Skip to content
Data
Skill

/sepa-strategy

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

From plugin
finance-skills
3.5k26 skills1 MCP

Claude Code

$ npx -y skills add himself65/finance-skills --skill sepa-strategy --agent claude-code

SKILL.md

sepa-strategy.SKILL.md
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

Read more
@himself65
Ships withfinance-skills

A collection of agent skills for financial analysis and trading, following the Agent Skills open standard. Visit skills.himself65.com for documentation, demos, and setup instructions.

3.5k26 skills1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
3.5k
Star history of himself65/finance-skills on GitHub, a chart by star-history.com

Other skills on finance-skills.

fintel-data

fintel-data

Query Fintel (fintel.io) institutional market data through its REST API or official MCP server. Use this skill whenever the user…

hormuz-strait

hormuz-strait

Check the live status of the Strait of Hormuz from the Hormuz Strait Monitor dashboard: open, restricted, or closed status,…

tradingview-mcp

tradingview-mcp

Query TradingView market data through the bundled tradingview MCP server without a desktop app or login. Use whenever the user…

More skills from other plugins.

context-loader
Auto-invoked

context-loader

Search memories from earlier Pi sessions in this repository. Use it when earlier work may already explain the code, error,…

mem04d69k
@mem0ai@mem0aiInstall Skill
analyzing-ai-citations

analyzing-ai-citations

Answer AI citation and answer engine optimization (AEO) questions in PostHog: whether AI answer engines (ChatGPT, Claude, and an…

posthog11d41k
@posthog@posthogInstall Skill

Questions about sepa-strategy.

Which coding agents can use sepa-strategy?
sepa-strategy installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.