JasonColapietro/suede-creator-skills / skills/suede-ai-seo
suede-ai-seo
VerifiedSuede Answer Engine Optimization Skills. Use when asked to "improve our AI citations" or optimize for ChatGPT/Perplexity: crawler policy, entity consistency, citation-ready pages, off-site evidence and prompt-panel measurement. NOT FOR: nine-lane technical SEO audits (suede-seo-audit), quick promotion grades (suede-visibility-grader), or funnel implementation (suede-site-alchemy).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.4 KB |
| SKILL.md | skill md | 15.9 KB |
| agents/openai.yaml | config | 574 B |
| evals/evals.json | config | 12.2 KB |
| references/ai-crawlers.md | markdown | 3.4 KB |
| references/citations-vs-recommendations.md | markdown | 4.1 KB |
| references/content-patterns.md | markdown | 5.5 KB |
| references/entity-graph.md | markdown | 4.6 KB |
| references/measurement.md | markdown | 6.6 KB |
| references/okf.md | markdown | 2.5 KB |
| references/platform-notes.md | markdown | 6.8 KB |
| references/sources.md | markdown | 2.4 KB |
| references/worked-contract.md | markdown | 2.1 KB |
references/ai-crawlers.md
View on GitHub# AI Crawler Policy
Checked against each operator's documentation on 2026-10-23. Sources are in
`platform-notes.md`. Re-check before shipping a robots.txt change.
## User-agent reference
| Token | Operator | Purpose | Blocking it means | Honors robots.txt |
|---|---|---|---|---|
| `Googlebot` | Google | Search crawling, including AI Overviews and AI Mode | Out of Google Search and its AI features | Yes |
| `Google-Extended` | Google | Product token for Gemini training and Gemini Apps / Vertex AI grounding | No Gemini training or grounding use; Search unaffected | Yes (token, no separate crawler) |
| `OAI-SearchBot` | OpenAI | ChatGPT search index | Not shown in ChatGPT search answers | Yes |
| `GPTBot` | OpenAI | Foundation-model training | Excluded from training; ChatGPT search unaffected | Yes |
| `ChatGPT-User` | OpenAI | User-initiated fetches | Rules may not apply | Not reliably |
| `ClaudeBot` | Anthropic | Training data collection | Future content excluded from training | Yes |
| `Claude-SearchBot` | Anthropic | Search indexing for Claude | Reduced visibility in Claude search answers | Yes |
| `Claude-User` | Anthropic | Fetches for a user's question | Claude cannot retrieve the page for users | Yes |
| `PerplexityBot` | Perplexity | Search index and links; not training | Not surfaced in Perplexity results | Yes |
| `Perplexity-User` | Perplexity | User-initiated fetches | Generally ignores robots.txt | No |
| `Bingbot` | Microsoft | Bing index, which grounds Copilot | Out of Bing and Copilot citations | Yes |
| `CCBot` | Common Crawl | Open web corpus used by many model builders | Excluded from Common Crawl | Yes |
`anthropic-ai` appears in older guides. Anthropic's current article names only
the three Claude agents above; an extra group for it is harmless but optional.
## Default Suede configuration for a brand that wants citations
Allow retrieval, decide training separately. Present the training lines as
the user's licensing decision, not a recommendation either way.
```text
# Search and answer retrieval: allow
User-agent: Googlebot
User-agent: Bingbot
User-agent: OAI-SearchBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
Allow: /
# Model training: the owner's call (shown here opted out)
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: CCBot
Disallow: /
User-agent: *
Allow: /
Disallow: /admin/
Sitemap: https://example.com/sitemap.xml
```
A named group replaces the `*` group for that bot, so repeat any private-path
`Disallow` lines inside named groups if they must apply.
## Checks robots.txt cannot answer
- CDN, WAF, or bot-management rules returning 403 or challenges to these
agents. Check firewall logs or test with the operator's published IP ranges.
- `noindex`, `nosnippet`, `max-snippet:0`, or `data-nosnippet` on key content.
- Content that only renders after client-side JavaScript. Several AI fetchers
do not execute JavaScript; compare raw HTML with the rendered DOM.
- Login walls, cookie walls, and geo-blocks on the pages you want cited.
## Verification steps
1. Fetch `/robots.txt` (and each relevant subdomain's) and record status.
2. Classify each token above as allowed, blocked, or unverified.
3. Grep server or CDN logs for each user agent over 30 days; confirm 200s on
priority pages. Verify IPs against the operator's list before trusting a UA
string.
4. Re-check 24 to 48 hours after any change.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |