BD china-stocks-daily-review
A股市场行情分析 Skill，支持生成三类报告：盘前市场综述、盘中市场简评、盘后复盘报告。 China A-Share Market Daily Review Skill — generates 3 report types: Pre-Market Briefing, Intraday Snapshot, Post-Market Review. 【触发词 · Trigger Words】开盘前分析、盘前综述、早盘预判、今天关注什么、盘中异动、午间复盘、 收盘复盘、今日行情怎么样、市场情绪、板块轮动、主线在哪、今天主线、连板梯队、 涨停分析、北向资金、南向资金、资金动向、成交额、全天行情、A股今日、复盘报告、 今日市场、行情综述、开盘情绪、涨跌停统计、市场概况、明日策略、今日策略。 Pre-market analysis, intraday alert, post-market recap, market sentiment, sector rotation, limit-up ladder, northbound/southbound flow, turnover, A-share today, daily review, tomorrow's strategy. 【数据架构 · Data Architecture】三层工具降级体系：Tushare Pro 官方 API（第一优先）→ AKShare 开源库（第二优先）→ 搜索引擎实时抓取（兜底）。每个数据项独立降级，数据缺失留空不臆想。 3-tier fallback: Tushare Pro API (primary) → AKShare (secondary) → Search Engine (final fallback). Each data item degrades independently; missing data is left blank, never fabricated. 【不适用场景 · Out of Scope】个股深度分析、宏观政策专项解读、选股推荐、龙虎榜席位分析、期权策略。 In-depth individual stock analysis, macro policy interpretation, stock picking, top-list broker analysis, options strategies.
As a process D 44/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
The same skill appears in 1 more place: ClawHub
How to improve
- 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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11615 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (china-stocks-daily-review) differs from the folder (china-a-stocks-daily-review)
- 40Execution cost. Instruction body is 11615 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 100Steps. 142 steps
- low 11 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
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1021: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 55 headings
- +3Step-by-step instructions: 142 items
- +4Has examples (37 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.