BB plume-notecard
Plume AI Notecard Generation Service. Triggered when users want to convert topics, long-form text, or reference images into notecards. Supports: topic notecards, long-form text to notecard, reference image notecards (sketch/style transfer/product embed/content rewrite), batch notecards, image-based slide deck notecards (cover+content+back cover), retry. Activate when user mentions: notecard, card, infographic, knowledge poster, visualize article, diagram, summary chart, timeline, turn this article into a graphic, create a visual about XX, use this card's style as reference, use this product image for notecard, replace the content of this notecard, create a series of notecards, split long text into multi-page notecards, notecard slide deck, card slides, notecard presentation, image PPT, image slides, 卡片, 信息卡片, 信息图, 知识图谱海报, 把文章可视化, 图解, 总结图, 时间线图, 把这篇文章转成图, 围绕XX主题做一张图解, 参照这张信息图的风格, 用这张产品图做信息图, 把这张信息图的内容换成, 做一组系列信息图, 把长文拆成多页信息图, 图片幻灯片, 图片PPT, 信息图幻灯片, 信息图PPT, 做一套图片PPT, 做一套信息图幻灯片, infographic slide deck, infographic slides, infographic presentation.
As a process B 70/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Shorten the description to 1024 characters.
- 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 Dangerous commands
cmd-pipe-to-shellSKILL.md:31Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition)- No remote code execution patterns like `curl | bash`
detector
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1060 chars, limit 1024
Process rating: all ten parameters 70/100
- 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. 24 mutating operations with no state check
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 39 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3436 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 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)
- +3Description length 1059: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -214 emoji in the instructions: noise for the model
- -32 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 39 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 55.