BF a-stock-data-quant
股市/股票/行情/股价/涨跌/大盘/指数/个股分析——金融/投资/股票/基金/ETF/板块/指数/宏观/外汇/大宗商品/财报/估值/持仓/交易/仓位/量化/因子/回测/选股/期权/衍生品/投行建模/技术指标/行情监控/预警——内置研究框架（红线/检索策略/数据口径/50+方法论 references/scripts）、A股量化数据引擎（12层数据源·bin/quant.py）、多市场数据层（港股/期货/期权/宏观/公告事件·bin/cn/*.py）与 8 个研报写作工作流（读年报/可比公司/深度报告/业绩快评/调研纪要/行业研究/晨会纪要/研报摘要·references/research-workflows/）。金融场景总入口，命中任一上述领域即优先加载；并集成同花顺金融数据服务（hithink-finance，iFinD 级 A股/指数/板块/公募基金/特色数据权威源，接入层见 references/hithink-finance/）；并集成东方财富·妙想（mx-skills，全市场含港股/美股/债券/基金/全球宏观/资讯研报的备用数据接入层，见 references/mx-skills/）。
股市/股票/行情/股价/涨跌/大盘/指数/个股分析——金融/投资/股票/基金/ETF/板块/指数/宏观/外汇/大宗商品/财报/估值/持仓/交易/仓位/量化/因子/回测/选股/期权/衍生品/投行建模/技术指标/行情监控/预警——内置研究框架（红线/检索策略/数据口径/50+方法论…
As a process F 31/100 · Will not run — References files that are not bundled: references/research-workflows/<slug>/, references/hithink-finance/, references/hithink-finance/00-overview.md
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Glob Grep Write Edit WebFetch WebSearch
Files scanned: 68. 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
body-longSKILL.md body ≈ 7715 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/research-workflows/<slug>/ - warning
missing-refreference to a missing file: references/hithink-finance/ - warning
missing-refreference to a missing file: references/hithink-finance/00-overview.md - warning
missing-refreference to a missing file: references/hithink-finance/cli.md - warning
missing-refreference to a missing file: references/hithink-finance/mcp.md - warning
missing-refreference to a missing file: references/hithink-finance/api.md - warning
missing-refreference to a missing file: references/hithink-finance/python-sdk.md - warning
missing-refreference to a missing file: references/mx-skills/{mx-finance-data,mx-finance-search,mx-macro-data,mx-stocks-screener}/ - warning
missing-refreference to a missing file: scripts/get_data.py - warning
missing-refreference to a missing file: references/auth_protocol.md - warning
missing-refreference to a missing file: references/mx-skills/*/references/auth_protocol.md - note
frontmatter-keyunknown frontmatter key "agent_created" - note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 31/100
- 0Tools and files. 11 referenced file(s) missing: references/research-workflows/<slug>/, references/hithink-finance/, references/hithink-finance/00-overview.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
- 30Running it twice. 3 mutating operations with no state check
- 70Execution cost. Instruction body is 7715 tokens
- 100Steps. 208 steps
- 100Consistency. Name and required fields are in place
- low 19 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- -231 emoji in the instructions: noise for the model
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +3Description length 505: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 208 items
- +4Reference files are cited in the instructions (47 of 47)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 44.