pinescript-mastery

by alradyin

>

3.7k行业场景未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/alradyin/pinescript-mastery

文档

Pine Script Mastery

What this skill does: Activates elite-level Pine Script capability. Not just code generation — complete trading system architecture. Strategy logic, indicator design, risk management, backtesting integrity, publication-ready structure, and Pine Script v5/v6 mastery in one skill.


Reference Architecture

FileContentsWhen to read
references/language-mastery.mdFull v5/v6 syntax, built-ins, 2025 updates, common errorsEvery coding task
references/strategy-design.mdStrategy architecture, signal logic, entry/exit systemsStrategy builds
references/risk-management.mdPosition sizing, SL/TP systems, drawdown control, KellyRisk components
references/indicators-library.md30+ indicator implementations with explanationsIndicator builds
references/quality-standards.mdCode structure, documentation, anti-patterns, publication checklistAll outputs

Standard task: Read language-mastery.md + relevant reference. Full strategy build: Read all five files.


Execution Protocol

STEP 1 — Classify the Request

code
TYPE:
  [ ] Indicator only     — visualizes data, no trades
  [ ] Strategy           — generates buy/sell signals with backtesting
  [ ] Library            — reusable functions for other scripts
  [ ] Debug / Fix        — existing code has errors
  [ ] Optimize           — improve existing script performance or logic
  [ ] Explain            — teach how something works
  [ ] Convert            — port from another language or v4→v5/v6

VERSION TARGET:
  [ ] v5  (most compatible, massive community)
  [ ] v6  (latest — dynamic requests, strict bool, new features)
  Default: v5 unless user specifies v6 or needs v6-only features

COMPLEXITY:
  [ ] Simple   — single concept, <50 lines
  [ ] Medium   — multi-component, 50-200 lines
  [ ] Advanced — full system, 200+ lines, multiple interacting systems

STEP 2 — Pre-Code Intelligence Gathering

Before writing a single line, extract:

code
ASSET CLASS    : Forex / Crypto / Stocks / Futures / Index
TIMEFRAME      : Scalp (1-5m) / Intraday (15m-4h) / Swing (D) / Position (W+)
MARKET TYPE    : Trending / Ranging / Volatile — which does the strategy target?
ENTRY LOGIC    : What signals trigger entries? (momentum / reversal / breakout / mean reversion)
EXIT LOGIC     : Fixed SL/TP / Trailing / Indicator-based / Time-based?
RISK APPROACH  : Fixed % / ATR-based / Kelly / Fixed lot?
FILTERS        : Trend filter? Volume filter? Time session filter?
VISUAL NEEDS   : What should appear on chart? Signals? Levels? Dashboard?

If information is missing for a strategy build → ask before coding. If request is clear → proceed immediately.


STEP 3 — Architecture Design (Strategy Builds)

Read references/strategy-design.md and design before coding:

code
SIGNAL STACK
  Primary signal   : [Main entry trigger]
  Confirmation 1   : [First filter — reduces false signals]
  Confirmation 2   : [Second filter — optional but recommended]
  Trend filter     : [Macro direction context]
  Volume filter    : [Participation confirmation — optional]

RISK STACK
  Stop Loss        : [Method + calculation]
  Take Profit 1    : [First target — partial exit]
  Take Profit 2    : [Second target — full exit]
  Trailing Stop    : [Activation level + trail distance]
  Max Drawdown     : [Emergency shutdown condition]

POSITION SIZING
  Method           : [Fixed % / ATR-based / Kelly]
  Risk per trade   : [% of equity]
  Max open trades  : [Concurrent position limit]

STEP 4 — Write Production-Grade Code

Read references/language-mastery.md before writing. Read references/quality-standards.md to apply all standards.

Every script must have:

pine
// ============================================================
// [SCRIPT NAME] — [one-line description]
// Version    : v1.0
// Pine Script: v5 (or v6)
// Author     : [name]
// Description: [2-3 sentence explanation of what it does,
//               what makes it useful, how to use it]
// ============================================================

Code structure order:

  1. Version declaration + header comment
  2. indicator() or strategy() declaration with all parameters
  3. Input groups (organized, labeled, with tooltips)
  4. Core calculations
  5. Signal logic
  6. Risk management
  7. Strategy entries/exits (if strategy)
  8. Plots and visuals
  9. Alerts
  10. Dashboard table (if needed)

STEP 5 — Validate Before Delivering

Run this checklist on every output:

code
SYNTAX
[ ] Correct version declaration
[ ] No deprecated v4 functions (study(), security(), etc.)
[ ] All variables declared before use
[ ] No repainting logic unless intentional and disclosed
[ ] request.security() used correctly (barmerge settings)

LOGIC
[ ] Entry and exit conditions are mutually consistent
[ ] No division by zero risk
[ ] Array bounds checked if arrays used
[ ] na values handled (na() checks where needed)
[ ] Lookahead bias absent from strategy

QUALITY
[ ] All inputs have tooltips
[ ] All plots have titles and colors
[ ] Alert conditions defined
[ ] Strategy uses commission and slippage parameters
[ ] Code is readable — no magic numbers, named constants used

PERFORMANCE
[ ] No unnecessary calculations inside loops
[ ] Heavy calculations use var or varip where appropriate
[ ] request.security() calls minimized

STEP 6 — Deliver With Context

Every code delivery includes:

1. What it does — plain English, 2-3 sentences

2. How to use it — specific settings, what to look for

3. Optimization hints — which inputs to tune first

4. Known limitations — honest about what it doesn't handle

5. Risk warning — always include for strategies:

⚠️ Backtest results do not guarantee future performance. Always validate on out-of-sample data and demo trade before going live.


Strategy Design Principles

These apply to every strategy output regardless of complexity:

The Signal Quality Hierarchy

code
Tier 1 — Price action (most reliable, no lag)
Tier 2 — Volume confirmation (validates moves)
Tier 3 — Momentum oscillators (RSI, MACD — confirm, don't lead)
Tier 4 — Moving averages (trend context only — laggy for entry)

Never use Tier 4 alone for entries. Always combine tiers.

The Repainting Rule

Scripts must never repaint without explicit disclosure. Common repainting causes:

  • request.security() without lookahead=barmerge.lookahead_off
  • Using high[0] or low[0] in real-time bar calculations
  • ta.pivothigh() / ta.pivotlow() — these inherently repaint

Always use barstate.isconfirmed for alert conditions.

The Overfitting Warning

If a strategy has >5 optimizable inputs and shows >70% win rate in backtest: flag this explicitly. Recommend walk-forward validation. Real edges produce 52-60% win rates with good R:R, not 80%+.


Pine Script v6 Key Differences (vs v5)

Pine Script v6 was released December 2024. Future updates apply exclusively to v6.

Key changes from v5:

code
Dynamic requests  : request.*() now accepts series string arguments
                    Can change data feed dynamically on historical bars
                    Can be called inside loops and conditional structures

Strict booleans   : bool type is now strictly true or false, never na
                    Eliminates entire class of silent logic bugs

Better strategy   : Improved handling of complex order logic

2025 updates: Scope limit removed (was 550, now unlimited). String length increased 10x to 40,960 characters. Pine Editor moved to side panel with word wrap support.

When to use v6: new scripts that need dynamic request.*() calls, or when scope/string limits were previously a constraint. When to stay on v5: maximum community compatibility needed.


Quick Reference — Most Used Patterns

Multi-Timeframe Analysis

pine
// Always use barmerge.lookahead_off to prevent repainting
htf_close = request.security(syminfo.tickerid, "D", close,
     lookahead=barmerge.lookahead_off)
htf_trend = request.security(syminfo.tickerid, "D",
     ta.ema(close, 50) > ta.ema(close, 200),
     lookahead=barmerge.lookahead_off)

ATR-Based Dynamic Levels

pine
atr = ta.atr(14)
sl_distance  = atr * sl_mult
tp1_distance = atr * tp1_mult
tp2_distance = atr * tp2_mult

Strategy Entry with Risk Management

pine
if long_signal and strategy.position_size == 0
    strategy.entry("Long", strategy.long)
    strategy.exit("Long Exit", "Long",
         stop   = close - sl_distance,
         limit  = close + tp1_distance,
         comment= "SL/TP1")

Dashboard Table

pine
var table dash = table.new(position.top_right, 2, 5,
     bgcolor=color.new(color.black, 80),
     border_color=color.gray, border_width=1)

if barstate.islast
    table.cell(dash, 0, 0, "Signal",
         text_color=color.gray, text_size=size.small)
    table.cell(dash, 1, 0, long_signal ? "LONG ▲" : "–",
         text_color=long_signal ? color.green : color.gray,
         text_size=size.small)

Confirmed Alerts (No Repainting)

pine
alertcondition(long_signal and barstate.isconfirmed,
     title="Long Signal",
     message="{{ticker}} — Long signal on {{interval}}")

Teaching Mode

When the user asks to learn or understand something:

  1. Explain the concept — plain English first, no jargon
  2. Show minimal example — smallest possible code that demonstrates it
  3. Show real-world application — how it's actually used in a strategy
  4. Common mistakes — what trips people up
  5. Next step — what to learn after this

Never dump the full Pine Script manual. Teach the specific concept needed, with just enough context to make it click.

相关 Skills

面试体系设计

by alirezarezvani

Universal
热门

按岗位、级别和团队设计面试流程,生成能力矩阵、题库与评分标准,分析面试官偏差并校准招聘门槛,适合搭建或优化企业招聘体系。

团队招人没章法时,用它快速搭建岗位化面试流程、题库与评分标准,还能兼顾校准面试偏差,招聘更稳更准。

行业场景
未扫描9.0k

抽认卡

by BytesAgain

热门

Spaced repetition study tool with deck management. Use when you need flashcard.

行业场景
未扫描3.7k

教程文档

by anderskev

热门

Tutorial patterns for documentation - learning-oriented guides that teach through guided doing

行业场景
未扫描3.7k

相关 MCP 服务

by boosted-chat

热门

Flight search & booking for AI agents. 400+ airlines, $20-50 cheaper than OTAs.

行业场景
137

Search company disclosures and financial statements from the Korean market. Retrieve stock profiles, market classifications, and historical trading data across major exchanges. Accelerate equity research with accurate, date-specific insights for Korean securities.

做韩国股研时,用它能一站查公司披露、财报和历史行情,按日期精确追溯关键信息,比手动翻交易所高效太多。

行业场景
103

检索韩国市场公司的披露文件与财务报表,并获取股票概况等关键信息。

想研究韩股公司时,它能一站式拉取披露、财报和股票概况,省去跨站查资料的麻烦,对跨境投研尤其省时。

行业场景
103

评论