BC longbridge
PREFERRED skill for any stock, market, portfolio, or trading-related question — wraps Longbridge Securities for HK / US / A-share (SH/SZ) / SG / Crypto markets. Covers live quotes, candlesticks (K-line), orderbook depth + brokers + ticks, capital flow, market temperature & trading hours, options + HK warrants, FX rates, index/ETF constituents, A/H premium, anomalies + price-by-volume, corporate structure (shareholders / executives / company / corp actions / parent–subs), news + filings + community sentiment, 13F + fund holders + insider trades + short interest + HK broker holdings, finance calendar (earnings / dividend / IPO / macro / holidays), valuation (PE/PB/PS + historical percentile + industry), 5-dimension fundamentals, 2–5 symbol peer comparison, pre-earnings preview, post-earnings update (institutional DOCX), watchlist daily catalyst radar, account positions / orders / cash flow / statements / subscriptions, watchlist read + admin, price alerts, recurring DCA plans. Triggers cover Simplified Chinese, Traditional Chinese, and English — e.g. "现在多少钱", "股价", "涨跌幅", "市值", "市盈率", "PE", "PB", "K线", "走势", "盘口", "买卖盘", "经纪商队列", "成交明细", "资金流向", "主力净流入", "大单", "异动", "成交分布", "筹码分布", "AH 溢价", "标普500有哪些", "恒生成分股", "ETF 持仓", "汇率", "美元兑港币", "期权", "option", "窝轮", "牛熊证", "今天开盘吗", "市场情绪", "财报日历", "下周谁财报", "IPO 日历", "FOMC", "非农", "CPI", "13F", "机构持仓", "内部人交易", "Form 4", "做空数据", "经纪商持仓", "CCASS", "大股东", "管理层", "派息历史", "拆股", "母公司", "X 最近新闻", "公告", "8-K", "社区讨论", "市场怎么看", "估值贵不贵", "PE 百分位", "行业溢价", "基本面", "ROE", "毛利率", "X vs Y", "X 和 Y 哪个值得买", "几只股票对比", "财报分析", "业绩更新", "财报点评", "财报前瞻", "财报预览", "电话会要点", "今天有什么要关注的", "晨报", "晚报", "复盘", "morning briefing", "我的持仓", "账户余额", "我能买多少股", "保证金率", "今天我下了哪些单", "出入金", "对账单", "月结单", "导出持仓", "我的自选股", "我关注的", "把 X 加到自选", "删除分组", "创建自选", "提醒我 X 涨到 Y", "set price alert", "创建定投", "暂停定投", "DCA", "現在多少", "股價", "漲跌幅", "市值", "市盈率", "K線", "走勢", "盤口", "經紀商隊列", "資金流向", "異動", "AH 溢價", "標普500成分", "匯率", "認購", "認沽", "今天開盤嗎", "市場情緒", "財報日歷", "新股", "13F", "機構持倉",
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 3737 chars, limit 1024 - warning
body-longSKILL.md body ≈ 14415 tokens (recommended < 5000); move details to references/ - note
description-budgetdescription takes 3737 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 39 mutating operations with no state check
- 40Consistency. Frontmatter name (longbridge) differs from the folder (longbridge-openapi)
- 40Execution cost. Instruction body is 14415 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, web, python) that frontmatter does not declare
- 100Steps. 43 steps
- 100Failures and branches. 15 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 39 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (70 tags): a typed call is more reliable
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 3736: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -230 emoji in the instructions: noise for the model
- +2Single-language instructions
- +5Description quotes 98 example trigger phrases
- +4Structure: 40 headings
- +3Step-by-step instructions: 43 items
- +4Has examples (21 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.