Sepa StrategySAFE
A collection of skills for AI financial analysis.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Analyze stocks using Mark Minervini's SEPA (Specific Entry Point Analysis) methodology — a complete framework for identifying high-probability growth stock entries with strict risk management.
Triggers
- Mentions of SEPA, Minervini, superperformance, trend template
- VCP (Volatility Contraction Pattern), stage analysis, Stage 2 uptrend
- Pivot point breakout, growth stock screening
- Moving average alignment checks (bullish stacking)
- Consolidation pattern analysis (cup-with-handle, flat base, flag, high tight flag)
- Position sizing with risk-based calculations
- "Should I buy this stock?" or "Is this a good setup?" in growth/momentum context
What It Does
- Stage Analysis — determines if a stock is in Stage 2 (the only buyable stage) and counts bases
- Trend Template — evaluates 8 mandatory conditions (MA hierarchy, price position, relative strength)
- Fundamental Check — grades EPS growth/acceleration, revenue, margins, institutional ownership
- Pattern Recognition — identifies VCP, cup-with-handle, flat base, flag, and high tight flag patterns
- Entry Assessment — calculates pivot point, buy zone (0-5% above pivot), breakout volume requirement
- Position Sizing — risk-based share calculation, 3-phase stop loss plan, pyramiding rules
- Market Environment — adjusts strategy based on bull/choppy/bear conditions
Platform
All (works on Claude Code, Claude.ai, and other agents)
Setup
No special setup required. Works best with access to market data tools (yfinance) for real-time prices and fundamentals.
Reference Files
317cbce031f1OBSERVED · 2026-10-08Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: sepa-strategy description: > Analyze stocks with Mark Minervini's SEPA (Specific Entry Point Analysis) methodology: stage analysis, the 8-condition trend template, fundamentals, VCP and other base patterns, pivot-point entries, market environment, and risk-based position sizing. Use this skill whenever the user mentions SEPA, Minervini, superperformance, the trend template, VCP (volatility contraction pattern), Stage 2, pivot or breakout entries, moving-average stacking (price above the 50/150/200-day MAs), breakout volume, position sizing from risk percentage, growth-stock screening or swing-trade entry criteria, or bases such as cup-with-handle, flat base, bull flag, or high tight flag. Also use it when the user asks "should I buy this stock" or "is this a good setup" about a growth or momentum name, or shares a chart for pattern analysis. --- # SEPA Strategy Analysis Analyze stocks using Mark Minervini's SEPA (Specific Entry Point Analysis) framework — a complete system for identifying high-probability growth stock entries with strict risk management. **Core philosophy:** Buy the right stock, in the right stage, at a precise entry point, with strict risk controls. Win rate is ~50-55% — profitability comes from asymmetric risk/reward (small losses, large gains), not from predicting direction. > This skill is for educational/analytical purposes only. It does not constitute investment advice. Never execute trades based solely on this analysis. --- ## Step 1: Gather Stock Data Collect the following data for the stock. Use yfinance or any available market data tool. | Data needed | Purpose | |---|---| | Current price | Trend template check | | 50-day, 150-day, 200-day moving averages | MA alignment verification | | 52-week high and low | Price position check | | 200MA value from 1 month ago and 4-5 months ago | MA200 slope direction | | 20-day average volume + today's volume | Volume ratio analysis | | Recent quarterly EPS (last 3-4 quarters) | EPS growth & acceleration | | Annual EPS (last 3 years) | Long-term growth trend | | Recent quarterly revenue (last 3-4 quarters) | Revenue growth check | | Gross margin and net margin trend | Margin health | | Institutional ownership changes (if available) | Smart money signal | | RS rating or 12-month relative performance vs S&P 500 | Relative strength | | Price history for pattern recognition | VCP / chart pattern analysis | Compute the moving averages, 200MA slope, 52-week range, volume ratio, and relative performance from daily price history in code rather than estimating them — two years of history covers the 200-day MA and its 5-month slope. If certain data is unavailable, note it and proceed with what you have. Missing RS rating is a significant gap — flag it. --- ## Step 2: Stage Analysis — Identify the Current Stage Every stock cycles through four stages. Read `references/stage-analysis.md` for full details. Determine which stage the stock is in: | Stage | Characteristics | Action | |---|---|---| | **Stage 1** — Basing | Price near 200MA, MA flat/declining, MAs tangled, low volume | Do nothing, wait | | **Stage 2** — Advancing | Making higher highs/lows, bullish MA alignment, volume on up days | **Only stage to buy** | | **Stage 3** — Topping | Wide swings at highs, frequent false breakouts, heavy volume without progress | Reduce, no new positions | | **Stage 4** — Declining | Below all MAs, bearish alignment, bounces are selling opportunities | Full cash, stay away | If the stock is NOT in Stage 2, stop here and tell the user. No further analysis needed. Within Stage 2, count the base number (how many consolidation-then-breakout cycles have occurred): - **Base 1-2**: Safest, most upside potential — full position - **Base 3-4**: Still valid but reduce position size - **Base 5-6**: Late stage — half position at most - **Base 7+**: Avoid — likely transitioning to Stage 3 --- ## Step 3: Trend Template — 8 Mandatory Conditions All 8 conditions must be met simultaneously. If any fails, the stock does not qualify. Read `references/trend-template.md` for detailed explanations. Present results as a checklist: | # | Condition | Status | Value | |---|---|---|---| | 1 | Price > 150MA and Price > 200MA | Pass/Fail | [actual values] | | 2 | 150MA > 200MA | Pass/Fail | [actual values] | | 3 | 200MA trending up for ≥1 month (ideally 4-5 months) | Pass/Fail | [slope data] | | 4 | 50MA > 150MA and 50MA > 200MA | Pass/Fail | [actual values] | | 5 | Price > 50MA | Pass/Fail | [actual values] | | 6 | Price ≥ 30% above 52-week low | Pass/Fail | [% above low] | | 7 | Price within 25% of 52-week high | Pass/Fail | [% from high] | | 8 | Relative Strength > 70th percentile (prefer 85-90+) | Pass/Fail/Unknown | [RS if available] | **Memory aid:** Conditions 1-5 = "MA staircase" (Price > 50MA > 150MA > 200MA, 200MA rising). Conditions 6-7 = "Price position" (far from low, near high). Condition 8 = "Relative strength" (market leader). --- ## Step 4: Fundamental Check Strong fundamentals separate real leaders from momentum-only stocks. Read `references/fundamentals.md` for thresholds and rating criteria. Check these in order of importance: 1. **Quarterly EPS growth ≥ 20%** (prefer 25-50%+). Below 20% = disqualify. 2. **EPS acceleration**: Current quarter growth > prior quarter growth. Deceleration (even with positive growth) is a warning. 3. **Annual EPS growth ≥ 25%** for each of the past 3 years. 4. **Revenue growth ≥ 15%** annually, ≥ 20-25% quarterly preferred. If EPS grows but revenue doesn't, the growth is likely from cost-cutting (unsustainable). 5. **Margin trend**: Gross and net margins stable or expanding = healthy. Contracting margins even with EPS growth = red flag. 6. **Institutional ownership increasing**: Smart money accumulating = fuel for Stage 2 move. 7. **Catalyst**: New product, FDA approval, major contract, market expansion, etc. Stocks with catalysts can run 50-100%+; without, typically
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
317cbce031f1full audit observations/trust-audit/skill/himself65__sepa-strategy.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 317cbce031f1 | SAFE | B | 89 | first audit |
Questions
What does the Sepa Strategy skill do?
A collection of skills for AI financial analysis.
Is Sepa Strategy safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Sepa Strategy access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Sepa Strategy work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (317cbce031f1), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.