FD jetson-cuda-voice
High-performance offline voice pipeline for NVIDIA Jetson with wake word detection, STT, and TTS.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 9
-
critical Secrets in code
secret-openrouter-keyreferences/VOICE_PIPELINE_NOTES.md:149OpenRouter API key (quoted — discussed, not commanded)- OpenRouter key hardcoded: `sk-o…571`
quoted -
critical Secrets in code
secret-openrouter-keyreferences/VOICE_PIPELINE_NOTES.md:270OpenRouter API key (quoted — discussed, not commanded)OPENROUTER_API_KEY = "sk-o…571"
quoted -
critical Secrets in code
secret-anthropic-keyscripts/voice_pipeline_v2.py:58Anthropic API key (quoted — discussed, not commanded)"sk-a…wAA"
quoted -
critical Secrets in code
secret-openrouter-keyscripts/voice_pipeline.py:372OpenRouter API key (quoted — discussed, not commanded)_OPENROUTER_KEY = os.environ.get("OPENROUTER_API_KEY", "sk-o…571")quoted
Medium and low: 5
-
medium Secrets in code
secret-labelled-tokenreferences/VOICE_PIPELINE_NOTES.md:373Labelled token / key literal (vendor format unknown — verify it is not a live credential)client = anthropic.Anthropic(api_key='BSAu…smP')
-
low Secrets in code
secret-high-entropy-tokenreferences/VOICE_PIPELINE_NOTES.md:373High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)client = anthropic.Anthropic(api_key='BSAu…smP')
quoted -
low Secrets in code
secret-password-literalreferences/VOICE_PIPELINE_NOTES.md:373Hard-coded password / key literal (may be an example)client = anthropic.Anthropic(api_key='BSAu…smP')
-
low Secrets in code
secret-high-entropy-tokenscripts/test_v2_pipeline.sh:164High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)api_key = os.environ.get("ANTHROPIC_API_KEY", "BSAu…smP")fixturequoted -
low Secrets in code
secret-high-entropy-tokenscripts/voice_pipeline_v2.py:419High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)BRAVE_API_KEY = "BSAu…smP"
quoted
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 882 tokens
- 100Running it twice. No mutating operations
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)
- +3Description length 97: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -41 reference files, but SKILL.md never points to them: the model will not open them
- -37 of 8 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.