{"id":11963,"name":"Busker","description":"Content-to-context toolkit for AI agents: stateless per-call paid transforms (HTML/PDF/OCR to markdown, structured extraction, RAG chunking, embeddings, reranking, URL fetch, format conversion, QR, image ops, object detection). Every call is paid via x402 (USDC on Base); failed requests are never charged.","card_url":"https://workbot1.oddsys.org/.well-known/agent-card.json","endpoint":"https://workbot1.oddsys.org/","protocol_version":"0.2.6","first_seen":"2026-10-10T13:34:39.771881+00:00","last_verified":"2026-10-10T13:34:39.771881+00:00","card":{"url":"https://workbot1.oddsys.org/","name":"Busker","skills":[{"id":"transform","name":"RemoteSight HTML→Markdown","tags":["html","markdown","extraction","context-compression","scraping"],"examples":["POST https://workbot1.oddsys.org/transform"],"description":"Convert raw HTML into clean markdown. Typically cuts page tokens by 80-85% before they hit an LLM context window."},{"id":"pdf","name":"RemoteSight PDF→Markdown","tags":["pdf","markdown","extraction","document","context-compression"],"examples":["POST https://workbot1.oddsys.org/pdf"],"description":"Extract clean markdown text from a PDF (text-layer PDFs; no OCR). Turns a document an agent can't cheaply read into compact tokens."},{"id":"ocr","name":"RemoteSight PDF OCR","tags":["ocr","pdf","scanned","extraction","document","tesseract"],"examples":["POST https://workbot1.oddsys.org/ocr"],"description":"OCR a scanned PDF into clean text (Tesseract, English, machine-printed documents). Up to 25 pages per call. PDFs that turn out to have a text layer are extracted the fast way at the same price."},{"id":"ocr-deep","name":"Busker Deep OCR","tags":["ocr","pdf","scanned","extraction","document","tesseract","batch","long-document"],"examples":["POST https://workbot1.oddsys.org/ocr-deep"],"description":"High-page-count OCR: scanned PDF into clean text (Tesseract, English, machine-printed documents), up to 100 pages per call — four times the /ocr cap. Runs under a 240s wall-clock budget; slower documents return the completed pages with truncatedReason \"time-budget\". Text-layer PDFs are extracted the fast way at the same price."},{"id":"extract","name":"RemoteSight Structured Extract","tags":["html","extraction","metadata","json-ld","schema.org","scraping"],"examples":["POST https://workbot1.oddsys.org/extract"],"description":"Extract structured JSON from a web page: title, byline, publish date, Open Graph/meta tags, embedded JSON-LD (schema.org), links, and images. Deterministic, no LLM."},{"id":"chunk","name":"RemoteSight RAG Chunker","tags":["chunking","rag","text","embeddings","context"],"examples":["POST https://workbot1.oddsys.org/chunk"],"description":"Split a document into token-bounded chunks at natural boundaries (paragraphs/sentences), with optional overlap. Ready-to-embed pieces for RAG, no tokens spent on the splitting logic."},{"id":"convert","name":"RemoteSight Format Convert","tags":["convert","json","yaml","csv","xml","data"],"examples":["POST https://workbot1.oddsys.org/convert"],"description":"Convert data between JSON, YAML, CSV, and XML. Deterministic format juggling done off-context, with edge cases handled."},{"id":"qr","name":"Busker QR Generator","tags":["qr","qrcode","image","png","svg","generation"],"examples":["POST https://workbot1.oddsys.org/qr"],"description":"Generate a QR code from text as PNG (base64) or SVG. Custom module size, quiet-zone margin, and hex colours. Deterministic, capacity-capped at 2953 bytes. Set delivery to \"url\" to receive a short-lived download link instead of inline data."},{"id":"image","name":"Busker Image Tools","tags":["image","resize","crop","greyscale","convert","png","jpeg","webp"],"examples":["POST https://workbot1.oddsys.org/image"],"description":"Modify an image in one call: crop, resize, convert to greyscale, and re-encode (PNG/JPEG/WebP) — applied in that order, any combination. Deterministic, no upscaling surprises. Set delivery to \"url\" to receive a short-lived download link instead of inline base64."},{"id":"detect","name":"Busker Object Detection","tags":["detection","vision","image","people","vehicles","pets","yolox","counting"],"examples":["POST https://workbot1.oddsys.org/detect"],"description":"Detect and locate objects in an image (YOLOX-nano, COCO classes): people, pets (dog/cat/horse), vehicles, and 70+ more. Returns per-class counts and pixel bounding boxes. Detection only — no identification. Best on clear, medium-to-large objects."},{"id":"embed","name":"Busker Embeddings","tags":["embeddings","vector","rag","semantic-search","minilm","nlp"],"examples":["POST https://workbot1.oddsys.org/embed"],"description":"Generate sentence embeddings (all-MiniLM-L6-v2, 384-dim, mean-pooled + L2-normalized) for up to 96 texts per call. Drop-in compatible with any all-MiniLM-L6-v2 index. Pairs with /chunk for a complete RAG pipeline."},{"id":"rerank","name":"Busker Reranker","tags":["rerank","reranking","rag","search","relevance","cross-encoder","retrieval"],"examples":["POST https://workbot1.oddsys.org/rerank"],"description":"Rerank candidate texts against a query with a cross-encoder (ms-marco-MiniLM-L-6-v2): joint query+document scoring, much sharper than cosine similarity over embeddings. Returns ranked indices with 0-1 relevance scores. Up to 64 texts per call. Pairs with /embed for a recall-then-precision RAG pipeline."},{"id":"fetch","name":"Busker Fetch & Clean","tags":["fetch","scraping","url","markdown","web","context-compression"],"examples":["POST https://workbot1.oddsys.org/fetch"],"description":"Fetch a public web page and return clean markdown (or structured JSON) — URL in, agent-ready content out, typically 80-85% fewer tokens than raw HTML. Handles redirects and compression."},{"id":"fx","name":"Busker FX Rates","tags":["fx","forex","exchange-rates","currency","usd","eur","finance","data"],"examples":["POST https://workbot1.oddsys.org/fx"],"description":"Live foreign-exchange reference rates (European Central Bank daily fixes, ~30 major currencies): any cross-rate from any base, optional amount conversion. Refreshed daily; response carries the rate date."},{"id":"phone","name":"Busker Phone Validator","tags":["phone","validation","e164","libphonenumber","normalization","data"],"examples":["POST https://workbot1.oddsys.org/phone"],"description":"Validate and normalize phone numbers (Google libphonenumber): validity, E.164/international/national formats, country, region, and line type (mobile/fixed/VoIP). Single number or batches up to 100."},{"id":"decode-tx","name":"Busker Tx Decoder","tags":["evm","base","calldata","decode","transaction","x402","usdc","receipt","chain"],"examples":["POST https://workbot1.oddsys.org/decode-tx"],"description":"Decode EVM calldata or a Base-mainnet transaction into human-readable form: function selector, matched signature, named args, plus ERC-20/USDC transfer events from the receipt — verify an x402 settlement receipt (tx hash in, payer/payee/amount out) in one call."},{"id":"screen","name":"Busker Sanctions Screen","tags":["sanctions","ofac","sdn","compliance","screening","kyc","risk","data"],"examples":["POST https://workbot1.oddsys.org/screen"],"description":"Fuzzy sanctions screening against the US OFAC SDN list (public-domain source, refreshed daily): name in, scored matches with programs and aliases out. Batches up to 50. Coverage is OFAC SDN only — stated in every response."},{"id":"verify-sig","name":"Busker Signature Verifier","tags":["signature","eip191","eip712","eip3009","x402","evm","verify","wallet","auth"],"examples":["POST https://workbot1.oddsys.org/verify-sig"],"description":"Verify EVM signatures offline: EIP-191 personal messages, EIP-712 typed data, and x402/EIP-3009 payment authorizations (paste a raw Payment-Signature header) — recovers the signing wallet, checks it against an expected address, and reports the authorization's amount, payee and validity window. No chain reads."},{"id":"iban","name":"Busker IBAN/BIC Validator","tags":["iban","bic","swift","banking","payments","validation","sepa","finance","data"],"examples":["POST https://workbot1.oddsys.org/iban"],"description":"Validate and decompose IBANs (checksum, country format, IBAN registry, SEPA membership; bank/branch/account parts) and BIC/SWIFT codes. Batches up to 100. Format validation only — does not prove an account exists."},{"id":"holidays","name":"Busker Holidays & Business Days","tags":["holidays","business-days","calendar","dates","scheduling","settlement","sla","data"],"examples":["POST https://workbot1.oddsys.org/holidays"],"description":"Public holidays for ~200 countries and their subdivisions, plus business-day arithmetic: is this date a holiday or business day, next business day, add N business days, count business days between dates. Configurable weekend and holiday types."},{"id":"tz","name":"Busker Time Zones","tags":["timezone","tz","iana","dst","scheduling","meeting","time","data"],"examples":["POST https://workbot1.oddsys.org/tz"],"description":"Time-zone conversion on the IANA database: convert a time between zones with offsets, abbreviations and DST flags, describe zones at an instant, or compute the shared business-hours window across several zones for meeting scheduling."},{"id":"validate","name":"Busker JSON Schema Validator","tags":["json-schema","validation","structured-output","schema","json","developer-tools"],"examples":["POST https://workbot1.oddsys.org/validate"],"description":"Validate JSON against a JSON Schema (draft-07, 2019-09, 2020-12, with string formats): every violation with path, keyword and message. One instance, a JSON string, or up to 100 instances against one schema."},{"id":"tokens","name":"Busker Token Counter","tags":["tokens","tiktoken","token-count","context-window","llm","budget","developer-tools"],"examples":["POST https://workbot1.oddsys.org/tokens"],"description":"Exact BPE token counts for OpenAI-family encodings (o200k_base for GPT-4o/4.1/5, cl100k_base for GPT-4/3.5/embeddings), single text or batches, with optional truncation to a token budget. Up to 512 KB per call."},{"id":"lang","name":"Busker Language ID","tags":["language","language-detection","nlp","iso639","text","routing","data"],"examples":["POST https://workbot1.oddsys.org/lang"],"description":"Language identification for 180+ languages (every language with ≥1M speakers): ISO 639-3 code, ISO 639-1 code and English name, with ranked candidates and a confidence margin. Single text or batches up to 100."},{"id":"suggest","name":"Busker Suggestion Box","tags":["feedback","feature-request","free"],"examples":["POST https://workbot1.oddsys.org/suggest"],"description":"FREE feature-request inbox: didn't find the capability you need? POST {\"want\": \"...\"} and steer which paid routes get built next."}],"version":"0.15.0","provider":{"url":"https://workbot1.oddsys.org","organization":"Busker"},"x-clients":{"mcp":{"note":"All skills as MCP tools; payment handled client-side via x402 with per-wallet serialisation.","install":"npx -y busker-mcp","package":"busker-mcp","registry":"https://www.npmjs.com/package/busker-mcp"}},"x-payments":{"network":"eip155:8453","manifest":"https://workbot1.oddsys.org/.well-known/x402","protocol":"x402","priceRange":"$0.001-$0.03 USDC per call"},"description":"Content-to-context toolkit for AI agents: stateless per-call paid transforms (HTML/PDF/OCR to markdown, structured extraction, RAG chunking, embeddings, reranking, URL fetch, format conversion, QR, image ops, object detection). Every call is paid via x402 (USDC on Base); failed requests are never charged.","capabilities":{"streaming":false,"pushNotifications":false,"stateTransitionHistory":false},"protocolVersion":"0.2.6","defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"preferredTransport":"HTTP+JSON"},"signature_status":"unsigned","signature_detail":"No card signature supplied","signature_key_url":null,"signature_checked_at":"2026-10-10T13:34:39.771881+00:00","domain_claimed_at":null,"domain_proof_checked_at":null,"source_name":"Agent Tools Catalog","source_url":"https://agent-tools.cloud","last_check":{"checked_at":"2026-10-10T13:34:39.771881+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"also_published_at":[],"history_urls":["https://workbot1.oddsys.org/.well-known/agent-card.json"],"skills":[{"skill_id":"ocr-deep","name":"Busker Deep OCR","description":"High-page-count OCR: scanned PDF into clean text (Tesseract, English, machine-printed documents), up to 100 pages per call — four times the /ocr cap. Runs under a 240s wall-clock budget; slower documents return the completed pages with truncatedReason \"time-budget\". Text-layer PDFs are extracted the fast way at the same price.","tags":["ocr","pdf","scanned","extraction","document","tesseract","batch","long-document"],"quality_warning":false},{"skill_id":"embed","name":"Busker Embeddings","description":"Generate sentence embeddings (all-MiniLM-L6-v2, 384-dim, mean-pooled + L2-normalized) for up to 96 texts per call. Drop-in compatible with any all-MiniLM-L6-v2 index. Pairs with /chunk for a complete RAG pipeline.","tags":["embeddings","vector","rag","semantic-search","minilm","nlp"],"quality_warning":false},{"skill_id":"fx","name":"Busker FX Rates","description":"Live foreign-exchange reference rates (European Central Bank daily fixes, ~30 major currencies): any cross-rate from any base, optional amount conversion. Refreshed daily; response carries the rate date.","tags":["fx","forex","exchange-rates","currency","usd","eur","finance","data"],"quality_warning":false},{"skill_id":"fetch","name":"Busker Fetch & Clean","description":"Fetch a public web page and return clean markdown (or structured JSON) — URL in, agent-ready content out, typically 80-85% fewer tokens than raw HTML. Handles redirects and compression.","tags":["fetch","scraping","url","markdown","web","context-compression"],"quality_warning":false},{"skill_id":"holidays","name":"Busker Holidays & Business Days","description":"Public holidays for ~200 countries and their subdivisions, plus business-day arithmetic: is this date a holiday or business day, next business day, add N business days, count business days between dates. Configurable weekend and holiday types.","tags":["holidays","business-days","calendar","dates","scheduling","settlement","sla","data"],"quality_warning":false},{"skill_id":"iban","name":"Busker IBAN/BIC Validator","description":"Validate and decompose IBANs (checksum, country format, IBAN registry, SEPA membership; bank/branch/account parts) and BIC/SWIFT codes. Batches up to 100. Format validation only — does not prove an account exists.","tags":["iban","bic","swift","banking","payments","validation","sepa","finance","data"],"quality_warning":false},{"skill_id":"image","name":"Busker Image Tools","description":"Modify an image in one call: crop, resize, convert to greyscale, and re-encode (PNG/JPEG/WebP) — applied in that order, any combination. Deterministic, no upscaling surprises. Set delivery to \"url\" to receive a short-lived download link instead of inline base64.","tags":["image","resize","crop","greyscale","convert","png","jpeg","webp"],"quality_warning":false},{"skill_id":"validate","name":"Busker JSON Schema Validator","description":"Validate JSON against a JSON Schema (draft-07, 2019-09, 2020-12, with string formats): every violation with path, keyword and message. One instance, a JSON string, or up to 100 instances against one schema.","tags":["json-schema","validation","structured-output","schema","json","developer-tools"],"quality_warning":false},{"skill_id":"lang","name":"Busker Language ID","description":"Language identification for 180+ languages (every language with ≥1M speakers): ISO 639-3 code, ISO 639-1 code and English name, with ranked candidates and a confidence margin. Single text or batches up to 100.","tags":["language","language-detection","nlp","iso639","text","routing","data"],"quality_warning":false},{"skill_id":"detect","name":"Busker Object Detection","description":"Detect and locate objects in an image (YOLOX-nano, COCO classes): people, pets (dog/cat/horse), vehicles, and 70+ more. Returns per-class counts and pixel bounding boxes. Detection only — no identification. Best on clear, medium-to-large objects.","tags":["detection","vision","image","people","vehicles","pets","yolox","counting"],"quality_warning":false},{"skill_id":"phone","name":"Busker Phone Validator","description":"Validate and normalize phone numbers (Google libphonenumber): validity, E.164/international/national formats, country, region, and line type (mobile/fixed/VoIP). Single number or batches up to 100.","tags":["phone","validation","e164","libphonenumber","normalization","data"],"quality_warning":false},{"skill_id":"qr","name":"Busker QR Generator","description":"Generate a QR code from text as PNG (base64) or SVG. Custom module size, quiet-zone margin, and hex colours. Deterministic, capacity-capped at 2953 bytes. Set delivery to \"url\" to receive a short-lived download link instead of inline data.","tags":["qr","qrcode","image","png","svg","generation"],"quality_warning":false},{"skill_id":"rerank","name":"Busker Reranker","description":"Rerank candidate texts against a query with a cross-encoder (ms-marco-MiniLM-L-6-v2): joint query+document scoring, much sharper than cosine similarity over embeddings. Returns ranked indices with 0-1 relevance scores. Up to 64 texts per call. Pairs with /embed for a recall-then-precision RAG pipeline.","tags":["rerank","reranking","rag","search","relevance","cross-encoder","retrieval"],"quality_warning":false},{"skill_id":"screen","name":"Busker Sanctions Screen","description":"Fuzzy sanctions screening against the US OFAC SDN list (public-domain source, refreshed daily): name in, scored matches with programs and aliases out. Batches up to 50. Coverage is OFAC SDN only — stated in every response.","tags":["sanctions","ofac","sdn","compliance","screening","kyc","risk","data"],"quality_warning":false},{"skill_id":"verify-sig","name":"Busker Signature Verifier","description":"Verify EVM signatures offline: EIP-191 personal messages, EIP-712 typed data, and x402/EIP-3009 payment authorizations (paste a raw Payment-Signature header) — recovers the signing wallet, checks it against an expected address, and reports the authorization's amount, payee and validity window. No chain reads.","tags":["signature","eip191","eip712","eip3009","x402","evm","verify","wallet","auth"],"quality_warning":false},{"skill_id":"suggest","name":"Busker Suggestion Box","description":"FREE feature-request inbox: didn't find the capability you need? POST {\"want\": \"...\"} and steer which paid routes get built next.","tags":["feedback","feature-request","free"],"quality_warning":false},{"skill_id":"tz","name":"Busker Time Zones","description":"Time-zone conversion on the IANA database: convert a time between zones with offsets, abbreviations and DST flags, describe zones at an instant, or compute the shared business-hours window across several zones for meeting scheduling.","tags":["timezone","tz","iana","dst","scheduling","meeting","time","data"],"quality_warning":false},{"skill_id":"tokens","name":"Busker Token Counter","description":"Exact BPE token counts for OpenAI-family encodings (o200k_base for GPT-4o/4.1/5, cl100k_base for GPT-4/3.5/embeddings), single text or batches, with optional truncation to a token budget. Up to 512 KB per call.","tags":["tokens","tiktoken","token-count","context-window","llm","budget","developer-tools"],"quality_warning":false},{"skill_id":"decode-tx","name":"Busker Tx Decoder","description":"Decode EVM calldata or a Base-mainnet transaction into human-readable form: function selector, matched signature, named args, plus ERC-20/USDC transfer events from the receipt — verify an x402 settlement receipt (tx hash in, payer/payee/amount out) in one call.","tags":["evm","base","calldata","decode","transaction","x402","usdc","receipt","chain"],"quality_warning":false},{"skill_id":"convert","name":"RemoteSight Format Convert","description":"Convert data between JSON, YAML, CSV, and XML. Deterministic format juggling done off-context, with edge cases handled.","tags":["convert","json","yaml","csv","xml","data"],"quality_warning":false},{"skill_id":"transform","name":"RemoteSight HTML→Markdown","description":"Convert raw HTML into clean markdown. Typically cuts page tokens by 80-85% before they hit an LLM context window.","tags":["html","markdown","extraction","context-compression","scraping"],"quality_warning":false},{"skill_id":"ocr","name":"RemoteSight PDF OCR","description":"OCR a scanned PDF into clean text (Tesseract, English, machine-printed documents). Up to 25 pages per call. PDFs that turn out to have a text layer are extracted the fast way at the same price.","tags":["ocr","pdf","scanned","extraction","document","tesseract"],"quality_warning":false},{"skill_id":"pdf","name":"RemoteSight PDF→Markdown","description":"Extract clean markdown text from a PDF (text-layer PDFs; no OCR). Turns a document an agent can't cheaply read into compact tokens.","tags":["pdf","markdown","extraction","document","context-compression"],"quality_warning":false},{"skill_id":"chunk","name":"RemoteSight RAG Chunker","description":"Split a document into token-bounded chunks at natural boundaries (paragraphs/sentences), with optional overlap. Ready-to-embed pieces for RAG, no tokens spent on the splitting logic.","tags":["chunking","rag","text","embeddings","context"],"quality_warning":false},{"skill_id":"extract","name":"RemoteSight Structured Extract","description":"Extract structured JSON from a web page: title, byline, publish date, Open Graph/meta tags, embedded JSON-LD (schema.org), links, and images. Deterministic, no LLM.","tags":["html","extraction","metadata","json-ld","schema.org","scraping"],"quality_warning":false}],"quality_flags":[],"check_history":{"checks":1,"passed":1},"recent_checks":[{"card_url":"https://workbot1.oddsys.org/.well-known/agent-card.json","checked_at":"2026-10-10T13:34:39.771881+00:00","success":true,"http_status":200,"detail":"Agent Card validated"}],"endpoint_tls_check":null,"protocol_check":{"checked_at":"2026-10-10T13:34:39.771881+00:00","state":"unconfirmed","http_status":404,"detail":"Endpoint returned a generic not-found response"},"events":[],"relationships":[],"verification":{"agent_card_url":"https://workbot1.oddsys.org/.well-known/agent-card.json","last_successful_card_check":"2026-10-10T13:34:39.771881+00:00","latest_card_check":{"checked_at":"2026-10-10T13:34:39.771881+00:00","success":true,"http_status":200,"detail":"Agent Card validated"},"signature_status":"unsigned","signature_checked_at":"2026-10-10T13:34:39.771881+00:00","task_endpoint_tested":true,"task_execution_tested":false,"endpoint_tls_checked_at":null,"endpoint_tls_reachable":null,"protocol_check_state":"unconfirmed","protocol_checked_at":"2026-10-10T13:34:39.771881+00:00","provider_identity_verified":false,"domain_claimed_at":null,"domain_proof_checked_at":null}}