{
  "markdown": "# url-eval\n\nA Claude Code skill that evaluates candidate domain names for a website — scoring them across 8 research-backed dimensions, checking availability, and suggesting alternatives you may not have considered.\n\n## What it does\n\nUpload a site description and a list of candidate URLs, and `/url-eval` produces a structured Markdown report with:\n\n- **Top 3 recommendations** — score, narrative, availability status\n- **Candidate narratives** — plain-English analysis of each domain you submitted\n- **Full score table** — all candidates + alternatives, sorted by overall score\n\nScoring criteria are derived from academic and industry research on domain name memorability, spelling reliability, brand fit, and more. The `--update` flag triggers a live web search to supplement the baked-in research with current findings before scoring.\n\n## Installation\n\n### From the mackayi marketplace (recommended)\n\n```\n/plugin marketplace add keithmackay/mackayi\n/plugin install url-eval@mackayi\n```\n\n### Claude Code\n\n```bash\ngit clone https://github.com/keithmackay/url-eval ~/.claude/plugins/url-eval\ncd ~/.claude/plugins/url-eval\n\nmkdir -p ~/.claude/skills/url-eval\nln -sf \"$(pwd)/SKILL.md\" ~/.claude/skills/url-eval/SKILL.md\n```\n\nRestart Claude Code, type `/`, and confirm `url-eval` appears in the autocomplete list.\n\n### Codex\n\nAdd an entry to your marketplace JSON (`~/.agents/plugins/marketplace.json`, create if absent):\n\n```json\n{\n  \"name\": \"personal\",\n  \"interface\": { \"displayName\": \"Personal Plugins\" },\n  \"plugins\": [\n    {\n      \"name\": \"url-eval\",\n      \"source\": { \"source\": \"local\", \"path\": \"/path/to/url-eval/\" },\n      \"policy\": { \"installation\": \"AVAILABLE\", \"authentication\": \"ON_INSTALL\" },\n      \"category\": \"Productivity\"\n    }\n  ]\n}\n```\n\nThen invoke with `/url-eval`.\n\n### Antigravity\n\nThe root `SKILL.md` is natively compatible — no conversion needed.\n\n**Global install** (all workspaces):\n```bash\ncp -r /path/to/url-eval/ ~/.gemini/antigravity/skills/url-eval/\n```\n\n**Workspace install** (current project only):\n```bash\ncp -r /path/to/url-eval/ .agents/skills/url-eval/\n```\n\nSkills are auto-discovered. You can also invoke by name: `/url-eval`.\n\n### Gemini CLI\n\nGemini CLI installs extensions directly from GitHub:\n\n```bash\ngemini extensions install https://github.com/keithmackay/url-eval\n```\n\nTo update:\n```bash\ngemini extensions update url-eval\n```\n\nThe skill is auto-discovered from `GEMINI.md` after installation.\n\n## Usage\n\n### Interactive mode (recommended)\n\n```\n/url-eval\n```\n\nClaude will ask for your site description, then your candidate URLs — one question at a time.\n\n### Inline mode\n\n```\n/url-eval --site \"description of your site\" candidate1.com candidate2.io\n```\n\n### With research refresh\n\n```\n/url-eval --update --site \"description\" candidate1.com\n```\n\nRuns live web searches for recent domain naming research before scoring. Changes apply to the current session only; see [Updating the research baseline](#updating-the-research-baseline) to make them permanent.\n\n## Scoring dimensions\n\n| Dimension              | Weight | What it measures |\n|------------------------|--------|-----------------|\n| Memorability           | 20%    | Length, syllables, distinctiveness |\n| Spelling Reliability   | 15%    | Typo risk, homophones, hyphens |\n| Pronunciation Clarity  | 10%    | Ambiguity, silent letters |\n| Associations           | 15%    | Positive/negative connotations, cultural fit |\n| Cleverness / Brand Fit | 10%    | Uniqueness, trademark potential |\n| Relevance to Purpose   | 15%    | How well the name signals site content |\n| Competitor Overlap     | 10%    | Similarity to existing brands |\n| TLD Appropriateness    | 5%     | TLD trust and context fit |\n\n**Overall score: 20–100.** Scores above 70 are strong candidates.\n\n## Research foundation\n\nScoring criteria are drawn from a curated research summary in [`docs/research/DOMAIN_NAME_RESEARCH.md`](docs/research/DOMAIN_NAME_RESEARCH.md), which covers 30+ academic and industry sources on memorability, spelling reliability, TLD trust, brand distinctiveness, and more.\n\nRun `/url-eval --update` to supplement the baked-in summary with live web searches for current findings. The skill will produce an Update Report at the top of the response describing what, if anything, changed.\n\n## Updating the research baseline\n\nTo make research updates permanent:\n\n1. Run `/url-eval --update` and note the findings\n2. Edit [`docs/research/DOMAIN_NAME_RESEARCH.md`](docs/research/DOMAIN_NAME_RESEARCH.md) with new findings\n3. Update the `<!-- RESEARCH_SUMMARY_START -->` section in `SKILL.md` to match\n4. If installed via symlink (recommended): no action needed — the symlink always points to the latest file. If installed via copy: `cp SKILL.md ~/.claude/skills/url-eval/SKILL.md`\n5. Commit and push\n\n## Development\n\nManual test cases covering all 8 phases of the skill are in [`docs/testing/TEST_CASES.md`](docs/testing/TEST_CASES.md). There is no automated test runner — tests are invoked manually inside Claude Code.\n\nTo run a test:\n\n```\n/url-eval --site \"recipe sharing platform for home cooks\" recipebox.com homechef.io cookwith.me\n```\n\nCompare the output against the expected behavior documented in `TEST_CASES.md`. Record actual outputs in [`docs/testing/SAMPLE_RUNS.md`](docs/testing/SAMPLE_RUNS.md) for regression reference.\n\nTo contribute a change, see [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## Compatibility\n\n| Feature | Claude Code | Codex | Antigravity | Gemini CLI |\n|---------|:-----------:|:-----:|:-----------:|:----------:|\n| Core skill | ✅ | ✅ | ✅ | ✅ |\n| Interactive input prompting | ✅ | ✅ | ✅ | ✅ |\n| Inline mode (`--site`, URL args) | ✅ | ✅ | ✅ | ✅ |\n| `--update` flag (web search) | ✅ | ✅ | ✅ | ✅ |\n| 8-dimension scoring | ✅ | ✅ | ✅ | ✅ |\n| Availability checking (web search) | ✅ | ✅ | ✅ | ✅ |\n| Alternative suggestions | ✅ | ✅ | ✅ | ✅ |\n\nLegend: ✅ Supported\n\nAll features are fully portable — the skill uses no platform-specific metadata, triggers, or tool APIs beyond standard web search.\n\n## References\n\n- **Claude Code Skills:** https://code.claude.com/docs/en/skills\n- **Codex Plugins:** https://developers.openai.com/codex/plugins/build\n- **Antigravity Skills:** https://antigravity.google/docs/skills\n- **Gemini CLI Extensions:** https://github.com/google-gemini/gemini-cli/blob/main/docs/extension.md\n- **Agent Skills open standard:** https://agentskills.io/home\n\n## Changelog\n\nSee [CHANGELOG.md](CHANGELOG.md) for release history.\n\n## License\n\n[MIT](LICENSE)\n",
  "bytes": 6475,
  "sha": "2c9656240903925f7c432d417e3265520af61fb16cd6a1b9b6482ae907ece254",
  "repo_slug": "keithmackay/url-eval",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_keithmackay_url_eval_e253d37c/readme"
}