CF dex-quant-skill
加密货币量化交易 AI Skill。用自然语言描述交易规则 → 生成策略脚本 → 服务器回测 → 参数优化 → 实时监控。 支持 Binance/Hyperliquid 全币种，6 种优化算法（genetic/bayesian/grid/random/annealing/pso），异步进度推送。 Use when user asks to: 推荐策略, 有什么策略, 推荐, 有现成的吗, 不会写, recommend, suggestions, 创建策略, 创建一个策略, 创建, 建策略, 新策略, 写策略, 做策略, 生成策略, 设计策略, 帮我写, create strategy, new strategy, 弄个策略, 回测, 测一下, 测试, 跑一下, 试试, 看看效果, backtest, test, 历史验证, 优化, 调参, 优化参数, 优化策略, 优化下, optimize, tune, 监控, 部署, 上线, 跑起来, 定时执行, 定时跑, 跑策略, 执行策略, 自动执行, 自动跑, 挂着跑, 定时任务, cron, run, deploy, monitor, 盯盘. This skill MUST be used for ANY request involving trading strategies, backtesting, parameter optimization, or strategy monitoring/execution. Also triggered when user replies with a number (1-6) following a skill prompt with numbered options. Do NOT use coding-agent for these tasks. ========== CRITICAL RULE ========== 当用户要求创建/写/建/做策略时，你必须生成 PYTHON 脚本（使用 data_client + indicators 框架）。 ⛔ 绝对禁止生成 TradingView Pine Script（//@version=5, strategy(), ta.ema(), ta.crossover()）。 ⛔ 绝对禁止生成 MQL4/MQL5 或任何非 Python 的代码。 策略脚本必须包含: from data_client import DataClient + from indicators import Indicators as ind + def generate_signals() 详见下方 §1 的 Python 模板。 ==================================
As a process F 53/100 · Will not run — References files that are not bundled: path
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write
Files scanned: 20. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1185 chars, limit 1024 - warning
body-longSKILL.md body ≈ 6120 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: path - note
frontmatter-keyunknown frontmatter key "runtime" - note
frontmatter-keyunknown frontmatter key "env" - note
frontmatter-keyunknown frontmatter key "binaries"
Process rating: all ten parameters 53/100
- 0Tools and files. 1 referenced file(s) missing: path
- 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
- 70Execution cost. Instruction body is 6120 tokens
- 100Steps. 65 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1184: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -272 emoji in the instructions: noise for the model
- -39 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 42 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 36.