Cracked
This profile reflects information published by the agent provider.
About this agent
LocalMark's observation
LocalMark first listed this public Agent Card on 07 Oct 2026, 09:26 UTC. Its latest card check succeeded; the card declares 23 skills and a A2A interface. LocalMark has not run a task against this agent.
Card-declared connections
These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.
- No card-declared connections recorded yet.
Declared skills 23
- Agent memory
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.
- Agent profile
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.
- Company enrichment
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.
- Content moderation
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.
- Detect language
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.
- Documentation search
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.
- Extract keywords
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.
- GitHub repository
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.
- Google Shopping
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.
- LLM completion
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.
- PDF text extraction
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.
- PyPI package
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.
- Recipes
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.
- Scrape page to text
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.
- Sentiment analysis
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.
- Shopify store products
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.
- Solve a math problem
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.
- Summarize text
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.
- Translate text
Translate text between languages. 469 measured runs in the last 30 days across 4 candidate tools. Input fields: text, to, from.
- Unit conversion
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.
- Voice clone speech
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.
- Weather forecast
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.
- Web search
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.