BF investment-research-os
投资研究操作系统 v1.2 — 来源可追溯 + 自动数据填入 + 行业量化模型 + 多标的并行。 触发条件：用户输入投资研究对象，要求"投资研究"、"深度研究"、 "投资决策分析"、"研究XXX"、"投资分析"、"对比XXX和YYY"等关键词时使用本 skill。 不写研报，只做判断。核心五问： 市场定价什么？→ 市场错在哪里？→ 预期差在哪里？→ 赔率风险比如何？→ 如何下注？ v1.2新功能（来源可追溯）： - 每个数据点必须标注来源URL、覆盖时段、验证方式 - 报告末尾强制附加「来源与注释」区块 + 「输出检查清单」 - 支持审计轨迹、数据验证、透明度及未来更新 v1.1功能： - 自动解析 Macrotrends/StockAnalysis 数据并填入模板 - 行业生命周期量化判定（基于营收增速+利润率趋势） - 多标的并行比较研究（--targets模式） 架构：6个专业Agent + 1个CIO裁决引擎，10层研究深度，形成研究→假设→建仓→跟踪→调整→退出的完整闭环。 数据源：NeoData（行情/财报）、OpenAlex（学术趋势）、World Bank（宏观）、web搜索（行业/竞争）
投资研究操作系统 v1.2 — 来源可追溯 + 自动数据填入 + 行业量化模型 + 多标的并行。 触发条件：用户输入投资研究对象，要求"投资研究"、"深度研究"、 "投资决策分析"、"研究XXX"、"投资分析"、"对比XXX和YYY"等关键词时使用本 skill。 不写研报，只做判断。核心五问： 市场定价什么？→…
As a process F 35/100 · Will not run — References files that are not bundled: url
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
-
low Risky intent
intent-offensive-securityprompts/agent6-redteam.md:1Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Agent6：红队分析师 (Red Team Analyst)
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: url
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Steps. 99 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1463 tokens
- 100Running it twice. No mutating operations
- low 12 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -212 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 516: enough signal without eating the budget
- +4Structure: 44 headings
- +3Step-by-step instructions: 99 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.