BC cloudarc-bounded-memory-benchmark
Make CloudArc large-package performance reproducible, measurable and safe to ship. Drives the bounded-memory workflow for the .vibo container - streaming pack/unpack inside a fixed RSS ceiling, high-cardinality multi-file archives with SHA-256 dedup, remote-search range telemetry and the CI/manual gates that guard them. Use when changing benchmarks, SLOs, manifest or index cardinality, remote metadata reads or GitHub Actions checks, or when reviewing a large-package MVP before real cloud providers are switched on.
Make CloudArc large-package performance reproducible, measurable and safe to ship.
As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 519 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 4 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Consistency. The Hermes dialect needs category and tags
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 38 steps
- 100Execution cost. Instruction body is 2324 tokens
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 519: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 38 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.