Brokerage Screenshot Parser
sizheng v0.1.2
Publisher description
From the marketplace listing
Extract visible positions, transactions, orders, balances, gains, and option contract details from brokerage screenshots into Markdown tables and validated JSON.
Language: English · Automatically detected from descriptions.
Publisher keywords
Search terms declared by the publisher.
Matches for “structured-data”
Exact text from the indicated source. A mention alone does not establish support for your task.
Publisher keywords · listing
brokerage portfolio positions transactions screenshots structured-data
Files & skills
File archives
Skill instructions
parse-brokerage-screenshots3.26 KB
--- name: parse-brokerage-screenshots description: Parse E*TRADE, Robinhood, and other brokerage screenshots into validated position or transaction tables and structured JSON. Use when screenshots show portfolios, holdings, stocks, options, transactions, orders, balances, gains, market values, quantities, prices, or cost basis. --- # Brokerage Screenshot Parser Convert attached brokerage screenshots into accurate structured data. Read [references/output-schema.json](references/output-schema.json) when producing JSON. ## Parse safely - Extract only information visible in the screenshots. - Never guess, extrapolate, calculate, or reconstruct cropped, obscured, or ambiguous values. - Use `null` for unavailable values. - Preserve negative signs and displayed decimal precision. - Normalize monetary values to JSON numbers without currency symbols or thousands separators. - Treat color as sign evidence only when the interface makes that meaning unambiguous. - Normalize complete dates to `YYYY-MM-DD`. Preserve incomplete date text separately and leave the normalized date `null`. - Add a warning for every cropped, ambiguous, or low-confidence field. - Do not provide investment advice, predictions, recommendations, or performance interpretations unless separately requested. ## Protect sensitive data Redact passwords, PINs, authentication codes, API keys, recovery codes, full account numbers, bank details, and authentication QR codes as `"[REDACTED]"`. Redact personal and account identifiers from output unless the user explicitly requests their inclusion. ## Classify the screen Identify the broker, screen type, account type, currency, and screenshot sequence. Use one of: - `portfolio_positions` - `transaction_history` - `order_history` - `balances` - `unknown` ## Parse instruments Classify each instrument as `stock`, `option`, `etf`, `cash`, `cryptocurrency`, or `unknown`. For stocks and ETFs, extract visible symbol, description, quantity, last price, average price, cost basis, market value, day gain, total gain, and percentages. For options, also extract the underlying symbol, expiration date, strike price, call or put type, and contract count. Do not infer quantity, cost basis, market value, or gains from other values unless the user explicitly requests calculations. For transactions and orders, extract visible dates, symbol, instrument type, action, quantity, price, amount, fees, status, order type, limit or stop price, option details, and description. Keep multiple fills separate. ## Merge screenshots When screenshots overlap: 1. Match rows using symbol, instrument details, expiration, strike, option type, and visible values. 2. Merge complementary columns from matching rows. 3. Do not duplicate overlapping rows. 4. Preserve conflicting readings and flag them instead of choosing silently. 5. Never combine rows merely because they share a ticker. ## Respond 1. Provide a concise Markdown table of the most important visible fields. 2. Provide JSON conforming to `references/output-schema.json`. 3. Briefly state what was extracted, what was missing or cropped, and what screenshot would complete the data. 4. Remind the user to verify extracted values before relying on them. Set confidence from `0.0` to `1.0`, reducing it for blurry, cropped, covered, or ambiguous text.
Referenced files: 1
Package details
Publisher declarations from the archived package. These are separate from our research and the live service's terms.
- Package author
- sizheng
- Keywords
- See publisher keywords
Declared capabilities
- Vision
- Structured output
Package observed Oct 4, 2026.
Technical details
- First seen
- Sep 30, 2026 · 22:02 UTC
- Last seen
- Oct 5, 2026 · 06:00 UTC
- Collection status
- Collected
plugins_6a8dc61d7094819197d1a75365eb4137
Download plugin data (JSON)Before you connect Brokerage Screenshot Parser
How do I connect it?
Open the publisher's marketplace listing to check current availability and follow its connection instructions. This directory does not install plugins. Check the requested access and any account requirements before connecting.
Check marketplace availability ↗
Does it require paid access?
We have not established the pricing or subscription requirements for this plugin. An absent price does not mean free access.
Compare researched pricing and access models →
How can I evaluate it?
Check the declared skills and available files, then try a small task whose result you can verify. Our archived descriptions and instructions establish publisher claims, not tested runtime quality. Review sources and coverage limits.