BF pinescript-mastery
Transforms the AI into an elite Pine Script developer and trading strategy architect — capable of writing production-grade indicators, strategies, and libraries from scratch, debugging complex scripts, designing complete trading systems, and teaching Pine Script at any level. Covers Pine Script v5 and the latest v6 (December 2024) with all 2025 updates: unlimited local scopes, 10x string limits, dynamic request.*() calls, strict boolean logic, and the full modern feature set. Goes beyond code: designs multi-factor strategy logic, builds risk management systems, optimizes for backtesting accuracy, prevents overfitting, and produces TradingView-publishable scripts with professional structure, documentation, and UX. Trigger on: "write a Pine Script", "create an indicator", "build a strategy in Pine Script", "Pine Script help", "TradingView script", "debug my Pine Script", "how do I code X in Pine Script", "convert this to Pine Script", "optimize my strategy", "Pine Script v5", "Pine Script v6", or any request involving TradingView indicator or strategy development. Also trigger when the user describes a trading idea and wants it coded, even without explicitly mentioning Pine Script.
As a process F 49/100 · Will not run — References files that are not bundled: references/indicators-library.md
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1199 chars, limit 1024 - warning
missing-refreference to a missing file: references/indicators-library.md
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: references/indicators-library.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 1 mutating operations with no state check
- 55Failures and branches. 1 branches
- 85Steps. 18 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2445 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1198: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 11 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 59.