SkillVaultskills Browse all 1,000+ skills

Frontend · Version 1.0.0 · Reviewed 2026-08-02

Image Function Auditor

Improve image purpose classification and alternative-text review with evidence, explicit trade-offs, and a verification plan.

4 method steps 6 documented failure modes 5 diagnostic checks 7 quality gates

Determines image purpose from surrounding context and interaction, then verifies appropriate text alternatives, decorative handling, labels, and complex-image descriptions.

₹199 one-time

Get this skill archive

Install in your AI coding tool

SkillVault packages this skill in the open Agent Skills format for five leading coding tools.

What this skill helps you do

  • Image purpose classification
  • Alternative-text review
  • Complex image description check

How Image Function Auditor works

You provide

Build definition, timings, and cache statistics

It inspects

Layer ordering and secret exposure for image purpose classification

It decides

A alternative-text review change that keeps every gate intact

You verify

Per-stage duration and cache hit rate re-measured

What it checks first

Image Function Auditor determines image purpose from surrounding context and interaction, then verifies appropriate text alternatives, decorative handling, labels, and complex-image descriptions. Use it when the work involves Image purpose classification, Alternative-text review, Complex image description check.

  1. Layer ordering relative to change frequency, which determines whether the cache is ever reused.
  2. Whether the build is reproducible, or depends on floating tags and network state at build time.
  3. Image provenance and base-image currency, since most container vulnerabilities come from the base.
  4. Whether secrets enter the build context or an intermediate layer, where they persist even if deleted later.
  5. The critical path of the pipeline, distinguished from total pipeline time.

Failure modes it recognizes

  • Copying the entire source before installing dependencies, invalidating the dependency cache on every commit.
  • A secret passed as a build argument and permanently embedded in image history.
  • A `latest` base tag making builds nondeterministic and silently changing runtime behavior.
  • Running as root because the image never declared a user, expanding container escape impact.
  • A cache key that includes a timestamp, so the cache never hits.
  • Parallel jobs sharing a mutable cache and corrupting each other intermittently.

Answers it will reject

  • Adding retries to a flaky pipeline step instead of fixing the nondeterminism, which triples the failure latency.
  • Building images in the same stage as tests, shipping test tooling and credentials to production.
  • Disabling a security scan to unblock a release without recording an exception and an expiry.
  • Optimizing total pipeline duration when the critical path is a single serial step.

Decision rules it applies

  • Order build layers from least to most frequently changed, and copy dependency manifests before source.
  • Use multi-stage builds so the runtime image contains only runtime artifacts.
  • Pin base images by digest for reproducibility and update them deliberately.
  • Never weaken a gate to increase speed; make the gate faster or move it, but keep the signal.

Evidence it asks for

  • Measure per-stage duration and cache hit rate to find where the pipeline actually spends time.
  • Scan the built image and compare findings against the base image to attribute ownership.
  • Verify no secret material exists in image history with a layer inspection.

The method inside

  1. Map the artifact, actors, boundaries, and invariants relevant to image purpose classification.
  2. Trace concrete failure or abuse paths for alternative-text review; do not report checklist items without a mechanism.
  3. Prioritize complex image description check findings by impact, likelihood, confidence, and cost of correction.
  4. Recommend the smallest defensible change, then define how an independent reviewer can verify it.

Deliverables

  • Image purpose classification assessment
  • Alternative-text review decision and action plan
  • Complex image description check verification checklist

Evidence requirements

  • Interface code, rendered behavior, and user journey
  • Browser/device matrix and accessibility tree
  • Performance and usability observations

Quality gates

  • Every material claim traces to supplied evidence or is labeled as a hypothesis.
  • The response follows the declared deliverable contract.
  • No execution, access, measurement, or verification is invented.
  • Secrets and personal data are redacted rather than repeated.
  • The user receives a concrete independent verification step.
  • The relevant failure modes in this domain were considered rather than only the reported symptom.
  • No listed anti-pattern was recommended as a solution.

Example task

Input

Audit the images on this marketing and checkout flow, including linked logos, icon-only buttons, decorative illustrations, and a pricing chart.

Expected output

Classify each image as informative, functional, decorative, text-bearing, or complex before judging its alternative. Functional images use the action name, decorative assets leave the accessibility tree, linked logos avoid duplicate link text, and complex charts expose the conclusion plus equivalent underlying data...

Boundaries and compatibility

Ideal for

  • Image purpose classification: produce a decision or artifact grounded in supplied evidence.
  • Alternative-text review: produce a decision or artifact grounded in supplied evidence.
  • Complex image description check: produce a decision or artifact grounded in supplied evidence.

Out of scope

  • Treating automated accessibility scans as complete
  • Changing visual style without preserving behavior

Agent compatibility

  • GitHub Copilot Agent Skills
  • Cursor Agent Skills
  • Claude Code Skills
  • OpenAI Codex Skills
  • JetBrains Junie Skills

Tool policy: Advisory by default. No tools are assumed. If the host provides tools, use read-only evidence gathering unless the user explicitly approves a scoped write or execution action.