BC paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Codex-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
Generate publication-quality AI illustrations for academic papers using Gemini image generation.
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Exfiltration
exfil-secret-in-urlSKILL.md:281Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)URL="https://generativelanguage.googleapis.com/v1beta/models/gemi…ent?key=…"
known servicequoted -
low Exfiltration
exfil-secret-in-urlSKILL.md:343Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)URL="https://generativelanguage.googleapis.com/v1beta/models/gemi…ent?key=…"
known servicequoted -
low Exfiltration
exfil-secret-in-urlSKILL.md:413Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)URL="https://generativelanguage.googleapis.com/v1beta/models/gemi…ent?key=…"
known servicequoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6578 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 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. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 6578 tokens
- 100Tools and files. No external tools needed
- 100Steps. 73 steps
- 100Consistency. Name and required fields are in place
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
- +4Description does not say when NOT to use the skill (false activations)
- -218 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 318: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 73 items
- +3Output format is stated explicitly
- +4Has examples (11 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.