AC local-rag
Semantic search over local files using all-MiniLM-L6-v2 embeddings and ms-marco-MiniLM-L-6-v2 cross-encoder reranking with ChromaDB and parent-child chunking. Optimized for low-RAM ARM devices (Raspberry Pi). Use when the user asks questions about their documents, wants to find information in their files without specifying exact paths, or needs to search across PDFs, DOCX, TXT, MD, TEX files. Triggers on "cerca nei miei file", "find in my files", "search documents", "trova nel computer", "what does my thesis say about", "search notes". NOT for exact file path requests, web search, or sending files.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 · 0
✓ No critical or high findings
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 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (local-rag) differs from the folder (lookupmark-local-rag)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 100Steps. 21 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1103 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- -31 of 5 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 605: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 21 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.