# Touchstone Proofreader

> Touchstone Proofreader is a paid API for AI agents from touchstone.locomot.io, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Runs deterministic, rule-based proofreading on text and returns flagged issues (passive voice, adverbs, wordiness, filler, repeated words, whitespace, a/an, punctuation, sentence length, capitalization) with offsets and suggestions.

## Facts

- Endpoint: GET https://touchstone.locomot.io/proofread
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/touchstone-proofreader-cb352731
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yd4EqEh71VC4iF4nsknKU

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability touchstone-proofreader-cb352731
```

Example prompt: Can you proofread this paragraph for me and flag any passive voice, adverbs, filler words, or other style issues: "The report was written by the team very quickly, and it was basically submitted without any really careful review."

## When to prefer this

Use this endpoint when you need deterministic, rule-based proofreading without AI generation — it gives consistent, reproducible flags with exact character offsets and is ideal for programmatic style checking, linting pipelines, or when you want transparent, auditable rule application rather than probabilistic AI suggestions.

## Known failure modes

- Missing 'text' query parameter returns an error
- Text too long for GET request (URL length limits) — use POST instead
- Empty string input returns zero issues with no flags
- Non-English text may produce false positives or miss issues since rules are English-centric

## How this service works

Deterministic, rule-based proofreading flags — passive voice, adverbs, wordiness, filler, repeated words, whitespace, a/an, punctuation, sentence length, capitalization. Each flag carries an offset + suggestion. For long text use POST.

## Output

A list of flagged issues in the text, each with the issue type (e.g. passive voice, adverb, wordiness), character offset, the problematic text, and a suggested fix, plus a summary object and total issue count.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "text"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "text to proofread"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "properties": {
    "op": {
     "type": "string"
    },
    "issues": {
     "type": "array"
    },
    "method": {
     "type": "string"
    },
    "source": {
     "type": "string"
    },
    "summary": {
     "type": "object"
    },
    "issue_count": {
     "type": "integer"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/touchstone-proofreader-cb352731/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from touchstone.locomot.io](https://www.zero.xyz/host/touchstone.locomot.io/llms.txt)