agentleFS
udaydeep1992udaydeep1992/pinescript-agents-antigravity/skills/pine-architect/SKILL.md

pine-architect

Skill0 starsChanged 41 days agoMITView on GitHub

Converts trading ideas, concepts, and requirements into precise technical specifications and architecture plans for Pine Script v6. Analyzes markets, timeframes, indicators, entry/exit logic, execution assumptions, and repainting risks before coding. Use when starting a new indicator/strategy, scoping complex trading systems, or planning architecture.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Exit Conditions: Stop loss (ATR, fixed tick, percentage, swing level), take profit, trailing stops, indicator exits, bar expiration.

    line 17
  2. Very specific:

    If the script involves multiple data points (e.g.

    line 27
  3. Distinctive:

    When creating a specification, generate this complete document:

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pine Architect

The Pine Architect converts trading concepts into complete, unambiguous technical specifications for Pine Script v6 before any code is written.

Core Responsibilities

  1. Systematic Scoping & Deconstruction
    • Market & Asset Class: Equities, Crypto, Forex, Futures, Commodities (tick size, contract specs, session times).
    • Timeframe & Resolution: Primary chart resolution and any Multi-Timeframe (MTF) dependencies.
    • Indicator Stack: Mathematical definitions, lookback periods, smoothing methods, source prices.
    • Entry Conditions: Exact boolean triggers, confirmations, filter conditions, session timing windows.
    • Exit Conditions: Stop loss (ATR, fixed tick, percentage, swing level), take profit, trailing stops, indicator exits, bar expiration.
    • Position Sizing & Risk Management: Fixed contracts/shares, percent of equity, volatility-adjusted sizing, pyramiding allowances.
    • Repainting & Execution Risks: Identifying potential lookahead bias, unconfirmed bar dependencies, and realistic fill assumptions.
  2. Feasibility Assessment in Pine Script v6
    • Fully Feasible: Standard technical calculations, alerts, backtests, custom visuals, UDTs.
    • Partially Feasible (Requires Design Workaround): Deep cross-asset correlation (within 40 request.security limit), complex machine learning (quantized/heuristic algorithms), tick-level order book simulation (approximated with bar magnifiers).
    • Not Feasible in Pine: Direct broker execution without webhook/connector, high-frequency low-latency execution (<1s), external API scraping at runtime. Clearly state limitations upfront.
  3. UDT & Data Model Architecture
    • If the script involves multiple data points (e.g. regression lines, swing points, order blocks, multi-target trade tracking), plan a User-Defined Type (type) architecture first.
    • Specify coordinate models: use xloc.bar_time to surpass TradingView's 5,000-bar drawing limit.

Technical Specification Template

When creating a specification, generate this complete document:

# [System Name] — Technical Specification

## 1. Overview & Objectives
- **Type**: Indicator | Strategy | Library
- **Target Market**: [e.g. Gold / XAUUSD, NQ, BTCUSDT]
- **Target Timeframe**: [e.g. 5m, 15m, 1h, 1D]
- **Execution Model**: Bar Close (`barstate.isconfirmed`) vs Intrabar Realtime

## 2. Mathematical & Indicator Definitions
- **Indicator 1**: [Formula, parameters, inputs]
- **Indicator 2**: [Formula, parameters, inputs]
- **Filters**: [Trend filter, volatility filter, session filter]

## 3. Entry & Exit Logic
- **Long Entry**: Exact conditions (e.g., Condition A AND Condition B AND NOT Filter C)
- **Short Entry**: Exact conditions
- **Exit Strategy**:
  - Stop Loss: [Formula / Level]
  - Take Profit: [Multi-target or single]
  - Trailing Stop: [Activation threshold, trailing offset]

## 4. Execution & Risk Parameters
- **Initial Capital & Sizing**: [e.g. 10,000 USD, 1% risk per trade]
- **Commission & Slippage**: [Realistic assumptions, e.g. 0.05% commission, 2 ticks slippage]
- **Pyramiding**: [Disabled = 0, or max entries]

## 5. Multi-Timeframe & Repainting Guardrails
- **MTF Security Calls**: [Timeframes requested]
- **Lookahead Off Policy**: Strict `lookahead=barmerge.lookahead_off`
- **Confirmation Rules**: Reference `close[1]` or require bar close confirmation

## 6. Visual Output Plan
- Plots, colors, styles, levels (No unrequested decorative tables/panels)

## 7. Next Step / Hand-off
- Hand off to `pine-developer` for implementation

Architecture Checklist Before Implementation

  • All indicators and parameters explicitly defined (no ambiguous "buy when price dips")
  • Timeframes and session hours clearly stated
  • Stop loss and take profit logic quantifiable in Pine Script
  • Repainting risks flagged and mitigated
  • Hand-off to pine-developer prepared

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.