AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified Apache-2.0 Self-run

Existing Site Analyzer

skill-sergekostenchuk-ui-ux-agent-skill-system-existing-site-analyzer · by sergekostenchuk

Analyze an existing website before improve, redesign, rebuild, or migration decisions. Use when a project has a current URL, local HTML/codebase, screenshots, sitemap, robots, analytics export, asset folder, or legacy site materials and needs a local-first audit with approval-gated crawling or authenticated access.

↗ Repository
— No reviews yet
0 installs
11 views
0.0% view→install

Install

$ agentstack add skill-sergekostenchuk-ui-ux-agent-skill-system-existing-site-analyzer

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ● Environment & secrets Used
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-sergekostenchuk-ui-ux-agent-skill-system-existing-site-analyzer)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Existing Site Analyzer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Existing Site Analyzer

This skill creates the evidence base for existing-site work. It does not decide rebuild strategy by itself and does not mutate the live site.

Operating Modes

  • local-inventory: inspect local HTML, source files, assets, sitemap, robots, and reports.
  • public-url-review: review public URLs or fetched HTML only after network/crawling approval.
  • screenshot-review: analyze screenshots when URL or source is unavailable.
  • asset-inventory: inventory images, videos, docs, icons, maps, and brand assets.
  • handoff: produce evidence for rebuild-or-improve-advisor and migration-planner.

Required Workflow

  1. Read [references/existing-site-analysis-contract.md](references/existing-site-analysis-contract.md).
  2. Confirm source type and privacy:
  • local files and user-provided public screenshots: allowed;
  • public URL crawling/fetching: approval required if not already requested;
  • authenticated/private pages, analytics, CRM, or CMS: explicit approval and data-handling note required.
  1. Use [assets/existing-site-audit.template.md](assets/existing-site-audit.template.md) for the report.
  2. Record evidence status for every source: Ran, Skipped, Planned, or Manual.
  3. Capture:
  • page inventory;
  • content and IA;
  • SEO/LLM surface;
  • UX and conversion issues;
  • technical constraints;
  • asset inventory;
  • migration risks.
  1. Hand off to rebuild-or-improve-advisor; involve migration-planner if URL structure, redirects, sitemap, robots, schema, or launch risk may change.

Safety Rules

  • Do not crawl private/authenticated pages without explicit approval.
  • Do not store private analytics exports, cookies, tokens, private URLs, or .env values in reports.
  • Do not claim Lighthouse, browser, crawler, or DOM evidence unless it was actually run.
  • Do not change production content, redirects, robots, sitemap, DNS, CMS, or deployment settings.

Handoff Shape

Mode:
Sources:
Evidence status:
Major findings:
SEO/LLM risks:
UX risks:
Technical constraints:
Asset inventory:
Migration risk:
Next owner:

Validation

When editing this skill, run:

python3 $CODEX_HOME/skills/.system/skill-creator/scripts/quick_validate.py $CODEX_HOME/skills/existing-site-analyzer
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $CODEX_HOME/skills/existing-site-analyzer
python3 -m json.tool $CODEX_HOME/skills/existing-site-analyzer/evals/evals.json >/dev/null

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Data & Analytics