insider-activity-trading
Skill17 starsChanged 4 months agoApache-2.0View on GitHub
Parse 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 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- IngAs8/ClaudeSkilledited, first seen Sep 28, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- IngAs8/ClaudeSkill★ 044% same
Wrote their own version · 0
None found.
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 repository56 other files it gives its agents.
- candlestick-patternsSkill
- channel-tradingSkill
- cup-and-handleSkill
- double-top-bottomSkill
- flag-pennantSkill
- head-and-shouldersSkill
- triangle-patternsSkill
- wedge-patternsSkill
- altcoin-rotationSkill
- arbitrage-tradingSkill
- dca-strategySkill
- funding-rate-tradingSkill
- on-chain-analysisSkill
- breakout-tradingSkill
- gap-tradingSkill
- momentum-tradingSkill
- news-tradingSkill
- pullback-tradingSkill
- range-tradingSkill
- scalping-strategySkill
- earnings-tradingSkill
- economic-calendar-tradingSkill
- market-correlation-tradingSkill
- sector-rotationSkill
- sentiment-analysisSkill
- breaker-blocksSkill
- fair-value-gapsSkill
- kill-zonesSkill
- liquidity-zonesSkill
- market-structure-shiftSkill
- optimal-trade-entrySkill
- order-blocksSkill
- premium-discountSkill
- correlation-riskSkill
- drawdown-managementSkill
- leverage-managementSkill
- partial-profit-takingSkill
- position-sizingSkill
- risk-reward-ratioSkill
- stop-loss-strategiesSkill
- trailing-stopSkill
- bollinger-bandsSkill
- divergence-tradingSkill
- fibonacci-tradingSkill
- ichimoku-cloudSkill
- macd-tradingSkill
- market-regime-detectionSkill
- mean-reversionSkill
- moving-average-crossoverSkill
- multi-timeframe-analysisSkill
- rsi-divergenceSkill
- stochastic-tradingSkill
- supply-demand-zonesSkill
- volume-profile-tradingSkill
- vwap-tradingSkill
- skill-nameSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use insider filings as delayed, contextual evidence.
- Distinctive: line 59
Look for: recent Form 4 filings, transaction size, buyer/seller role, and whether purchases are scheduled (10b5-1) or discretionary.
- Distinctive: line 74
Treat the setup as a testable hypothesis, not a prediction.
- Distinctive: line 82
Never trade on a headline.
- Distinctive: line 83
Do not equate a 10b5-1 label with neutrality or a transaction with a disclosed motive.
- Distinctive: line 85
Use filing availability time—not transaction time—to prevent look-ahead bias.
≈ “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.
Files
Insider Activity Trading
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.
Filing Fields
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.
Signal Interpretation
Open-Market Purchases
| Factor | Stronger Signal |
| Multiple independent insiders buying | Candidate cluster; define window before testing |
| Large purchases | Meaningful % of holdings |
| After price drop | Buying the dip |
| C-suite buying | CEO/CFO conviction |
Sales and Other Codes
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.
| Selling Reason | Signal Strength |
| Planned (10b5-1) | Contextual; inspect adoption date, terms, and amendments |
| Diversification | Weak negative |
| After big run-up | Moderate negative |
| Unusual amount | Stronger negative |
| Multiple C-suite selling | Candidate cluster requiring plan/code/holdings context |
Bullish vs Bearish Patterns
| Bullish | Bearish |
| CEO buying the dip | Multiple C-suite selling |
| Independently defined purchase cluster | Selling right after guidance |
| Large $ purchases on weakness | Unusual volume of sales |
| Buying after bad news | Selling before scheduled news |
Workflow
1. Research Insider Activity
get_financial_news(topic="AAPL insider buying selling SEC Form 4 filing", max_results=15)
get_fundamentals(ticker="AAPL")Look for: recent Form 4 filings, transaction size, buyer/seller role, and whether purchases are scheduled (10b5-1) or discretionary.
2. Assess Pattern
- Single insider selling = low signal, check if 10b5-1 planned
- Single insider buying = moderate signal, check size relative to holdings
- Purchase cluster = count independent insiders within a predeclared window and compare with issuer history
- C-suite selling unusual amounts = red flag, investigate further
3. Combine with Fundamentals
Insider activity is a confirming signal, not standalone. Cross-reference with company fundamentals, recent earnings, and technical setup before acting.
Evidence and Validation
- Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes.
- Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried.
- 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.
- Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status.
- Research basis: The SEC Form 3/4/5 bulletin explains codes and two-business-day reporting, while the 10b5-1 rule requires plan-related disclosures.
Key Rules
- Never trade on a headline; parse the filed form, codes, footnotes, ownership, and amendments.
- Do not equate a 10b5-1 label with neutrality or a transaction with a disclosed motive.
- Normalize transaction value by prior holdings, compensation, market capitalization, and insider history.
- 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.
- Define cluster windows and event exclusions before testing; report
no tradewhen context is missing.
Related Skills
- earnings-trading -- Insider activity around earnings signals management confidence
- sentiment-analysis -- Insider buying is a high-credibility input to sentiment scoring
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.

