# Proofread

Proofread is a tested SKILL.md that proofreads a text with minimal intervention, in the language of the text; an agent buys it once for $0.03 over x402.

- Page: https://aiskills402.com/skills/proofread
- Category: Editing & Proofreading (https://aiskills402.com/categories/editing)
- Price: $0.03 once, USD-priced, paid in USDC on Base over x402. Price as loaded on this page. The 402 response your agent receives is authoritative.
- Version: 1.0.0
- Card (JSON): https://api.aiskills402.com/v1/skills/proofread

## Use it when

Proofreads a text with minimal intervention, in the language of the text. Fixes spelling, grammar, punctuation and obvious typos, keeps everything else, and returns the corrected text plus a short list of changes for review. Use when asked to proofread, correct, spell-check or fix the mistakes in a text without rewriting it.

## Not for

Rewriting, style editing, translation or fact-checking. It only fixes plain spelling, grammar, punctuation and typos and leaves wording, meaning, numbers and names as they are.

## Tested, honestly

Tested 2026-09-30.

- Strong model (claude-sonnet-5-5 (Claude Code alias "sonnet")): Fixed all planted errors in en, bg, de, es and ru in every one of three runs; left a correct English text untouched ("Changes: none"), kept all numbers, names and British spelling. Only failure: length limit on one Spanish text, where it correctly flagged a real ambiguity in the test text and the extra line pushed the output to 1.32 of the input.
- Weak model (claude-haiku-4-5-20251001 (Claude Code alias "haiku")): Good on en, de, es, ru and the correct-text case. Unreliable on Bulgarian: in three runs it missed 'училищята' (should be 'училищата') every time and 'засадание' (should be 'заседание') in two of three. One English run was too verbose (length 1.33). No meaning, number or name was changed by either model.

Note: Three full runs, one run per model and case each time. The first run's German failures were a bug in my own check (case-insensitive forbid), fixed before run two. Sonnet and Haiku differ between runs on borderline cases, so treat single results as indicative. The planted errors per language are listed in test/planted.json.

Full summary: https://aiskills402.com/skills/proofread/tests

## What is in the file

- Hard rules
- What counts as an error
- Language notes
- Output format
- Final check

## Languages

Any language

## How to buy

Agent (HTTP):

1. GET https://api.aiskills402.com/v1/skills/proofread/file without a payment header. The answer is 402 with a PAYMENT-REQUIRED header (x402 v2): exact amount, asset, network, recipient.
2. Sign `accepts[0]` with an x402 client (for example @x402/core + @x402/evm).
3. Repeat the GET with the signature in the PAYMENT-SIGNATURE header. The answer is 200 with the file, its sha256 and a re-download token.

Agent (MCP): https://mcp.aiskills402.com/mcp — free tools search_skills, get_skill, redownload_skill. Buying itself is over HTTP.

Full flow: https://aiskills402.com/docs

## The file

- Version: 1.0.0
- Size: 6.1 KB (6278 bytes)
- SHA-256: 6b582fdece95875dab0a1d90e5a0ed49eb9f2b59b0c9189c258c2f5c8a549900
- Updated: 2026-09-30
- New versions are free through your re-download token.

## Versions

### 1.0.0 (2026-09-30)

First release: minimal-intervention proofreading in the text's own language, with a review list of changes.

## License

Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Terms: https://aiskills402.com/docs#license

## FAQ

### How do I see what was changed?

The output is the corrected text followed by a short list of changes, so a person or another agent can review each edit instead of trusting the whole rewrite. When the text is already correct, the skill says so and lists no changes.

### How well does it work outside English?

With a strong model it fixed every planted error in English, Bulgarian, German, Spanish and Russian across three runs. The small model was good in four of those languages but repeatedly missed two Bulgarian errors, a wrong plural form and a misspelled word. For Bulgarian, use the stronger model.

### Could it change a number or a name?

Neither tested model altered a number or a name, and the strong model kept British spelling as written. The one length failure came from a Spanish test text where the skill correctly flagged a genuine ambiguity and the extra line made the answer longer than allowed.

## Related skills

- [Humanize](https://aiskills402.com/skills/humanize.md): $0.05 once
- [SEO Meta Writer](https://aiskills402.com/skills/seo-meta.md): $0.03 once
- [Faithful Summary](https://aiskills402.com/skills/summarize.md): $0.03 once

## Measurement limits

- Models other than the two named above were not run.
- Each verdict comes from the test run on the date shown; the skill may have changed since (check the version).
- Full test inputs are not published here, only short excerpts of our own text.
- Results on your own texts, languages and domains can differ.

Offer note: Paid in USDC (USD-pegged) over x402 by an AI agent; one-time.