← ClaudeAtlas

ai-trackerlisted

Track whether AI assistants mention and cite a brand or domain for a fixed set of buyer questions, using the user's own OpenAI, Anthropic and Perplexity API keys with web search on. Builds the prompt set (discovery, problem, price, comparison, alternatives, trust, brand), confirms the cost before any call, logs every answer to .sitetiller/track/*.jsonl, and compares weeks with margins of error. Use when the user asks 'does ChatGPT recommend us', 'AI share of voice', 'track our AI visibility', 'who do AI answers cite for our topic', 'are we mentioned by Perplexity/Claude', or 'monitor AI answers weekly'. Results are a sample from APIs, not a ranking and not the consumer apps.
sitetiller/ai-visibility-skills · ★ 0 · AI & Automation · score 75
Install: claude install-skill sitetiller/ai-visibility-skills
# AI answer tracker Goal: a small, repeatable sample of what AI assistants say for the questions buyers ask, so the user can see mentions, citations, competitors and cited sources move over weeks. It is a sample with a margin of error, not a rank. ## Inputs - The brand names to look for (`--brand "Acme,acme.com"`), the domain (`--domain acme.com`), optional competitors (`--competitors "Asana,Trello"`). - A prompts file, one prompt per line (`#` lines and blank lines are ignored). Build it from the seven types in `references/prompt-types.md`. - Keys in the environment, never in chat: `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `PERPLEXITY_API_KEY`. An engine without a key is skipped and listed under `skipped`. ## Cost: confirm before every run Every call is billed to the user's API accounts. Without `--yes` the CLI only prints the number of calls and stops: ```bash npx sitetiller track --prompts prompts.txt --brand "Acme,acme.com" --domain acme.com --competitors "Asana,Trello" ``` Calls = prompts x engines x `--runs`. Example: 40 prompts x 3 engines x 3 runs = 360 calls. Tell the user that number and the provider price pages before asking for a go-ahead: - Anthropic: web search is $10 per 1,000 searches plus token costs; the tracker allows up to 5 searches per answer (`max_uses` 5), so one answer can cost up to 5 searches plus tokens. - OpenAI: "Search actions incur a tool call cost" (see OpenAI's pricing page for the current figure; not stated on the web search guide). - Perple