BF Bundle Size Audit
JavaScript bundle size auditor and budget enforcer. Parses webpack stats JSON, Vite bundle report, Rollup output, or Next.js build output to identify largest chunks, flag chunks that exceed configurable size budgets, detect duplicate dependencies across chunks, find treeshaking failures (packages that should be side-effect-free but aren't), and generate CI fail-gate commands. Outputs a GitHub PR annotation-ready summary with per-chunk size, gzip estimate, and actionable optimization suggestions. Zero external API — pure local file analysis. Triggers on "bundle too large", "webpack stats", "chunk size", "bundle budget", "treeshaking", "bundle analyzer", "/bundle-size-audit".
As a process F 32/100 · Will not run — References files that are not bundled: react|react-dom|lodash-es
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: 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") - warning
missing-refreference to a missing file: react|react-dom|lodash-es - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 32/100
- 0Tools and files. 1 referenced file(s) missing: react|react-dom|lodash-es
- 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 (Bundle Size Audit) differs from the folder (phy-bundle-size-audit)
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 4758 tokens
- 100Steps. 10 steps
- 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
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 682: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (20 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.