AF makewpfast-bench
This skill should be used when the user asks about a WordPress plugin's or theme's real performance/speed impact, wants to compare the speed of plugins or themes, asks whether a plugin is slow or heavy, or wants to audit the plugins on a WordPress site — e.g. "how fast is WooCommerce", "compare Yoast vs Rank Math speed", "is this plugin slow", "what's the TTFB cost of this plugin", "audit my site's plugins". It queries the MakeWPFast Benchmark API (real measured activation/homepage/wp-admin deltas for ~52,000 WordPress.org plugins and themes) via the bundled mwf-bench CLI.
This skill should be used when the user asks about a WordPress plugin's or theme's real performance/speed impact, wants to compare the speed of plugins or…
As a process F 51/100 · Will not run — References files that are not bundled: scripts/mwf-bench
How to improve
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/mwf-bench - note
frontmatter-keyunknown frontmatter key "domain" - note
frontmatter-keyunknown frontmatter key "type" - note
frontmatter-keyunknown frontmatter key "tools"
Process rating: all ten parameters 51/100
- 0Tools and files. 1 referenced file(s) missing: scripts/mwf-bench
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 843 tokens
- 100Running it twice. No mutating operations
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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 579: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 12 items
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.