 
23- `trader/targets.json`: the weights to copy, in the shape every other trader
24  skill reads: `{ "source", "as_of", "weights": [ {"ticker", "name",
25  "weight"} ] }`, weights in % with 2 decimals summing to 100 over the stock
26  sleeve (keep the 2 decimals: budget sizing needs them), plus the
27  13F share, value, CUSIPs, what was skipped and why, and the caveats.
28- `trader/tickers.json` (optional, yours): CUSIP to ticker fixes the tool
29  will always use first, as `{"650111107": "NYT"}`.
30 
31`targets.example.json` in this folder is the real output of the reel's run
32(Berkshire, top 5).
33 
34## The rules
35 
36- **Say how old the data is, every time.** A 13F is a snapshot of the last
37…