AB upstage-studio
Run document processing workflows using Upstage Document Agent API (v2) — both Studio-UI-configured agents (`agt_xxx`) and programmatically defined Agents/Configs via REST API. Handles file upload, agent/config creation, job execution, and result polling. Use when user asks to run an agent workflow, execute a Studio pipeline, create an agent or config via API, run a Document Agent job, or process documents through parse → classify → extract chains. Triggers on '에이전트 워크플로우 돌려줘', 'Studio 파이프라인 실행해줘', 'Document Agent API', 'config 생성해줘', 'create agent', 'run job'.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
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
-
low Exfiltration
net-credential-useSKILL.md:62Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host; quoted — discussed, not commanded)**API Key**: Always use `os.environ["UPSTAGE_API_KEY"]`. Get your key at [console.upstage.ai/api-keys](https://console.upstage.ai/api-keys) (keys start with `up_`).
vendor-hostquoted
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 60Tools and files. Uses tools (web) 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
- 100Steps. 14 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1744 tokens
- 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)
- +1No license
- +2Single-language instructions
- +3Description length 567: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 14 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.