BF a-share-fact-check
对中国上市公司相关的荐股文章、公众号推文、投资点评、雪球/小红书帖子、业绩说明会转述等"已存在的内容"做事实核验：把其中的财务数字与表态逐条拆出， 强制对齐 A 股/港股官方披露（巨潮资讯网 CNINFO、沪深北交易所、互动易/上证e互动、定期报告、临时公告、招股书），输出一份"哪些为真 / 哪些对不上 / 哪些查无此据 / 哪些是纯话术"的核验体检报告。当用户贴出一篇荐股文、股票点评、公司分析或截图并想知道"这靠不靠谱 / 数据是不是真的 / 帮我核实一下"时，当用户想核对某上市公司被引用的营收、净利润、毛利率、订单、市占率、股权或战略表态时，都要使用本 skill。 关键区分：本 skill 只"审计已有内容里的断言"，方向是从内容出发、去官方披露里对账；它不"从 ticker 生成一份新的个股研究报告"—— 凡是"帮我分析这只股票 / 做估值 / 做杜邦 / 建个模型"这类生成与判断类需求，不属于本 skill 范围。
对中国上市公司相关的荐股文章、公众号推文、投资点评、雪球/小红书帖子、业绩说明会转述等"已存在的内容"做事实核验：把其中的财务数字与表态逐条拆出， 强制对齐 A 股/港股官方披露（巨潮资讯网 CNINFO、沪深北交易所、互动易/上证e互动、定期报告、临时公告、招股书），输出一份"哪些为真 / 哪些对不上 /…
As a process F 35/100 · Will not run — References files that are not bundled: 真实URL, references/narrative-errors.md, references/normalization.md
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 · 0
✓ No critical or high findings
Files scanned: 16. 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: 真实URL - warning
missing-refreference to a missing file: references/narrative-errors.md - warning
missing-refreference to a missing file: references/normalization.md - warning
missing-refreference to a missing file: references/evidence-rules.md
Process rating: all ten parameters 35/100
- 0Tools and files. 4 referenced file(s) missing: 真实URL, references/narrative-errors.md, references/normalization.md
- 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. 45 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3262 tokens
- 100Running it twice. No mutating operations
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
- -263 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 418: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.