Skip to content

makinotes/elab-trading-skills / elab-research

elab-research

Verified

EdgeLab 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"

FileKindSize
README.mdmarkdown1.0 KB
SKILL.mdskill md27.4 KB
references/external-research.mdmarkdown3.2 KB
references/html-report.mdmarkdown3.2 KB
references/research-methods.mdmarkdown6.2 KB
references/sector-crowding.mdmarkdown3.6 KB
references/tool-registry.mdmarkdown10.0 KB
scripts/edgelab_api.pyscript9.6 KB
scripts/iv_metrics.pyscript2.7 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()
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: 472kUpdated Claude CodeCodexUnverifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
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 availableStars: 322kUpdated Claude CodeCodexVerifiedInstall