AC paperbanana
Generate publication-quality academic diagrams, methodology figures, architecture illustrations, and statistical plots from text descriptions using the PaperBanana multi-agent AI pipeline. Also evaluate diagram quality against reference images. Use when: (1) user asks to generate, create, or make a research diagram, methodology figure, system architecture illustration, pipeline diagram, or framework figure, (2) user asks to create a statistical plot, bar chart, or data visualization from CSV/JSON data, (3) user asks to evaluate or score a generated diagram against a reference, (4) user asks to refine or improve a previously generated diagram. NOT for: analyzing existing images, general image generation (non-academic), or chart/graph discussions without explicit generation intent.
As a process C 58/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
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
- 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-shell-known-hostREADME.md:79Pipe-to-shell installer from a well-known host (still executes remote code)curl -LsSf https://astral.sh/uv/install.sh | sh
Files scanned: 7. 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 58/100
- 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
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (paperbanana) differs from the folder (openclaw-paperbanana)
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 18 steps
- 100Execution cost. Instruction body is 1361 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 790: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 18 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 98.