AB upstage-builder
Build pipelines, agents, RAG flows, and full web services by combining Upstage Solar models, embeddings, and document APIs. Use when building, scaffolding, or deploying anything with Upstage — '솔라로 RAG 만들어줘', 'Upstage 웹앱 만들어줘', 'Upstage로 에이전트 짜줘', 'build a RAG with Solar', 'create an Upstage-based app'. Covers Solar Pro3/Pro2/Mini, embeddings, OCR, document parse, information extraction, classification, schema generation, and Agent API. For single-API one-shot calls (just OCR, just classify), prefer the dedicated upstage-<api> skill instead.
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:57Credential 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"]`. Never hardcode keys. Users get their key from [console.upstage.ai](https://console.upstage.ai).
vendor-hostquoted
Files scanned: 18. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (bash, 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
- 100Steps. 72 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2743 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 (4 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 547: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 72 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 94.