SKILLEMALL.ai
GitHub ↗ RU Sign in

AF bybit-orderbook-backtester

Download, process, and backtest ByBit derivatives historical order book data. Use this skill when the user wants to: (1) download historical order book snapshots from ByBit's derivatives history-data page using Selenium automation, (2) process/unzip ob500 JSONL files and filter to depth 50, (3) run any of 10 order-book-based trading strategies (Order Book Imbalance, Breakout, False Breakout, Scalping, Momentum, Reversal, Spoofing Detection, Optimal Execution, Market Making, Latency Arbitrage) against the data, or (4) generate full backtest performance reports with PnL, Sharpe ratio, win rate, max drawdown, and strategy comparison. Triggers on: "bybit order book", "order book backtest", "download bybit data", "ob500", "order book imbalance", "spoofing detection strategy", "market making backtest", "crypto order book", "depth of book backtest", "bybit historical data".

modbender/skill-library-mcp Agent Skills author: modbender MIT 6 files body ≈ 991 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Download, process, and backtest ByBit derivatives historical order book data.

As a process F 42/100 · Will not run — References files that are not bundled: scripts/download_orderbook.py, references/bybit_data_format.md, scripts/process_orderbook.py

ProcedurePlaywrightCloudflareData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
74
Run on models
none yet
Process rating
F
42/100
Will not run
References files that are not bundled: scripts/download_orderbook.py, references/bybit_data_format.md, scripts/process_orderbook.py
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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

  • warning missing-ref reference to a missing file: scripts/download_orderbook.py
  • warning missing-ref reference to a missing file: references/bybit_data_format.md
  • warning missing-ref reference to a missing file: scripts/process_orderbook.py
  • warning missing-ref reference to a missing file: scripts/backtest.py
  • warning missing-ref reference to a missing file: references/strategies.md

Process rating: all ten parameters 42/100

Will not run. References files that are not bundled: scripts/download_orderbook.py, references/bybit_data_format.md, scripts/process_orderbook.py
  • 0Tools and files. 5 referenced file(s) missing: scripts/download_orderbook.py, references/bybit_data_format.md, scripts/process_orderbook.py
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (bybit-orderbook-backtester) differs from the folder (bybit-order-book)
  • 50Failures and branches. 0 branches, has a failure section
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 17 steps
  • 100Execution cost. Instruction body is 991 tokens
  • 100Running it twice. No mutating operations

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 879: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 9 example trigger phrases
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 17 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.