AF renesas-search
Search and recommend Renesas semiconductor solutions for embedded system design. Triggers ONLY when the user explicitly mentions "Renesas" (or "瑞萨") OR names a Renesas product family (DA14xxx, RA, RX, RL78, RZ, ISL, RAA, EL, HS, etc.). Do NOT trigger for generic embedded/electronic questions without a Renesas mention. Primary data source: Renesas official website (www.renesas.com) and official datasheets. All chip parameters MUST be fetched from official datasheets or renesas.com product pages. When a solution is provided, the corresponding chip datasheet PDF must be downloaded to the current working directory under "embedded_dev/renesas/datasheet/".
Search and recommend Renesas semiconductor solutions for embedded system design.
As a process F 48/100 · Will not run — References files that are not bundled: workspace/<PartNumber>_datasheet.pdf, ../workspace/<PartNumber>_datasheet.pdf
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 · 0
✓ No critical or high findings
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 659 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
missing-refreference to a missing file: workspace/<PartNumber>_datasheet.pdf - warning
missing-refreference to a missing file: ../workspace/<PartNumber>_datasheet.pdf
Process rating: all ten parameters 48/100
- 0Tools and files. 2 referenced file(s) missing: workspace/<PartNumber>_datasheet.pdf, ../workspace/<PartNumber>_datasheet.pdf
- 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
- 60Result and completion. Output format stated, no completion criterion
- 60Consistency. The Hermes dialect needs category and tags
- 85Steps. 60 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2932 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 658: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 60 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.