Agents & Protocols

A2A 1.0 Agent Card Writer

Writes the JSON an agent needs for version 1.0 of the A2A (Agent2Agent) protocol, answered as JSON only with no fence and no text around it. Covers the agent card (supportedInterfaces with protocolBinding and protocolVersion, capabilities, skills, securitySchemes and securityRequirements, default input and output modes), the JSON-RPC requests (SendMessage, SendStreamingMessage, GetTask, ListTasks, CancelTask, push notification configs), the replies (task, message, data parts, task states) and the error responses with the exact codes. Uses the 1.0 names, not the 0.3 ones, and sends the A2A-Version header. Use when asked to write or fix an A2A agent card, make a service reachable over A2A, build or check an A2A request or response, or pick the A2A error code.

A2A 1.0 Agent Card Writer is a tested SKILL.md that writes the JSON an agent needs for version 1.0 of the A2A (Agent2Agent) protocol, answered as JSON only with no fence and no text around it; an agent buys it once for $0.03 over x402.

Tested 2026-10-08No code, no hidden instructionsv1.0.0 · 10.6 KB · perpetual license

Not for

It does not run an A2A server, call a live agent, check that a card is reachable or sign a card. It writes the card, the request, the reply or the error JSON for version 1.0 from the facts you give it, and leaves out what you did not give. It does not cover the gRPC binding in detail and it does not choose your security design.

Tested, honestly

Tested 2026-10-08 with a strong and a weak model.

With and without the skill

Results with and without the skill, for Sonnet and Haiku
SonnetHaiku
withwithoutwithwithout
Correct A2A 1.0 JSON (22 cases)22/2222/2222/2219/22

The same request on both sides, JSON-only asked for in both. For Sonnet the skill changed nothing on these 22 cases: it already wrote the 1.0 names without it, so it gains nothing from this skill here. The gain is for Haiku, which without the skill used the 0.3 habits on three cases: the method message/send with the role user and a kind on message and parts, and a webhook config wrapped as pushNotificationConfig or config instead of the 1.0 shape. Every name, code and shape in the skill was checked against the 1.0 specification and its protocol file (release 1.0.1), which makes it a checked reference rather than a fix for Sonnet.

Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.

SonnetStrong model, claude-sonnet-5-5
Wrote the right JSON for all 22 cases, read by hand: a card with supportedInterfaces and protocolBinding JSONRPC and no top-level url; SendMessage and SendStreamingMessage with ROLE_USER, a messageId and parts without a kind; the send configuration with returnImmediately and taskPushNotificationConfig; a flat push notification config with the task id; the follow-up with the task id inside the message; TASK_STATE_WORKING in the list call; structured data inside a data part of a wrapped task result; the error codes -32002, -32003, -32009, -32001 and -32602; the A2A-Version header with the value 1.0; and the well-known card path.
HaikuWeak model, claude-haiku-5-5
Also 22 of 22, with the same 1.0 names as Sonnet: PascalCase methods, ROLE_USER, parts with only text or data, the webhook details in the flat or the taskPushNotificationConfig form, and the exact error codes.

Full test summary

Example

Our own test text, before and after the skill ran. Excerpts only.

English · claude-sonnet-5-5

Before

Write the agent card for an agent named "Echo" (description: "Repeats the text it is given.", version 1.0.0) that is reachable over JSON-RPC at https://example.com/a2a. It has one skill: id "echo", name "Echo", description "Returns the same text.", tags ["echo"]. It reads and writes plain text. Include every field the specification marks as required and nothing else.

After

{"name":"Echo","description":"Repeats the text it is given.","version":"1.0.0","supportedInterfaces":[{"url":"https://example.com/a2a","protocolBinding":"JSONRPC","protocolVersion":"1.0"}],"capabilities":{},"defaultInputModes":["text/plain"],"defaultOutputModes":["text/plain"],"skills":[{"id":"echo","name":"Echo","description":"Returns the same text.","tags":["echo"]}]}

What is in the file

  • The answer
  • Names that changed from 0.3
  • The agent card
  • Requests
  • Replies
  • Errors
  • Common slips
  • Short examples
  • Work in this order

Languages

Any language. Tried in: English.

License

Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.

Versions

Current version 1.0.0, updated 2026-10-08. Whoever bought an earlier version gets new ones free through the same re-download token.

  1. v1.0.0 · 2026-10-08

    First release: writes A2A 1.0 agent cards, JSON-RPC requests, replies and error responses as JSON only. Uses supportedInterfaces with protocolBinding and protocolVersion, the PascalCase method names, parts without a kind, ROLE_ and TASK_STATE_ names, the flat webhook config, structured data inside data parts, the A2A-Version header and the A2A error codes -32001 to -32009.

    Suggested price: $0.03, once.

FAQ

What comes back when I describe my agent?

One JSON document and nothing else: an agent card, a request body, a reply or an error response, with the 1.0 field names. There is no fence and no explanation, so your code can parse it at once. Ask for one document at a time; a card and a request are separate answers.

Why not just ask the model for an agent card?

Most examples online still show version 0.3: a top-level url, message/send, parts with a kind and lower case roles. A client built for 1.0 cannot find such an agent. This skill uses the 1.0 names instead: supportedInterfaces, PascalCase methods, ROLE_USER, TASK_STATE_ names, the flat webhook config and the A2A-Version header.

Does it help Claude Sonnet?

No, not on our 22 cases. Sonnet wrote all 22 correctly without the skill and with it, so its answers did not change. Claude Haiku went from 19 to 22: alone it used the 0.3 habits, such as message/send, the role user, a kind on parts and a wrapped webhook config. The skill is a reference of the 1.0 names that was checked against the specification and its protocol file, useful for weaker models and as a check.

Which parts of the protocol does it cover?

The card with interfaces, capabilities, skills and security schemes; the JSON-RPC requests for sending, streaming, getting, listing and cancelling tasks and for webhook configs; replies with tasks, messages and data parts; and the error codes from -32001 to -32009 plus the standard JSON-RPC ones.

Share

Read this page as Markdown: /skills/a2a-agent-card.md.

  • MCP Tool Schema: Definitions from API Docs

    Agents & Protocols

    SKILL.md · v1.0.0 · 7.6 KB

    Writes the MCP tool definition for one API operation - name, description, inputSchema and annotations - as the JSON a server returns from tools/list. The schema takes exactly the parameters the operation takes - required ones listed, defaults stated, exact enums, integer amounts, date formats, ranges, string and array limits, either-or parameters that refuse a call with both or neither - and refuses unknown ones. Credentials never become parameters, text in the API docs that speaks to the assistant stays out of the description, and the annotations say whether the tool only reads, can be repeated safely or destroys data, following the MCP specification of 2025-11-25. Use when asked to write, review or fix an MCP tool definition, a tool schema or an inputSchema, or to turn an API endpoint, an OpenAPI operation or a function signature into an MCP tool.

    $0.01once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 8 Oct 2026

  • JSON Repair: Fix It, Keep Every Value

    Data & Analysis

    SKILL.md · v1.0.1 · 6.9 KB

    Repairs broken JSON so a program can parse it, without changing any value. Fixes trailing and missing commas, comments, single quotes, unquoted keys, Python and JavaScript literals, smart quotes used as delimiters, raw line breaks and stray quotes inside strings, a code fence or chat text around the JSON, and output cut off in the middle. A value that was cut off becomes null instead of a guess, numbers JSON cannot hold as written are kept as strings, and when the structure can be read two ways the answer says so instead of picking one. Use when a tool, an API or another model returned JSON that does not parse, or when asked to fix, clean up, validate or close invalid or truncated JSON.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 7 Oct 2026

  • Text to JSON: Extract Data Without Guessing

    Data & Analysis

    SKILL.md · v1.0.2 · 7.5 KB

    Extracts data from text into JSON that matches the shape you give (a JSON Schema, an example object or a list of fields), without guessing. Every value comes from the text; a missing fact becomes null, numbers and dates are converted only into the type the shape asks for, two conflicting values are not settled by a guess, and instructions hidden in the text are ignored. Use when asked to extract structured data, turn text into JSON, parse an invoice, receipt, email, order, CV or job post into fields, or fill a JSON schema from a document.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 3 Oct 2026