json1.4 KB

Openai-Compatible Accessibility Review Prompt 27

JSON openai-compatible prompt 27 for the planning phase of a accessibility review; it asks for assumptions, reversible actions, and explicit acceptance checks. Stable P8 artifact p8-prompt-117.

Prompt engineering Prompt testing Content creation

Preview — first 50 linesjson

{
  "model": "example-model",
  "messages": [
    {
      "role": "system",
      "content": "Keep creator edits reversible and testable."
    },
    {
      "role": "user",
      "content": "Plan a accessibility review; return assumptions, ordered actions, and acceptance checks."
    },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_p8_27",
          "type": "function",
          "function": {
            "name": "inspect_media_metadata",
            "arguments": "{\"asset_id\":\"input-01\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "call_p8_27",
      "content": "{\"durationSeconds\":30,\"channels\":2,\"offline\":true}"
    }
  ],
  "response_format": {
    "type": "json_object"
  },
  "metadata": {
    "fixture": "p8-prompt-117",
    "offline": true
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "inspect_media_metadata",
        "description": "Read metadata from a local fixture id; inert example only.",
        "parameters": {
          "type": "object",
          "properties": {
            "asset_id": {
              "type": "string"
            }

… 62 lines total — download for the full file.

Specifications

Prompt Number: 117
Provider Variant: openai-compatible
Topic: accessibility review
Phase: planning
Example Kind: tool
Delivery Mode: download-only
Provider: openai-compatible
Provenance: Synthetic deterministic P8 fixture generated by generation/p8_content.py; seed namespace 2026082300

Testing contract

Reference control

Scenario: Parse the JSON fixture using the openai-compatible envelope and extract its task plus response contract.
Expected result: The request targets a accessibility review, identifies the planning phase, and requires assumptions, ordered actions, and acceptance checks without a network call; the inert tool example preserves tools, tool_choice, tool_calls, and the matching tool_call_id.

What is a .json file?

JSON (JavaScript Object Notation) is a lightweight, text-based data-interchange format representing objects, arrays, strings, numbers, booleans, and null. It is language-independent, human-readable, and the dominant format for web APIs and configuration. It requires a single well-formed root value.

How to use this file

Use an example JSON file to test parsers and serializers, schema validation, Unicode and number-precision handling, and API request or response processing.

How to use this file for testing

“Openai-Compatible Accessibility Review Prompt 27” is a deterministic Novus Examples fixture for Prompt engineering, Prompt testing, Content creation. A templated prompt library in JSON Lines with tasks, tags, and placeholders — for testing prompt-management tools and JSONL parsers.

Documented properties for this file: JSON · 1,386 bytes. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.

Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such — expect parsers to fail loudly rather than silently accept them.

Prompt fixtures are static, provider-labelled inputs and contracts — they do not call an API. For a six-step kit, follow workflowOrder from the brief through the expected output, then compare the documented assertions before trying the controlled edge case.

Code examples

import json

with open("p8-prompt-117.json") as f:
    data = json.load(f)
print(type(data), len(data))

Generated by generation/p8_content.py. Free for any use, no attribution required — license.