BB paper_viz
从论文 PDF、实验截图或表格图片中提取实验结果，自动匹配图表类型，调用 Python 生成确定性图表，并导出 PNG、PDF 和 LaTeX；默认在用户指定输出根目录下自动创建与论文同名的文件夹保存结果。
As a process B 71/100 · Nearly there — weak spots: consistency, running it twice, progress reporting
ReferenceLaTeXSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 71/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 10 mutating operations with no state check
- 40Consistency. Frontmatter name (paper_viz) differs from the folder (paper-viz)
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 124 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1897 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 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 103: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 124 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.
External checks
ClawHub: clean
The only supported concern is ordinary local file creation, which appears purpose-aligned but should be used with attention to where files are written.
LLM: benign (medium) · VirusTotal: · 29 May 2026