Pinescript

Pine Script Development

Verify before implementing: For Pine Script version-specific syntax or new built-in functions, look up current docs via Context7 (query-docs) before writing code. TradingView updates Pine Script frequently and training data may be stale.

Critical Syntax Rules

• Ternary operators MUST stay on one line -- splitting across lines causes "end of line without line continuation" error. For complex ternaries, use intermediate variables:

  isBull = close > open
  barColor = isBull ? color.green : color.red

• Continuation lines MUST be indented MORE than the starting line -- same indentation = error
• NEVER use plot() inside local scopes (if/for/functions) -- use conditional value instead: plot(condition ? value : na)
• barstate.isconfirmed -- use to prevent repainting on real-time bars

Platform Limits

500 bars history for request.security() | 500 plot calls | 64 drawing objects | 40 request.security() calls | 100KB compiled size

Performance

• Tuple security calls -- one request.security() returning [close, high, low] instead of 3 separate calls
• Pre-allocate arrays with array.new<type>(size) instead of push-and-resize
• Short-circuit signals: build conditions incrementally, exit early when first condition fails
• Cache repeated calculations in variables -- Pine recalculates every bar

Debugging

TradingView has no console or debugger. Use these patterns:

• Label debugging: label.new(bar_index, high, str.tostring(myVar)) to inspect values
• Table monitor: table.new() with barstate.islast for real-time variable dashboard
• Debug mode toggle: wrap all debug code in if input.bool("Debug", false) -- remove before publishing
• Repainting detector: track previousValue = value[1], flag when historical values change

Strategy & Backtesting

• Use strategy.* functions: strategy.wintrades, strategy.losstrades, strategy.grossprofit
• Drawdown tracking: maxEquity = math.max(strategy.equity, nz(maxEquity[1])), then dd = (maxEquity - strategy.equity) / maxEquity * 100
• Sharpe: dailyReturn * 252 / (stdDev * math.sqrt(252))
• Walk-forward validation -- optimize on period 1, test on period 2, re-optimize on period 2, test on period 3. If metrics degrade > 30%, parameters are overfit.
• Indicator accuracy testing -- use forward-looking close[lookforward] to measure prediction accuracy, track true/false positive rates

Visualization

• color.from_gradient() for trend strength coloring
• Adaptive text sizing: size.small for intraday, size.normal for daily+
• Dynamic table rows -- resize based on enabled features via input toggles
• Professional color constants: define BULL_COLOR, BEAR_COLOR, NEUTRAL_COLOR once with transparency

Publishing

• Documentation goes at TOP of .pine file as comments before indicator()/strategy()
• Use @version, @description, @param tags
• Multi-line tooltips: tooltip="Line 1" + "\n" + "Line 2"
• TradingView House Rules: no financial advice, no performance guarantees, no external links, no obfuscated code, no donation requests

Common Coding Mistakes

• Indicator stacking (RSI + Stochastics + CCI) -- all measure the same thing (momentum). Use indicators from different categories instead.
• Overfitting parameters: if optimal values are oddly specific (RSI 23 instead of 20), the backtest is curve-fitted. Use round numbers and input() with sensible defaults.
• Missing barstate.isconfirmed guard -- calculations on unconfirmed bars cause repainting. Always guard entry signals.
• Hardcoded thresholds without input() -- makes the script untestable across instruments.

Workflow

1. Write indicator/strategy in Pine Editor 2. Test with bar replay and strategy tester on multiple timeframes 3. Walk-forward validate before trusting backtest results (see Strategy & Backtesting above) 4. Verify: run on 3+ symbols and 2+ timeframes

Verify

• Indicator compiles without errors on TradingView
• No repainting: barstate.isconfirmed guard present where needed
• Walk-forward tested on 3+ symbols across different timeframes

ia-pinescript findings log

Persistent iteration evidence for ia-pinescript. See the /diagnose-negatives workflow Step 3 for the schema.

EX-001: Misfire on TradingView MCP server (JS) audit

• Label: negative
• Kind: wrong_trigger
• Origin: human-verified (diagnose-negatives reviewer accepted)
• Source: 2 of 2 negative sessions in distillery/.eval-data/ia-pinescript/sessions.jsonl (2026-04-27 harvest)
• Status: resolved
• Expected behavior: skill should not inject when the user is auditing a JavaScript MCP server that connects to the TradingView API but contains zero .pine files
• Observed behavior: skill injected because regex tradingview|... matched bare "tradingview" in the prompt; agent then loaded ia-simplifying-code and ia-code-review (correct skills), wasting the injection
• Skill delta:
• plugins/whetstone/hooks/skill-patterns.sh:65: tightened regex so bare tradingview no longer matches; required Pine-context qualifier within 30 chars (tradingview.{0,30}(pine|indicator|strategy|chart|script)); added symmetric \bstrategy\b.{0,20}(pine|trading.?view) clause
• plugins/whetstone/skills/ia-pinescript/SKILL.md:4-7: rewrote description to scope triggers to .pine files or TradingView Pine indicators/strategies (drops standalone "TradingView", "indicators", "strategies", "backtesting" as triggers)
• distillery/tests/fixtures/triggers/ia-pinescript.jsonl: added two negative-case fixtures from the actual misfire prompts
• Anonymization: redacted nothing; both prompts were generic infrastructure audits with no sensitive content

ia-pinescript Specification

Intent

ia-pinescript is a language-class skill (stack-specific patterns and idioms). Pine Script v6 patterns: syntax, performance, error diagnosis, backtesting, visualization. Use when working with PineScript, TradingView, indicators, strategies, or backtesting.

Scope

In scope:

• Behaviors described in SKILL.md and routed via the should_trigger phrasings in distillery/tests/fixtures/triggers/ia-pinescript.jsonl.
• Updates to runtime behavior, structure, trigger precision, references, and validation.

Out of scope:

• Acting as the runtime instructions themselves (those live in SKILL.md).
• Trigger phrasings already covered by adjacent ia-* skills (validate-plugin flags >70% description overlap as DUPLICATE_TRIGGER).
• <!-- to fill in: domain-specific exclusions when the skill drifts -->

Trigger Context

• Class: language
• Hook regex: plugins/whetstone/hooks/skill-patterns.sh -> SKILL_PATTERNS[ia-pinescript]
• Common requests (from fixture should_trigger):
• "write a pine script indicator for RSI divergence"
• "fix the TradingView strategy backtest results"
• "write a Pine Script v6 indicator for ATR-based stops"
• Should not trigger for (from fixture should_not_trigger):
• "set up a PostgreSQL replication cluster"
• "write unit tests for the checkout service"
• "write a Python pandas script to backtest"

Source And Evidence Model

Authoritative sources:

• SKILL.md -- runtime instructions and reference routing.
• references/*.md -- bundled supplementary content (0 file(s)).
• distillery/tests/fixtures/triggers/ia-pinescript.jsonl -- positive and negative trigger phrasings under regression test.
• plugins/whetstone/hooks/skill-patterns.sh -- regex pattern that fires this skill.
• distillery/.eval-data/ia-pinescript/ -- harvested session examples (when present).

Data that must not be stored in this skill or its references:

• Secrets, credentials, tokens.
• Machine-specific filesystem paths (/home/..., /Users/..., ~/ai/...). The validator (MACHINE_PATH_LEAK) flags these as HIGH.
• Private URLs, customer data, or unredacted personal information.

Coverage matrix

Evaluation

Lightweight (run on every change):

python3 distillery/scripts/distiller.py validate-plugin --component ia-pinescript
python3 distillery/scripts/distiller.py test-triggers --skill ia-pinescript

Deeper (when behavior risk warrants):

python3 distillery/scripts/distiller.py dspy-eval ia-pinescript
python3 distillery/scripts/distiller.py diagnose-negatives ia-pinescript

Acceptance gates:

• validate-plugin --component ia-pinescript returns 0 HIGH findings.
• test-triggers --skill ia-pinescript returns F1 = 1.0 with floors of 5 should_trigger and 5 should_not_trigger.
• For dspy-eval, the composite score does not regress against the most recent saved baseline (see distillery/.eval-data/ia-pinescript/history.json).

Known Limitations

<!-- to fill in over time as drift surfaces. Default rule: any time diagnose-negatives surfaces a recurring failure pattern, document it here so future maintainers understand the trade-off the current implementation accepts. -->

Maintenance Notes

• Update SKILL.md when the runtime workflow, branch conditions, or output contract changes.
• Update this SPEC.md when intent, scope, evidence model, evaluation gates, or maintenance expectations change.
• Update the trigger fixture when adding new positive phrasings, removing stale ones, or expanding scope (the 5/5 floor is a hard validator gate).
• Update the hook regex in skill-patterns.sh whenever fixture positives expose a missed phrasing; verify F1 = 1.0 with eval-triggers before committing.
• Run the full release pipeline via /release -- never bump versions or update CHANGELOG.md from a per-skill edit.