BF vss-deploy-dense-captioning
Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.
Not for VSS profile deploy or video-search ingestion.
As a process F 57/100 · Will not run — References files that are not bundled: ../vss-deploy-profile/SKILL.md, references/deploy-rt-vlm-service.md, references/api-surface-26.05.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
net-credential-useSKILL.md:142Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)export API_KEY="${NGC_CLI_API_KEY:-${RTVI_VLM_API_KEY:-}}" # bearer token used by host-side curl commandsquoted -
low Exfiltration
net-credential-useSKILL.md:152Credential used in a network call (verify the destination is the intended service) (quoted — discussed, not commanded)MODEL_ID="$(curl -fsS "$BASE_URL/v1/models" -H "Authorization: Bearer $API_KEY" | jq -r '.data[0].id // .id')"
quoted
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../vss-deploy-profile/SKILL.md - warning
missing-refreference to a missing file: references/deploy-rt-vlm-service.md - warning
missing-refreference to a missing file: references/api-surface-26.05.md - warning
missing-refreference to a missing file: references/kafka-workflows.md - note
edit-residuethe text marks something as outdated (lines 217): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 57/100
- 0Tools and files. 4 referenced file(s) missing: ../vss-deploy-profile/SKILL.md, references/deploy-rt-vlm-service.md, references/api-surface-26.05.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 32 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Steps. 23 steps
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3214 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 197: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (7 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.