makinotes/elab-trading-skills / elab-research
elab-research
VerifiedEdgeLab 投研编排器。按问题选择财报、产业链、估值、事件、波动率、拥挤度或宏观研究;可按用户提供的方法执行,或在明确接口与权限后委派外部研究 Agent。支持按指定连接读取富途、长桥、IBKR 数据,综合带证据与反证的中性研报。不给买卖方向。 触发方式:/elab-research、/投研、「深度研究一下 X」「用富途/长桥/IBKR 数据研究 X」「研究 X 的期权面」「拉个多空辩论」 EdgeLab research orchestrator: pluggable tools + self-refutation + optional real multi-agent debate (bull/bear + independent judge). Trigger: /elab-research, "deep-research this ticker", "run a bull/bear debate"
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 1.0 KB |
| SKILL.md | skill md | 27.4 KB |
| references/external-research.md | markdown | 3.2 KB |
| references/html-report.md | markdown | 3.2 KB |
| references/research-methods.md | markdown | 6.2 KB |
| references/sector-crowding.md | markdown | 3.6 KB |
| references/tool-registry.md | markdown | 10.0 KB |
| scripts/edgelab_api.py | script | 9.6 KB |
| scripts/iv_metrics.py | script | 2.7 KB |
scripts/iv_metrics.py
View on GitHub#!/usr/bin/env python3
"""Compute IV position metrics; never infer history or recommend a trade."""
import argparse
import json
import math
def checked(value):
if isinstance(value, bool) or not isinstance(value, (int, float)):
raise ValueError("IV values must be numeric")
if not math.isfinite(value) or value < 0:
raise ValueError("IV values must be finite and non-negative")
return float(value)
def calculate(current, *, history=None, low=None, high=None):
current = checked(current)
if history is not None:
if low is not None or high is not None:
raise ValueError("Use history OR bounds, not both")
values = [checked(value) for value in history]
if not values:
raise ValueError("History must contain at least one observation")
low, high = min(values), max(values)
percentile = 100.0 * sum(value < current for value in values) / len(values)
count = len(values)
else:
if low is None or high is None:
raise ValueError("History or both bounds are required")
low, high = checked(low), checked(high)
if low > high:
raise ValueError("Minimum IV must not exceed maximum IV")
percentile, count = None, None
rank = None if low == high else 100.0 * ((current - low) / (high - low))
if rank is not None and not math.isfinite(rank):
raise ValueError("Rank cannot be represented as a finite number")
return {
"current_iv": current,
"minimum_iv": low,
"maximum_iv": high,
"iv_rank": rank,
"iv_rank_status": "undefined_flat_range" if rank is None else "calculated",
"iv_percentile": percentile,
"iv_percentile_status": "history_missing" if history is None else "calculated",
"percentile_definition": "strictly_less_than_current",
"history_count": count,
"out_of_range": current < low or current > high,
"input_alignment": "caller_must_verify_tenor_delta_model_and_window",
}
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--current", type=float, required=True)
parser.add_argument("--unit", choices=("percent", "decimal"), required=True)
parser.add_argument("--history", type=float, nargs="+")
parser.add_argument("--low", type=float)
parser.add_argument("--high", type=float)
args = parser.parse_args()
try:
result = calculate(args.current, history=args.history, low=args.low, high=args.high)
except ValueError as exc:
parser.error(str(exc))
result["input_unit"] = args.unit
print(json.dumps(result, ensure_ascii=False, allow_nan=False))
if __name__ == "__main__":
main()
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Unverified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |