AF voyageai
Voyage AI embedding and reranking CLI integrated with MongoDB Atlas Vector Search. Use for: generating text embeddings, reranking search results, storing embeddings in Atlas, performing vector similarity search, creating vector search indexes, listing available models, comparing text similarity, bulk ingestion, interactive demos, and learning about AI concepts. Triggers: embed text, generate embeddings, vector search, rerank documents, voyage ai, semantic search, similarity search, store embeddings, atlas vector search, embedding models, cosine similarity, bulk ingest, explain embeddings.
Voyage AI embedding and reranking CLI integrated with MongoDB Atlas Vector Search.
As a process F 31/100 · Will not run — weak spots: result and completion, when it triggers, inputs and preconditions
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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
-
medium Dangerous commands
cmd-shell-rcSKILL.md:189Writes to a shell startup filevai completions bash >> ~/.bashrc && source ~/.bashrc
Files scanned: 3. 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 31/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (voyageai) differs from the folder (voyageai-skill)
- 50Steps. 2 steps
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Execution cost. Instruction body is 1506 tokens
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 595: enough signal without eating the budget
- +4Structure: 24 headings
- +4Has examples (18 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.