CB nemotron-retrieval-recipes
Use for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval.
Use for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval.
As a process B 73/100 · Nearly there — weak spots: running it twice, progress reporting
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 files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.
Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.
How to improve
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 4
✓ No critical or high findings
Medium and low: 4
-
medium Obfuscation
obf-base64-blobreferences/embed.md:127Long base64-looking blob[walkthrough at the supported revision](https://github.com/NVIDIA-NeMo/Nemotron/blob/db63…47c/docs/nemotron/embed/multimodal.md).
-
medium Obfuscation
obf-base64-blobreferences/multimodal-data.md:137Long base64-looking blob- [Data contract at the supported Nemotron revision](https://github.com/NVIDIA-NeMo/Nemotron/blob/db63…47c/docs/nemotron/embed/data-reference.md).
-
medium Obfuscation
obf-base64-blobreferences/multimodal-data.md:138Long base64-looking blob- [SDG configuration at the supported Nemotron revision](https://github.com/NVIDIA-NeMo/Nemotron/blob/db63…47c/docs/nemotron/embed/sdg-reference.md).
-
medium Obfuscation
obf-base64-blobreferences/rerank.md:93Long base64-looking blob[reranker guide at the supported revision](https://github.com/NVIDIA-NeMo/Nemotron/blob/db63…47c/docs/nemotron/rerank/README.md#fine…age
Files scanned: 8. 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 73/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 54 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2980 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (17 tags): a typed call is more reliable
- low No test case covers injection arriving through data
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 140: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 54 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.