BC content-refresh-impact
Checks whether the pages you updated actually won back search traffic, from live Google Search Console data in your Coupler.io workspace with the refresh dates you give it — clicks, impressions and position before and after each update, measured against how the rest of the site moved over the same weeks, so a site-wide lift isn't credited to the refresh. Use for "did our content refresh work", "did updating those blog posts help", "which page updates recovered traffic", "is refreshing old content worth it", "what happened after we rewrote these pages", "should we keep updating old posts" — even when the user never says "refresh". This is the did-it-work view after an update. For which pages need refreshing in the first place use content-decay-analysis. Google Search Console only.
Checks whether the pages you updated actually won back search traffic, from live Google Search Console data in your Coupler.io workspace with the refresh…
As a process C 60/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 60/100
- 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
- 30Running it twice. 4 mutating operations with no state check
- 55Failures and branches. 1 branches
- 70When it triggers. States when to use, but not when not to
- 85Steps. 34 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3128 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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 7 example trigger phrases
- +3Description length 790: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 34 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.