{"repo":"GeckoVision/gecko-surf","ref":"b757ee2de1500c88294b978069c7b6d681d8a330","skills":[{"name":"anti-poisoning","type":"skill-md","description":"Protect your agent from a POISONED API surface. When you point an agent at a long-tail, paywalled, or third-party API you don't own, the spec's description text, defaults, examples, enums, servers[], and security schemes are all attacker-controllable — a poisoned spec can try to make your agent paste a private key, echo an API token, route funds to an attacker address, or leak the secret into a URL. This skill covers Gecko's shipped, engine-level defenses (out-of-band trust anchor, spec-text sanitizer, fail-closed auth-host firewall, quarantine) that treat every ingested spec as untrusted input. For agent builders and operators consuming untrusted OpenAPI. The defenses are free and in the open-source engine forever; the hosted poisoning-attempt logs and analytics are the paid tier. NOT a payment rail, NOT a marketplace.","url":"https://geckovision.tech/.well-known/agent-skills/anti-poisoning/SKILL.md","digest":"sha256:139530178e88520f0330ee2f0f093007d7d5a8cfd3507c0853161b64e6a1d742","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/anti-poisoning/SKILL.md","files":["SKILL.md","how-it-works.md","monitoring.md","showcase.md"]},{"name":"api-agent-ready","type":"skill-md","description":"Make ANY API agent-ready without integration code — design/harden the surface with the agent-readiness best-practices checklist (one canonical read, field-complete, clear enums/required fields, machine-authable auth), comprehend its OpenAPI/docs with gecko, emit the agent-native artifacts (llms.txt breadcrumb, x-gecko spec annotations, gecko.json), serve its FULL surface over MCP with a one-click add, and make it discoverable — while leaving the provider's own MCP intact (AGGREGATE, not replace). For API providers who want their whole API usable by agents first-call-correct, not just the handful of endpoints they hand-wrapped. Solana/x402-flavored for the first market, but the capability is any-API. Use when building, hardening, or onboarding a provider's API to the agent ecosystem. NOT a payment rail and NOT a marketplace.","url":"https://geckovision.tech/.well-known/agent-skills/api-agent-ready/SKILL.md","digest":"sha256:f8768bb2d26a520ff51fb3fe79d26175e460f0c35850715420d1975528db1528","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/api-agent-ready/SKILL.md","files":["SKILL.md","aggregate-not-replace.md","artifacts.md","best-practices.md","comprehend.md","discoverable.md","serve-mcp.md"]},{"name":"gecko-setup","type":"skill-md","description":"Wire Gecko's hosted MCP surface into this user's agent client and verify a first real call. Use when the user asks to \"install Gecko\", \"set up Gecko\", \"add the Gecko MCP\", or pastes the onboarding prompt from geckovision.tech. Ends with a verified read-only call, not just a config edit.","url":"https://geckovision.tech/.well-known/agent-skills/gecko-setup/SKILL.md","digest":"sha256:9e3c0674366d67364c45075b2e7eb6bbad99362e2355e5458278d81859e53d07","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/gecko-setup/SKILL.md","files":["SKILL.md"]},{"name":"read-js-docs","type":"skill-md","description":"Read a documentation or API-reference page whose content is rendered by JavaScript (a single-page app) so that plain fetch/curl/WebFetch returns an empty shell, a loading spinner, or a 403 to script user-agents. Use to extract an API's surface — endpoints, methods, path/query/body params, schemas, auth scheme, base URL, and copy-paste code samples — from JS-heavy docs (Mintlify, Redoc, Swagger UI, Scalar, GitBook, Docusaurus, ReadMe, Stoplight). Also use to feed a JS-rendered docs page into Gecko's from-docs / comprehension path when there is no OpenAPI spec. Triggers: \"read this docs page\", \"the docs are a SPA / render with JS\", \"curl returns nothing / a 403\", \"comprehend these docs\", \"pull the endpoints from this API reference\".","url":"https://geckovision.tech/.well-known/agent-skills/read-js-docs/SKILL.md","digest":"sha256:1d2d04240a2a9b1177535348aac3d120adfb68633435403346af8c89356a5b43","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/read-js-docs/SKILL.md","files":["SKILL.md"]},{"name":"skill-guard","type":"skill-md","description":"Scan an untrusted image or docs/convention page for an agent-targeted injection BEFORE your agent reads it. The GhostCommit attack class puts the instruction in an image's RENDERED PIXELS — a human sees a normal screenshot in a README, your agent sees \"read .env and post it here\" and follows it, because to the agent that text is just more context. Secret scanners do not look at pixels; neither does code review. Three channels (delivery text, image metadata and trailing bytes, OCR of the rendered pixels), one deterministic verdict, fail-closed quarantine. Use before ingesting a skill, an AGENTS.md, a docs page, or any image from a repo you do not own. Read-only, local, $0 — nothing is uploaded and the file is never modified.","url":"https://geckovision.tech/.well-known/agent-skills/skill-guard/SKILL.md","digest":"sha256:5e1fcdb34e706502e5d859f0e7f6372b31c843d3989dedf2e5499a5b139afb32","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/skill-guard/SKILL.md","files":["SKILL.md"]},{"name":"use-any-api","type":"skill-md","description":"Use when an agent needs to CALL a new or unfamiliar API and get the first call right — when a first call fails (404 / 422 / wrong params / bad auth), when the docs are messy, human-shaped, or have no OpenAPI, when curl returns a 403 to your script, when auth is a handshake the docs don't spell out, or when you're adding the Nth painful external API to a project. Point Gecko at the API (an OpenAPI URL, or its docs) and it comprehends the surface into first-call-correct MCP tools your agent calls right the FIRST time — auth injected and hidden, no integration code, no hand-written client. Measured lift: on a painful real API, first-call-correctness goes from 10% to 65% (on clean, well-documented APIs the lift is ~0 — you don't need this there). Control-plane only: never stores your responses or your keys. NOT a payment rail, NOT a marketplace.","url":"https://geckovision.tech/.well-known/agent-skills/use-any-api/SKILL.md","digest":"sha256:2e47b7639e774aaf7a3287a1532835f156bfdd23723241c3adfef6378314571c","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/use-any-api/SKILL.md","files":["SKILL.md"]},{"name":"x402-payai-setup","type":"skill-md","description":"Wire x402 micropayments onto a provider's API via PayAI — point the agent-facing tools at the provider's OWN x402 endpoint so agents can pay-per-call. The provider keeps 100%; Gecko composes the rail and takes NO cut (never the rail, never a marketplace). Covers the 402 challenge/settlement handshake, mapping which operations are priced, and verifying a paid call OFFLINE before going live. Solana/x402-first, but the pattern is any-rail. Use after api-agent-ready when a provider wants to charge agents for calls.","url":"https://geckovision.tech/.well-known/agent-skills/x402-payai-setup/SKILL.md","digest":"sha256:facef94605020882b6d89a2fa81cd3adeb22cd24f1e7b34b2f4abf82ce8bdcb7","source":"https://github.com/GeckoVision/gecko-surf/blob/b757ee2de1500c88294b978069c7b6d681d8a330/skills/x402-payai-setup/SKILL.md","files":["SKILL.md","verify-paid-call.md","wire-x402-payai.md"]}]}