BC alibabacloud-parse-x
Alibaba Cloud Parse-X intelligent document parsing and extraction tool. Supports two capabilities: (1) Parse — convert documents, images, and audio/video to structured Markdown/JSON/HTML with layout, table, and synopsis support; (2) Extract — schema-driven information extraction with citations from parsed or new documents. Uses Parse-X HTTP (Spectrum gateway, Bearer token via DASHSCOPE_API_KEY). **When to use this skill** — the user asks to: - Parse / convert / analyze any document, image, spreadsheet, or media file (PDF, Word, PPT, Excel, Markdown, HTML, images, audio, video) - Extract structured fields or entities from a document - Convert files to Markdown or JSON format - Process files with mentions of: 解析, 文档解析, 文件解析, 表格, Excel, xlsx, xls, PDF, Word, PPT, 合同, 发票, 报告, 图片, 本地文件, 上传, markdown, JSON, 提取, 抽取, 字段, parse, extract, document parsing, parse file, 解析文档, 解析文件, 文件转换, 图片解析, 表格提取
Alibaba Cloud Parse-X intelligent document parsing and extraction tool.
As a process C 53/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Exfiltration
read-dotenvskill-card.md:31Reads a .env file (detector / deny-list definition)Mitigation: Set DASHSCOPE_API_KEY using an approved secrets manager or a safe environment-variable setup; do not use `export $(cat .env | xargs)`.
detector -
low Exfiltration
read-dotenvSKILL.md:445Reads a .env filecp .env.example .env
-
low Exfiltration
read-dotenvSKILL.md:460Reads a .env filesource .env
-
low Exfiltration
read-dotenvSKILL.md:462Reads a .env fileexport $(cat .env | xargs)
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 53/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 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
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4803 tokens
- 85Steps. 20 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 907: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 31 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (17 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.