BD CWV Budget Guard
Core Web Vitals budget enforcer that runs Lighthouse against a local dev server or staging URL, extracts LCP, INP, CLS, FCP, and TTFB scores, compares against a project .cwv-budget.json config, and fails CI if any metric regresses. Identifies which source file, image, render-blocking resource, or JavaScript chunk caused each metric violation with specific fix recommendations. Tracks metric trends across runs by appending to a local history file. Works with any framework (Next.js, Vite, CRA, Rails, Django). Zero external cloud account — runs Lighthouse via npx locally. Triggers on "core web vitals", "LCP slow", "CLS regression", "Lighthouse score dropped", "performance budget", "web vitals", "/cwv-check".
As a process D 45/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 45/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 40Consistency. Frontmatter name (CWV Budget Guard) differs from the folder (phy-cwv-budget-guard)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 9 steps
- 100Execution cost. Instruction body is 3152 tokens
- low 10 top-level sections: this looks like several domains in one skill
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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 713: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (13 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.