AC render-on-hermes
Use whenever any other render-* skill loads, or any time the user asks you to do something on Render. Tells you that this Hermes container has the Render MCP server pre-registered with full MCP tool access for the provided API key and that the `render` CLI is NOT installed in this image, so skip every "install MCP", "install CLI", and "run render CLI" step that upstream render-* skills describe.
Tells you that this Hermes container has the Render MCP server pre-registered with full MCP tool access for the provided API key and that the render CLI is…
As a process C 52/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 398 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 52/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Steps. 15 steps, 5 vague phrases
- 60Consistency. The Hermes dialect needs category and tags
- 65Failures and branches. 3 branches
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1625 tokens
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 398: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 15 items
- +4Has examples (3 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.