flag-pennant
starsforks
How to install flag-pennant?
ske-labs/agent-trading-skills/flag-pennant
$npx -y skills add SKE-Labs/agent-trading-skills --skill flag-pennantDefine and test flag or pennant continuation shapes. Use when measuring an impulse, consolidation, closed-bar break, invalidation, and measured-move hypothesis.
SKILL.md
| 1 | # Flag & Pennant Patterns |
| 2 | |
| 3 | Continuation patterns that form during pauses in strong trends. |
| 4 | |
| 5 | ## Pattern Structure |
| 6 | |
| 7 | **Components:** Flagpole (strong impulsive move) → Flag/Pennant (consolidation) → Breakout (continuation). |
| 8 | |
| 9 | - **Bull Flag** — Strong upward pole, downward-sloping rectangular channel, breaks upward |
| 10 | - **Bear Flag** — Strong downward pole, upward-sloping rectangular channel, breaks downward |
| 11 | - **Pennant** — Strong move (pole), symmetrical triangle consolidation, breaks in pole direction |
| 12 | |
| 13 | | Criteria | Flag | Pennant | |
| 14 | |----------|------|---------| |
| 15 | | Shape | Rectangular channel (2 parallel lines) | Symmetrical triangle (2 converging lines) | |
| 16 | | Slope | Against trend | Neutral | |
| 17 | | Volume | Decreasing | Decreasing | |
| 18 | |
| 19 | ## Workflow |
| 20 | |
| 21 | ### 1. Get Swing Point Data |
| 22 | |
| 23 | Identify the flagpole and consolidation boundaries: |
| 24 | |
| 25 | ``` |
| 26 | get_candles_around_date(symbol=<symbol>, exchange=<exchange>, interval=<interval>, date=<flag_date>) |
| 27 | ``` |
| 28 | |
| 29 | ### 2. Draw Flag/Pennant Boundaries (2 parallel calls) |
| 30 | |
| 31 | **For flags** (2 parallel trend lines sloping against the pole): |
| 32 | |
| 33 | ``` |
| 34 | # Upper flag boundary |
| 35 | draw_chart_analysis(action="create", drawing={ |
| 36 | "type": "trend", |
| 37 | "points": [ |
| 38 | {"time": <flag_high1_time>, "price": <flag_high1_price>}, |
| 39 | {"time": <flag_high2_time>, "price": <flag_high2_price>} |
| 40 | ], |
| 41 | "options": {"text": "Flag R"} |
| 42 | }) |
| 43 | |
| 44 | # Lower flag boundary (parallel to upper) |
| 45 | draw_chart_analysis(action="create", drawing={ |
| 46 | "type": "trend", |
| 47 | "points": [ |
| 48 | {"time": <flag_low1_time>, "price": <flag_low1_price>}, |
| 49 | {"time": <flag_low2_time>, "price": <flag_low2_price>} |
| 50 | ], |
| 51 | "options": {"text": "Flag S"} |
| 52 | }) |
| 53 | ``` |
| 54 | |
| 55 | **For pennants:** same approach but lines converge (like a small symmetrical triangle). |
| 56 | |
| 57 | ### 3. Confirm and Enter |
| 58 | |
| 59 | Confirm declining volume during consolidation via `get_indicators(indicator_code="mfi", symbol=<symbol>, exchange=<exchange>, interval=<interval>)`. |
| 60 | |
| 61 | **Standard:** Enter on break of flag/pennant boundary with volume spike. Stop beyond opposite side. |
| 62 | **Conservative:** Wait for breakout + retest of boundary. Enter on bounce. |
| 63 | **Target:** Flagpole length projected from breakout point. |
| 64 | |
| 65 | ## Evidence and Validation |
| 66 | |
| 67 | - Treat the setup as a testable hypothesis, not a prediction. Define thresholds, entry, invalidation, and exit before evaluating outcomes. |
| 68 | - Calibrate on the same instrument, venue, session, and timeframe. Use closed candles and a held-out or walk-forward sample; record every variant tried. |
| 69 | - 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. |
| 70 | - Return observed inputs, missing data, cost assumptions, entry, invalidation, exit, and a valid, watch, or no-trade status. |
| 71 | - Research basis: [Lo, Mamaysky & Wang](https://www.nber.org/papers/w7613) supports objective pattern definitions and conditional testing rather than visual labels alone. |
| 72 | |
| 73 | ## Key Rules |
| 74 | - Quantify the pole with return divided by ATR and a maximum bar count; “looks impulsive” is not reproducible |
| 75 | - Define and calibrate the maximum retracement rather than assuming 50% is universal |
| 76 | - Treat volume contraction and breakout expansion as candidate filters; report their measured values |
| 77 | - Quick formations are more reliable than extended consolidations |
| 78 | - Flag duration should be short relative to the pole |
| 79 | |
| 80 | ## Related Skills |
| 81 | - **triangle-patterns** — Pennants are small symmetrical triangles |
| 82 | - **channel-trading** — Flags are short-duration trending channels |
People who liked this also viewed
6 picksType
- azure-costAzure cost management: query costs, forecast spending, optimize to reduce waste. WHEN: \"Azure costs\", \"Azure bill\", \"cost breakdown\", \"how much am I spending\", \"forecast spending\", \"optimizSkillsJul 2026
- pricingWhen the user wants help with pricing decisions, packaging, or monetization strategy. Also use when the user mentions 'pricing,' 'pricing tiers,' 'freemium,' 'free trial,' 'packaging,' 'price increaseSkillsJul 2026
- stripe-integrationMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- startup-financial-modelingMulti-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLISkillsJul 2026
- tushare-finance专为 Claude Code 设计的 Tushare Pro 金融数据技能包，支持 220+ 个接口，用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。SkillsJul 2026
- azure-pricingFetches real-time Azure retail pricing using the Azure Retail Prices API (prices.azure.com) and estimates Copilot Studio agent credit consumption. Use when the user asks about the cost of any Azure seSkillsJul 2026
