AC wm-report-extract
财报 PDF（年报/半年报/季报，A 股 + 港股 IFRS）内容理解与按需可溯源提取。双轨转换（Docling FAST + PyMuPDF 有框线表格接管 + ACCURATE 报表页精修）→ 可提取性 meta → adapt-plan 提取剧本 → 全表 records 预提取 → materialize 分表 → 定型晋升 + 质量门（勾稽校验/数值存在性/quote 回验）→ review-extract 独立审核。每个数值带页码与原文 quote 溯源，无 quality.json / review.json 不得给下游。Standalone——`fetch --pdf-url` 无需任何 API key 即可全链路运行；可选接入 WinMale 平台启用 symbol 模式。Use when the user asks to extract or locate data in a financial report PDF (annual/semi-annual/quarterly), e.g. 货币资金、前十大股东、分红方案、全量核心数据、第 N 页内容。
财报 PDF（年报/半年报/季报，A 股 + 港股 IFRS）内容理解与按需可溯源提取。双轨转换（Docling FAST + PyMuPDF 有框线表格接管 + ACCURATE 报表页精修）→ 可提取性 meta → adapt-plan 提取剧本 → 全表 records 预提取 → materialize…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "display_name"
Process rating: all ten parameters 52/100
- 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
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 51 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2373 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
- +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
- -32 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 493: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 51 items
- +4Has examples (15 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.