CF office-recalculate
Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.
Promises to refresh spreadsheet formula caches and validate results via LibreOffice Kit. Single instruction file at 398 tokens, no scripts. Safety scores 100, quality 56, process 20—mixed signal. Broken references and missing files noted; skill is incomplete. No model runs or sandbox testing performed.
LibreOffice Kit itself must be present in your environment—not guaranteed out of the box. The instruction serves as a starting point but needs error handling and environment-specific adjustments. Install only if you're prepared to adapt it to your setup.
Refresh spreadsheet formula caches and verify calculated values with LibreOffice Kit.
As a process F 20/100 · No process to follow — References files that are not bundled: ../office/references/sidecar.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
missing-refreference to a missing file: ../office/references/sidecar.md
Process rating: all ten parameters 20/100
- 0Tools and files. 1 referenced file(s) missing: ../office/references/sidecar.md
- 0Steps. Prose only: no discrete steps
- 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
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 398 tokens
- 100Running it twice. No mutating operations
- low The response is described with custom markup (4 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 85: 120–800 characters recommended
- +4Structure: 1 headings, hard to scan
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.