{"id":980,"name":"Cracked","description":"Tool router for AI agents: discover, inspect and run 13,713 endpoints across 1,225 providers and 80,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 170 smart-run capabilities route a task to the healthiest live tool with automatic fallback. Agents can register their own workspace at POST https://cracked.ai/v1/agents/register ($1 trial credit, no human needed) and earn $5 of credit for every workspace that signs up through their referral link (GET https://cracked.ai/v1/referrals).","card_url":"https://cracked.ai/.well-known/agent-card.json","endpoint":"https://cracked.ai/mcp","protocol_version":"0.3.0","first_seen":"2026-10-07T09:26:46.342007+00:00","last_verified":"2026-10-07T09:26:46.342007+00:00","card":{"url":"https://cracked.ai/mcp","name":"Cracked","skills":[{"id":"llm-chat","name":"LLM completion","tags":["llm","chat","completion","gpt","claude","gemini","generate text","prompt","model"],"examples":["MCP: llm_chat({\"prompt\":\"A lighthouse at dawn, watercolor\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"llm-chat\",\"input\":{\"prompt\":\"A lighthouse at dawn, watercolor\"}}"],"inputModes":["application/json"],"description":"Generate text with a frontier or open model. Cheapest live model first. 873 measured runs in the last 30 days across 9 candidate tools. Input fields: prompt, system, max_tokens, json.","outputModes":["application/json"]},{"id":"keyword-extract","name":"Extract keywords","tags":["keywords","extract","key phrases","topics","tags","nlp","seo"],"examples":["MCP: keyword_extract({\"text\":\"Tirzepatide is a dual GIP and GLP-1 receptor agonist approved for type 2 diabetes and chronic weight management. Clinical trials showed average weight loss above 15 percent at the highest dose.\",\"limit\":8})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"keyword-extract\",\"input\":{\"text\":\"Tirzepatide is a dual GIP and GLP-1 receptor agonist approved for type 2 diabetes and chronic weight management. Clinical trials showed average weight loss above 15 percent at the highest dose.\",\"limit\":8}}"],"inputModes":["application/json"],"description":"Most important keywords and key phrases in a text, ranked (JSON array). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text, limit.","outputModes":["application/json"]},{"id":"math-solve","name":"Solve a math problem","tags":["math","solve","equation","calculate","algebra","calculus","wolfram"],"examples":["MCP: math_solve({\"problem\":\"Solve 3x^2 - 12x + 9 = 0\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"math-solve\",\"input\":{\"problem\":\"Solve 3x^2 - 12x + 9 = 0\"}}"],"inputModes":["application/json"],"description":"Step-by-step solution and final answer for a math problem (JSON). 700 measured runs in the last 30 days across 6 candidate tools. Input fields: problem.","outputModes":["application/json"]},{"id":"moderation","name":"Content moderation","tags":["moderation","safety","toxicity","flag","content policy","abuse","spam"],"examples":["MCP: moderation({\"text\":\"Buy cheap followers now!!! Click here http://spam.example\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"moderation\",\"input\":{\"text\":\"Buy cheap followers now!!! Click here http://spam.example\"}}"],"inputModes":["application/json"],"description":"Flag text for harassment, hate, sexual content, violence, self-harm and spam, with per-category scores (JSON). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","outputModes":["application/json"]},{"id":"sentiment","name":"Sentiment analysis","tags":["sentiment","classify","positive","negative","reviews","nlp","opinion"],"examples":["MCP: sentiment({\"text\":\"The support team was fast and the product works great, but shipping took two weeks.\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"sentiment\",\"input\":{\"text\":\"The support team was fast and the product works great, but shipping took two weeks.\"}}"],"inputModes":["application/json"],"description":"Classify the sentiment of a text as positive, neutral or negative with a score and short rationale (JSON). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","outputModes":["application/json"]},{"id":"summarize-text","name":"Summarize text","tags":["summarize","summary","tldr","condense","text","abstract"],"examples":["MCP: summarize_text({\"text\":\"Peptides are short chains of amino acids linked by peptide bonds. They are distinguished from proteins on the basis of size, typically containing fewer than fifty amino acids. Many peptides act as hormones or signalling molecules, and synthetic peptides are studied as drugs for metabolic disease, recovery and skin health.\",\"sentences\":2})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"summarize-text\",\"input\":{\"text\":\"Peptides are short chains of amino acids linked by peptide bonds. They are distinguished from proteins on the basis of size, typically containing fewer than fifty amino acids. Many peptides act as hormones or signalling molecules, and synthetic peptides are studied as drugs for metabolic disease, recovery and skin health.\",\"sentences\":2}}"],"inputModes":["application/json"],"description":"Concise summary of a passage of text, with a configurable length. 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text, sentences.","outputModes":["application/json"]},{"id":"translate-detect","name":"Detect language","tags":["language","detect","identify","translate","locale","iso code"],"examples":["MCP: translate_detect({\"text\":\"Bonjour tout le monde, comment allez-vous aujourd'hui ?\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"translate-detect\",\"input\":{\"text\":\"Bonjour tout le monde, comment allez-vous aujourd'hui ?\"}}"],"inputModes":["application/json"],"description":"Identify the language of a text. Returns JSON with language name, ISO code and confidence. 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","outputModes":["application/json"]},{"id":"unit-convert","name":"Unit conversion","tags":["units","convert","conversion","metric","imperial","temperature","measurement"],"examples":["MCP: unit_convert({\"value\":72,\"from\":\"fahrenheit\",\"to\":\"celsius\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"unit-convert\",\"input\":{\"value\":72,\"from\":\"fahrenheit\",\"to\":\"celsius\"}}"],"inputModes":["application/json"],"description":"Convert a value between units (length, mass, temperature, volume, speed, data, energy) with the result as JSON. 700 measured runs in the last 30 days across 6 candidate tools. Input fields: value, from, to.","outputModes":["application/json"]},{"id":"translate","name":"Translate text","tags":["translate","translation","language","localize"],"examples":["MCP: translate({\"text\":\"Hello world\",\"to\":\"es\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"translate\",\"input\":{\"text\":\"Hello world\",\"to\":\"es\"}}"],"inputModes":["application/json"],"description":"Translate text between languages. 469 measured runs in the last 30 days across 4 candidate tools. Input fields: text, to, from.","outputModes":["application/json"]},{"id":"web-scrape","name":"Scrape page to text","tags":["scrape","fetch","read","url","page","markdown","extract","crawl"],"examples":["MCP: web_scrape({\"url\":\"https://example.com\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"web-scrape\",\"input\":{\"url\":\"https://example.com\"}}"],"inputModes":["application/json"],"description":"Fetch one URL and return its readable content (text or markdown) plus title and metadata. 334 measured runs in the last 30 days across 5 candidate tools. Input fields: url, max_chars.","outputModes":["application/json"]},{"id":"company-enrich","name":"Company enrichment","tags":["company","enrich","enrichment","firmographics","domain","b2b","organization","waterfall"],"examples":["MCP: company_enrich({\"domain\":\"anthropic.com\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"company-enrich\",\"input\":{\"domain\":\"anthropic.com\"}}"],"inputModes":["application/json"],"description":"Firmographics for a company by website domain: name, industry, size, location, description, socials. Waterfall: providers are tried cheapest-first, a provider with no record for the domain is a free miss, only the provider that answers is billed. 220 measured runs in the last 30 days across 5 candidate tools. Input fields: domain, max_cost_usd, prefer, exclude, waterfall.","outputModes":["application/json"]},{"id":"pypi-package","name":"PyPI package","tags":["pypi","python","package","pip","dependency","version"],"examples":["MCP: pypi_package({\"name\":\"requests\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"pypi-package\",\"input\":{\"name\":\"requests\"}}"],"inputModes":["application/json"],"description":"PyPI package metadata: latest version, summary, license, requires-python, project URLs, release list. 212 measured runs in the last 30 days across 2 candidate tools. Input fields: name.","outputModes":["application/json"]},{"id":"weather-forecast","name":"Weather forecast","tags":["weather","forecast","temperature","rain","conditions"],"examples":["MCP: weather_forecast({\"latitude\":30.2672,\"longitude\":-97.7431,\"days\":3})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"weather-forecast\",\"input\":{\"latitude\":30.2672,\"longitude\":-97.7431,\"days\":3}}"],"inputModes":["application/json"],"description":"Current conditions plus daily forecast for coordinates. Use geocode first for a city name. 200 measured runs in the last 30 days across 1 candidate tools. Input fields: latitude, longitude, days, units.","outputModes":["application/json"]},{"id":"github-repo","name":"GitHub repository","tags":["github","repo","repository","stars","open source","code"],"examples":["MCP: github_repo({\"repo\":\"vercel/next.js\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"github-repo\",\"input\":{\"repo\":\"vercel/next.js\"}}"],"inputModes":["application/json"],"description":"Repository metadata: description, stars, forks, language, license, default branch, topics. 200 measured runs in the last 30 days across 2 candidate tools. Input fields: repo.","outputModes":["application/json"]},{"id":"shopify-store-products","name":"Shopify store products","tags":["shopify","store","products","catalog","prices","ecommerce","competitor"],"examples":["MCP: shopify_store_products({\"store\":\"allbirds.com\",\"limit\":10})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"shopify-store-products\",\"input\":{\"store\":\"allbirds.com\",\"limit\":10}}"],"inputModes":["application/json"],"description":"Product catalog of any Shopify storefront by domain: title, variants, prices, images, availability. 200 measured runs in the last 30 days across 3 candidate tools. Input fields: store, limit.","outputModes":["application/json"]},{"id":"pdf-extract","name":"PDF text extraction","tags":["pdf","extract","text","document","parse","read"],"examples":["MCP: pdf_extract({\"url\":\"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"pdf-extract\",\"input\":{\"url\":\"https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf\"}}"],"inputModes":["application/json"],"description":"Extract the text (markdown where possible) from a hosted PDF. 133 measured runs in the last 30 days across 5 candidate tools. Input fields: url.","outputModes":["application/json"]},{"id":"web-search","name":"Web search","tags":["search","google","serp","web","results","internet"],"examples":["MCP: web_search({\"query\":\"peptide therapy\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"web-search\",\"input\":{\"query\":\"peptide therapy\"}}"],"inputModes":["application/json"],"description":"Search the web and get ranked results with titles, URLs and snippets. 111 measured runs in the last 30 days across 7 candidate tools. Input fields: query, limit.","outputModes":["application/json"]},{"id":"docs-search","name":"Documentation search","tags":["docs","documentation","developer","api reference","search","readme"],"examples":["MCP: docs_search({\"query\":\"how to stream responses\",\"site\":\"docs.anthropic.com\",\"limit\":5})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"docs-search\",\"input\":{\"query\":\"how to stream responses\",\"site\":\"docs.anthropic.com\",\"limit\":5}}"],"inputModes":["application/json"],"description":"Search developer documentation or one docs site for a question and get the most relevant pages with content. 92 measured runs in the last 30 days across 5 candidate tools. Input fields: query, site, limit.","outputModes":["application/json"]},{"id":"voice-clone","name":"Voice clone speech","tags":["voice","clone","tts","speech","reference audio","text to speech"],"examples":["MCP: voice_clone({\"text\":\"Hello from Cracked, this is a cloned voice test.\",\"audio_url\":\"https://download.samplelib.com/mp3/sample-9s.mp3\"})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"voice-clone\",\"input\":{\"text\":\"Hello from Cracked, this is a cloned voice test.\",\"audio_url\":\"https://download.samplelib.com/mp3/sample-9s.mp3\"}}"],"inputModes":["application/json"],"description":"Speak text in the voice of a short reference audio clip (zero-shot voice cloning). 63 measured runs in the last 30 days across 3 candidate tools. Input fields: text, audio_url.","outputModes":["application/json"]},{"id":"google-shopping","name":"Google Shopping","tags":["google shopping","shopping","prices","products","offers","price comparison"],"examples":["MCP: google_shopping({\"query\":\"creatine monohydrate\",\"limit\":10})","HTTP: POST https://cracked.ai/v1/run {\"capability\":\"google-shopping\",\"input\":{\"query\":\"creatine monohydrate\",\"limit\":10}}"],"inputModes":["application/json"],"description":"Product offers for a query across merchants: title, price, seller, rating, product URL. 47 measured runs in the last 30 days across 2 candidate tools. Input fields: query, limit.","outputModes":["application/json"]},{"id":"agent-profile","name":"Agent profile","tags":["profile","routing","budget","preferences"],"examples":["MCP: set_profile({\"preferred_providers\":[\"hunter\"],\"default_max_cost_usd\":0.5})","HTTP: PATCH https://cracked.ai/v1/profile {\"preferred_providers\":[\"hunter\"],\"blocked_providers\":[\"crustdata\"],\"default_max_latency_ms\":8000}","HTTP: GET https://cracked.ai/v1/profile"],"inputModes":["application/json"],"description":"Per-key routing defaults: preferred and blocked providers honoured by every smart run and waterfall, default max cost per run and default max latency, free-form tags and notes. Explicit prefer, exclude, max_cost_usd and maxLatencyMs on a request always win.","outputModes":["application/json"]},{"id":"agent-memory","name":"Agent memory","tags":["memory","state","key-value"],"examples":["MCP: memory_set({\"name\":\"last-cursor\",\"value\":{\"page\":3}})","MCP: memory_get({\"name\":\"last-cursor\"})","HTTP: PUT https://cracked.ai/v1/memory/last-cursor {\"value\":{\"page\":3}}","HTTP: GET https://cracked.ai/v1/memory"],"inputModes":["application/json"],"description":"Key-scoped store and recall: one JSON value per name (64 KB), 200 names per key, listed with sizes. For cursors, run ids and preferences between sessions; no search or embeddings.","outputModes":["application/json"]},{"id":"recipes","name":"Recipes","tags":["recipes","templates","automation"],"examples":["MCP: save_recipe({\"name\":\"austin-weather\",\"capability\":\"weather-forecast\",\"input_template\":{\"latitude\":30.27,\"longitude\":-97.74},\"options\":{\"cache\":3600}})","MCP: run_recipe({\"recipe\":\"austin-weather\"})","HTTP: POST https://cracked.ai/v1/recipes/austin-weather/run {\"input\":{}}"],"inputModes":["application/json"],"description":"Named input templates over a capability or a tool with saved run options (prefer, exclude, max_cost_usd, cache, tag). Running a recipe merges the call's input over the template and bills like any run; the recipe counts its runs.","outputModes":["application/json"]}],"iconUrl":"https://cracked.ai/brand/icon.png","related":{"mcp":"https://cracked.ai/.well-known/mcp.json","llms":"https://cracked.ai/llms.txt","x402":"https://cracked.ai/.well-known/x402","memory":"https://cracked.ai/v1/memory","skills":"https://cracked.ai/.well-known/skills/index.json","openapi":"https://cracked.ai/openapi.json","profile":"https://cracked.ai/v1/profile","recipes":"https://cracked.ai/v1/recipes","bounties":"https://cracked.ai/v1/bounties/program","receipts":"https://cracked.ai/.well-known/cracked-receipts.json","register":"POST https://cracked.ai/v1/agents/register","profileDocs":"https://cracked.ai/docs/agents#profile","capabilities":"https://cracked.ai/v1/capabilities","docsMarkdown":"https://cracked.ai/docs.md"},"version":"0.9.0","provider":{"url":"https://cracked.ai","organization":"Cracked"},"receipts":{"alg":"EdDSA","docs":"https://cracked.ai/docs/receipts","jwks":"https://cracked.ai/.well-known/cracked-receipts.json","keys":["40deec7d36c90767"],"note":"Every terminal run response carries receipt {id, url, signature}: an Ed25519-signed document with the tool, workspace and key ids, hashes of the input and output (never the data), status, latency, price and payment ids. Private until the owner shares it.","page":"https://cracked.ai/r/{id}","share":"POST https://cracked.ai/v1/receipts/{id}/share","receipt":"https://cracked.ai/v1/receipts/{id}","version":"cracked-receipt/1","verifyTool":"verify_receipt"},"security":[{"bearer":[]},{"oauth2":["tools:discover","tools:run","wallet:read","openid","email"]}],"interfaces":[{"url":"https://cracked.ai/mcp","type":"mcp","transport":"streamable-http"},{"url":"https://cracked.ai/mcp/public","auth":"none","type":"mcp","transport":"streamable-http"},{"url":"https://cracked.ai/v1","docs":"https://cracked.ai/docs/api","type":"http"},{"url":"https://cracked.ai/SKILL.md","type":"skill"}],"description":"Tool router for AI agents: discover, inspect and run 13,713 endpoints across 1,225 providers and 80,000+ Apify actors from one balance, with a measured success rate, latency and per-call price on every tool. 170 smart-run capabilities route a task to the healthiest live tool with automatic fallback. Agents can register their own workspace at POST https://cracked.ai/v1/agents/register ($1 trial credit, no human needed) and earn $5 of credit for every workspace that signs up through their referral link (GET https://cracked.ai/v1/referrals).","capabilities":{"streaming":true,"pushNotifications":false,"stateTransitionHistory":false},"authentication":{"schemes":["Bearer","OAuth2"],"credentials":"https://cracked.ai/.well-known/oauth-authorization-server"},"protocolVersion":"0.3.0","securitySchemes":{"bearer":{"type":"http","scheme":"bearer","description":"ck_live_ API key from https://cracked.ai/app/keys or POST https://cracked.ai/v1/agents/register"},"oauth2":{"type":"oauth2","flows":{"authorizationCode":{"scopes":{"email":"email","openid":"openid","tools:run":"tools:run","wallet:read":"wallet:read","offline_access":"offline_access","tools:discover":"tools:discover"},"tokenUrl":"https://cracked.ai/oauth/token","refreshUrl":"https://cracked.ai/oauth/token","authorizationUrl":"https://cracked.ai/oauth/authorize"}},"description":"OAuth 2.1 with PKCE; metadata at the oauth2MetadataUrl","oauth2MetadataUrl":"https://cracked.ai/.well-known/oauth-authorization-server"}},"documentationUrl":"https://cracked.ai/docs","defaultInputModes":["application/json","text/plain"],"defaultOutputModes":["application/json"],"additionalInterfaces":[{"url":"https://cracked.ai/mcp","auth":"oauth2 or bearer","protocol":"mcp","transport":"streamable-http","description":"Authenticated MCP server: every skill above as a typed tool plus discover, inspect, run and balance tools"},{"url":"https://cracked.ai/mcp/public","auth":"none","protocol":"mcp","transport":"streamable-http","description":"Unauthenticated MCP server: discover_tools, inspect_tool, register_agent, recruit_agent, bounty_program, verify_receipt"},{"url":"https://cracked.ai/v1","docs":"https://cracked.ai/docs/api","openapi":"https://cracked.ai/openapi.json","protocol":"rest","transport":"http"},{"url":"https://cracked.ai/SKILL.md","protocol":"skill","transport":"text","description":"Agent skill file: paste one line and an agent learns the discover, inspect, run loop"}]},"signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-07T09:26:59.687284+00:00","source_name":"Global A2A Registry","source_url":"https://api.a2a-registry.org/public/agents","last_check":{"checked_at":"2026-10-07T09:26:46.342007+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"skills":[{"skill_id":"agent-memory","name":"Agent memory","description":"Key-scoped store and recall: one JSON value per name (64 KB), 200 names per key, listed with sizes. For cursors, run ids and preferences between sessions; no search or embeddings.","tags":["memory","state","key-value"]},{"skill_id":"agent-profile","name":"Agent profile","description":"Per-key routing defaults: preferred and blocked providers honoured by every smart run and waterfall, default max cost per run and default max latency, free-form tags and notes. Explicit prefer, exclude, max_cost_usd and maxLatencyMs on a request always win.","tags":["profile","routing","budget","preferences"]},{"skill_id":"company-enrich","name":"Company enrichment","description":"Firmographics for a company by website domain: name, industry, size, location, description, socials. Waterfall: providers are tried cheapest-first, a provider with no record for the domain is a free miss, only the provider that answers is billed. 220 measured runs in the last 30 days across 5 candidate tools. Input fields: domain, max_cost_usd, prefer, exclude, waterfall.","tags":["company","enrich","enrichment","firmographics","domain","b2b","organization","waterfall"]},{"skill_id":"moderation","name":"Content moderation","description":"Flag text for harassment, hate, sexual content, violence, self-harm and spam, with per-category scores (JSON). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","tags":["moderation","safety","toxicity","flag","content policy","abuse","spam"]},{"skill_id":"translate-detect","name":"Detect language","description":"Identify the language of a text. Returns JSON with language name, ISO code and confidence. 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","tags":["language","detect","identify","translate","locale","iso code"]},{"skill_id":"docs-search","name":"Documentation search","description":"Search developer documentation or one docs site for a question and get the most relevant pages with content. 92 measured runs in the last 30 days across 5 candidate tools. Input fields: query, site, limit.","tags":["docs","documentation","developer","api reference","search","readme"]},{"skill_id":"keyword-extract","name":"Extract keywords","description":"Most important keywords and key phrases in a text, ranked (JSON array). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text, limit.","tags":["keywords","extract","key phrases","topics","tags","nlp","seo"]},{"skill_id":"github-repo","name":"GitHub repository","description":"Repository metadata: description, stars, forks, language, license, default branch, topics. 200 measured runs in the last 30 days across 2 candidate tools. Input fields: repo.","tags":["github","repo","repository","stars","open source","code"]},{"skill_id":"google-shopping","name":"Google Shopping","description":"Product offers for a query across merchants: title, price, seller, rating, product URL. 47 measured runs in the last 30 days across 2 candidate tools. Input fields: query, limit.","tags":["google shopping","shopping","prices","products","offers","price comparison"]},{"skill_id":"llm-chat","name":"LLM completion","description":"Generate text with a frontier or open model. Cheapest live model first. 873 measured runs in the last 30 days across 9 candidate tools. Input fields: prompt, system, max_tokens, json.","tags":["llm","chat","completion","gpt","claude","gemini","generate text","prompt","model"]},{"skill_id":"pdf-extract","name":"PDF text extraction","description":"Extract the text (markdown where possible) from a hosted PDF. 133 measured runs in the last 30 days across 5 candidate tools. Input fields: url.","tags":["pdf","extract","text","document","parse","read"]},{"skill_id":"pypi-package","name":"PyPI package","description":"PyPI package metadata: latest version, summary, license, requires-python, project URLs, release list. 212 measured runs in the last 30 days across 2 candidate tools. Input fields: name.","tags":["pypi","python","package","pip","dependency","version"]},{"skill_id":"recipes","name":"Recipes","description":"Named input templates over a capability or a tool with saved run options (prefer, exclude, max_cost_usd, cache, tag). Running a recipe merges the call's input over the template and bills like any run; the recipe counts its runs.","tags":["recipes","templates","automation"]},{"skill_id":"web-scrape","name":"Scrape page to text","description":"Fetch one URL and return its readable content (text or markdown) plus title and metadata. 334 measured runs in the last 30 days across 5 candidate tools. Input fields: url, max_chars.","tags":["scrape","fetch","read","url","page","markdown","extract","crawl"]},{"skill_id":"sentiment","name":"Sentiment analysis","description":"Classify the sentiment of a text as positive, neutral or negative with a score and short rationale (JSON). 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text.","tags":["sentiment","classify","positive","negative","reviews","nlp","opinion"]},{"skill_id":"shopify-store-products","name":"Shopify store products","description":"Product catalog of any Shopify storefront by domain: title, variants, prices, images, availability. 200 measured runs in the last 30 days across 3 candidate tools. Input fields: store, limit.","tags":["shopify","store","products","catalog","prices","ecommerce","competitor"]},{"skill_id":"math-solve","name":"Solve a math problem","description":"Step-by-step solution and final answer for a math problem (JSON). 700 measured runs in the last 30 days across 6 candidate tools. Input fields: problem.","tags":["math","solve","equation","calculate","algebra","calculus","wolfram"]},{"skill_id":"summarize-text","name":"Summarize text","description":"Concise summary of a passage of text, with a configurable length. 700 measured runs in the last 30 days across 5 candidate tools. Input fields: text, sentences.","tags":["summarize","summary","tldr","condense","text","abstract"]},{"skill_id":"translate","name":"Translate text","description":"Translate text between languages. 469 measured runs in the last 30 days across 4 candidate tools. Input fields: text, to, from.","tags":["translate","translation","language","localize"]},{"skill_id":"unit-convert","name":"Unit conversion","description":"Convert a value between units (length, mass, temperature, volume, speed, data, energy) with the result as JSON. 700 measured runs in the last 30 days across 6 candidate tools. Input fields: value, from, to.","tags":["units","convert","conversion","metric","imperial","temperature","measurement"]},{"skill_id":"voice-clone","name":"Voice clone speech","description":"Speak text in the voice of a short reference audio clip (zero-shot voice cloning). 63 measured runs in the last 30 days across 3 candidate tools. Input fields: text, audio_url.","tags":["voice","clone","tts","speech","reference audio","text to speech"]},{"skill_id":"weather-forecast","name":"Weather forecast","description":"Current conditions plus daily forecast for coordinates. Use geocode first for a city name. 200 measured runs in the last 30 days across 1 candidate tools. Input fields: latitude, longitude, days, units.","tags":["weather","forecast","temperature","rain","conditions"]},{"skill_id":"web-search","name":"Web search","description":"Search the web and get ranked results with titles, URLs and snippets. 111 measured runs in the last 30 days across 7 candidate tools. Input fields: query, limit.","tags":["search","google","serp","web","results","internet"]}],"relationships":[]}