$npx -y skills add SKE-Labs/agent-trading-skills --skill insider-activity-tradingParse and evaluate SEC insider filings as delayed contextual evidence. Use when analyzing Form 4 codes, holdings changes, footnotes, amendments, purchase/sale clusters, and 10b5-1 disclosures.
| 1 | # Insider Activity Trading |
| 2 | |
| 3 | Use insider filings as delayed, contextual evidence. A transaction may reflect valuation views, compensation, taxes, liquidity needs, ownership policy, or a trading plan; it does not reveal motive by itself. |
| 4 | |
| 5 | ## Filing Fields |
| 6 | |
| 7 | Record issuer, insider role, filing and transaction timestamps, direct/indirect ownership, transaction code, price, shares, post-transaction holdings, footnotes, derivative status, and 10b5-1 disclosure. Confirm amendments and avoid double counting the same beneficial owner. |
| 8 | |
| 9 | ## Signal Interpretation |
| 10 | |
| 11 | ### Open-Market Purchases |
| 12 | |
| 13 | | Factor | Stronger Signal | |
| 14 | | --- | --- | |
| 15 | | Multiple independent insiders buying | Candidate cluster; define window before testing | |
| 16 | | Large purchases | Meaningful % of holdings | |
| 17 | | After price drop | Buying the dip | |
| 18 | | C-suite buying | CEO/CFO conviction | |
| 19 | |
| 20 | ### Sales and Other Codes |
| 21 | |
| 22 | Separate open-market purchases/sales (`P`/`S`) from grants, option exercises, tax withholding, gifts, and other codes. Read footnotes and plan disclosures; even an open-market purchase or sale has an unobserved motive. |
| 23 | |
| 24 | | Selling Reason | Signal Strength | |
| 25 | | --- | --- | |
| 26 | | Planned (10b5-1) | Contextual; inspect adoption date, terms, and amendments | |
| 27 | | Diversification | Weak negative | |
| 28 | | After big run-up | Moderate negative | |
| 29 | | Unusual amount | Stronger negative | |
| 30 | | Multiple C-suite selling | Candidate cluster requiring plan/code/holdings context | |
| 31 | |
| 32 | ## Bullish vs Bearish Patterns |
| 33 | |
| 34 | | Bullish | Bearish | |
| 35 | | --- | --- | |
| 36 | | CEO buying the dip | Multiple C-suite selling | |
| 37 | | Independently defined purchase cluster | Selling right after guidance | |
| 38 | | Large $ purchases on weakness | Unusual volume of sales | |
| 39 | | Buying after bad news | Selling before scheduled news | |
| 40 | |
| 41 | ## Workflow |
| 42 | |
| 43 | ### 1. Research Insider Activity |
| 44 | |
| 45 | ``` |
| 46 | get_financial_news(topic="AAPL insider buying selling SEC Form 4 filing", max_results=15) |
| 47 | get_fundamentals(ticker="AAPL") |
| 48 | ``` |
| 49 | |
| 50 | Look for: recent Form 4 filings, transaction size, buyer/seller role, and whether purchases are scheduled (10b5-1) or discretionary. |
| 51 | |
| 52 | ### 2. Assess Pattern |
| 53 | |
| 54 | - Single insider selling = low signal, check if 10b5-1 planned |
| 55 | - Single insider buying = moderate signal, check size relative to holdings |
| 56 | - Purchase cluster = count independent insiders within a predeclared window and compare with issuer history |
| 57 | - C-suite selling unusual amounts = red flag, investigate further |
| 58 | |
| 59 | ### 3. Combine with Fundamentals |
| 60 | |
| 61 | Insider activity is a confirming signal, not standalone. Cross-reference with company fundamentals, recent earnings, and technical setup before acting. |
| 62 | |
| 63 | ## Evidence and Validation |
| 64 | |
| 65 | - Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes. |
| 66 | - Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried. |
| 67 | - Include spread, fees, slippage, borrow or funding, partial fills, and latency. Reject the setup when net expectancy is not positive or depends on one narrow parameter. |
| 68 | - Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status. |
| 69 | - Research basis: The [SEC Form 3/4/5 bulletin](https://www.sec.gov/file/forms-3-4-5pdf) explains codes and two-business-day reporting, while the [10b5-1 rule](https://www.sec.gov/rules-regulations/2022/12/insider-trading-arrangements-related-disclosures) requires plan-related disclosures. |
| 70 | |
| 71 | ## Key Rules |
| 72 | |
| 73 | - Never trade on a headline; parse the filed form, codes, footnotes, ownership, and amendments. |
| 74 | - Do not equate a 10b5-1 label with neutrality or a transaction with a disclosed motive. |
| 75 | - Normalize transaction value by prior holdings, compensation, market capitalization, and insider history. |
| 76 | - Use filing availability time—not transaction time—to prevent look-ahead bias; Form 4 is generally due within two business days, subject to form rules. |
| 77 | - Define cluster windows and event exclusions before testing; report `no trade` when context is missing. |
| 78 | |
| 79 | ## Related Skills |
| 80 | |
| 81 | - **earnings-trading** -- Insider activity around earnings signals management confidence |
| 82 | - **sentiment-analysis** -- Insider buying is a high-credibility input to sentiment scoring |