Agent skill

Iflytek Text Proofread

by iflytek in iflytek/iFly-Skills

iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types).

Apache-2.0Auto-check passedWriting & Content

Install Iflytek Text Proofread

skills CLI
$ npx skills add iflytek/iFly-Skills --skill iflytek-text-proofread -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install iflytek/iFly-Skills iflytek-text-proofread --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/iflytek/iFly-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/iflytek-text-proofread .claude/skills/iflytek-text-proofread && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
iflytek-text-proofread
GitHub stars
209
Token cost
~1.4k tokens
SKILL.md length
353 words
Files
4 (incl. scripts)
Skills in repo
11
Repo updated
First seen
Licence
Apache-2.0

At a glance

iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types).

  • Works in 2 steps: Create an app at 讯飞控制台 with 公文校对 service… → Set environment variables
  • The user wants to proofread
  • SKILL.md covers Setup, Usage, Output and Notes, plus 1 more section
  • Runs Python scripts from its folder; calls python3; reaches cn-huadong-1.xf-yun.com; needs IFLY_API_KEY and IFLY_API_SECRET

What it does

Iflytek Text Proofread is an agent skill from iflytek/iFly-Skills. iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types). Supports up to 220,000 characters. Use when the user wants to proofread, check, or correct Chinese text, especially official documents. Pure Python stdlib, no pip dependencies.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `README.md`, `_meta.json` and `scripts/text_proofread.py`).

It sits in Writing & Content, covering Copy editing and proofreading. It works with Python. The repository describes itself as: Official collection of iFLYTEK skills for speech, OCR, translation, proofreading, and multimodal AI capabilities. The licence is Apache-2.0.

When your agent uses it

  • The user wants to proofread
  • Correct Chinese text
  • Especially official documents

Example prompts

  • “/iflytek-text-proofread”

Requirements

  • Python 3
  • A credential in IFLY_API_KEY
  • A credential in IFLY_API_SECRET

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Create an app at 讯飞控制台 with 公文校对 service enabled
  2. Set environment variables

What it can do on your machine

Read from SKILL.md and the folder at commit 58dc114. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cn-huadong-1.xf-yun.com

    Also links to:

    • console.xfyun.cn
    • xfyun.cn

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • IFLY_API_KEY
    • IFLY_API_SECRET

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Iflytek Text Proofread loads about 1.4k tokens when it runs. Until then it costs about 99 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from iflytek/iFly-Skills at commit 58dc114, republished under its Apache-2.0 licence (© iflytek). 353 words, ~1,447 tokens.

Download SKILL.mdSave it as .claude/skills/iflytek-text-proofread/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
iflytek-text-proofread
description
iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types). Supports up to 220,000 characters. Use when the user wants to proofread, check, or correct Chinese text, especially official documents. Pure Python stdlib, no pip dependencies.
metadata.homepage
https://www.xfyun.cn/services/text_proofread
metadata.openclaw
{"emoji":"✏️","dimensions":["公文校对","文本纠错"],"user_instructions":["帮我校对这段文字","检查这篇文章有没有错别字","公文纠错"],"requires":{"bins":["python3"],"env":["IFLY_APP_ID","IFLY_API…

ifly-text-proofread

Proofread Chinese text using iFlytek's Official Document Proofreading API (公文校对). Detects 27 types of errors across three categories:

文字标点差错: 错别字、多字、少字、语义重复、语序错误、句式杂糅、标点符号、量词单位、数字差错、句子查重、序号检查

知识性差错: 地理名词、机构名称、专有名词及术语、常识差错、媒体报道禁用词和慎用词

内容导向风险: 涉低俗辱骂、其他敏感内容

Setup

  1. Create an app at 讯飞控制台 with 公文校对 service enabled
  2. Set environment variables:
    bash
    export IFLY_APP_ID="your_app_id"
    export IFLY_API_KEY="your_api_key"
    export IFLY_API_SECRET="your_api_secret"

Usage

Basic proofreading
bash
python3 scripts/text_proofread.py "第二个百年目标"
Read from stdin
bash
echo "我们要加强对蓝球运动的推广" | python3 scripts/text_proofread.py -
Read from file
bash
python3 scripts/text_proofread.py --file document.txt
Options
FlagShortDescription
textText to proofread (use - for stdin)
--file-fRead text from a file
--rawOutput decoded JSON response
Examples
bash
# Proofread a sentence
python3 scripts/text_proofread.py "我国加强蓝球运动的推广力度"

# Proofread a long document from file
python3 scripts/text_proofread.py -f report.txt

# Pipe from clipboard or other tools
pbpaste | python3 scripts/text_proofread.py -

# Raw JSON for debugging
python3 scripts/text_proofread.py --raw "测试文本"

Output

  • ✅ 无错误 — text passed proofreading with no issues
  • 🔍 发现 N 处问题 — lists each error with:
    • Error word + category
    • Explanation
    • Context in the original text
    • Position and length
    • Suggested action (标记/替换/删除)
    • Correction suggestions

Notes

  • Max text length: 220,000 characters per request (auto-truncated with warning)
  • Auth: HMAC-SHA256 signed URL (host + date + request-line → signature → authorization)
  • Endpoint: POST https://cn-huadong-1.xf-yun.com/v1/private/s37b42a45
  • Env vars: IFLY_APP_ID, IFLY_API_KEY, IFLY_API_SECRET
  • No pip deps: Uses only Python stdlib (urllib, hmac, hashlib, json, etc.)
  • Text is base64-encoded in the request body; response text field is also base64-encoded

常见问题

❓ 错误能力ID对照表

在使用API时,返回的 belongId 字段对应以下错误类型:

belongId说明常见场景
9错别字、词「蓝球」→「篮球」、「的」「地」「得」混淆
31多字错误「大大大大力」→ 删除多余字
32少字错误「中国成立」→ 「中华人民共和国成立」
35语义重复「大力大力发展」→ 语义重复
34语序错误「很好很强大」→ 「很强大很好」
39量和单位差错「3斤米」→ 「3公斤米」
36数字差错「第十几个」→ 数据不一致
20句式杂糅「原因是由于...」→ 句式杂糅
21标点符号差错顿号逗号混用、书名号错误
24句子查重文档内部重复句子
119重要讲话引用领导人讲话用词规范
123地理名词省市区名称、行政区划
19机构名称党政机关、企事业单位名称
124专有名词及术语专业术语、科技术语
122媒体报道禁用词敏感词、违规词检测
6常识差错明显与事实不符的内容
111涉低俗辱骂低俗内容、辱骂词汇
118其他敏感内容各类敏感信息检测

Show full SKILL.md (126 more words)Show less
🔧 出现错误怎么办?— 用户视角引导
1️⃣ 收到错误响应不要慌~ (´▽`)
  • 首先检查:环境变量 IFLY_APP_ID、IFLY_API_KEY、IFLY_API_SECRET 是否都设置好了呢?ฅ•̀∀•́ฅ
  • 然后看这里:
    • 返回的 code 字段:0 = 成功,其他 = 失败 (详见下文错误码表)
    • 响应里的 data 字段包含检测结果,message 字段有详细说明哦~
2️⃣ 常见错误码一览 ✧(•̀ω•́)✧
code说明解决方法
0成功完美!继续使用吧~ ✨
101参数缺失快检查一下 text 参数有没有传呀?
102参数无效文本内容有问题,看看是不是太长了(≤220000字符)?
103请求超长文本太长了啦!分段处理试试吧~
104超过并发访问太频繁啦,休息一下再试试呗~ ⏳
105无配额配额用完了...去讯飞控制台看看还能不能用吧 (。•́︿•̀。)
106无产品权限还没开通公文校对服务哦!去 讯飞控制台 开通一下吧~
107授权失败API密钥可能过期或错误,检查一下环境变量吧!
108模型加载失败服务端问题,稍后再试一次吧~
3️⃣ 解析结果好迷茫?来,手把手教你~ (。・ω・。)

返回的 detail 数组里每个元素代表一个错误,来看看怎么读懂它:

detail[i].word        → 错误的内容是什么
detail[i].type        → 错误类型ID(对应上面的对照表哦)
detail[i].position    → 错误开始位置(从0开始计数)
detail[i].length      → 错误内容的长度
detail[i].suggestion  → 纠错建议
detail[i].ruleName    → 具体触发的规则名称

📍 小技巧:想知道错误在哪里结束吗?position + length 就是结束位置啦!这样就可以精准定位错误咯~


💡 常见问题解答
Q1: 公文校对与文本纠错、文本合规有哪些区别?

A: 文本纠错主要偏向通用领域(如写作、出版)文本进行纠错,公文校对在公文写作使用等领域效果更佳,同时也适合通用领域~ 文本合规对各类场景风险拦截更全面哦!(`・ω・´)ゞ

Q2: 公文校对的position仅标记开始位置,结束位置怎么计算呢?

A: 超简单的啦!讯飞已经给了 position 和 length,用 position + length 就是对应错误词在文本中的结束位置咯~ ✧٩(ˊᗜˋ*)و✧

Q3: 公文校对的文本有什么要求吗?

A: 有的呢~ 原请求的校对文本:

  • ✨ 不能为空
  • ✨ 不能超过 220,000个字符
  • ✨ 汉字、英文字符、数字、标点都算做一个字符哦!

💡 小提示:如果文本太长,建议拆分成多条请求处理,这样效果会更好呀~

Q4: 为什么返回的结果是空的呀?(。•́︿•̀。)

A: 可能的原因:

    1. 文本太短,没有检测到错误(这是好事!说明文本很棒棒~)
    1. API调用失败了,检查一下 code 是不是 0 呢
    1. 网络波动导致的,再试一次看看吧!
Q5: 如何开通或购买服务?

A: 去讯飞官方平台就好啦~


🎉 使用小贴士
  1. 批量处理:长文本可以拆分成多条请求,结果合并起来就好啦~
  2. 实时反馈:可以配合编辑器插件,实现输入即校对功能哦!
  3. 错误分类:利用 belongId 统计各类错误数量,方便针对性修改~

📚 更多资源

祝大家校对顺利!有问题随时来问哦~ (´▽`)ノ 💕

© iflytek, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in skills/iflytek-text-proofread of iflytek/iFly-Skills.

  • SKILL.md
  • README.md
  • _meta.json
  • scripts/text_proofread.py

Open the folder on GitHubat commit 58dc114

Compare with similar skills

Iflytek Text Proofread next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Iflytek Text Proofread compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Iflytek Text Proofread this skilliflytek/iFly-Skills209—~1.4kAutomated safety check: PassApache-2.0
AIGC Detection Rate Reducerxiaofenggan01/aigc-reduce612—~1.5kAutomated safety check: PassMIT
Chinese Official Document QAzhaohui-yang/official-document-drafting139—~466Automated safety check: PassCustom licence
WeChat Article Compliance Revieweraiworkskills/wechat-article-skills665—~1.5kAutomated safety check: PassApache-2.0
Visual Auditpedrohcgs/claude-code-my-workflow1.6k—~651Automated safety check: NotesMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover23k—~3.5kAutomated safety check: PassMIT

Similar skills

  • AIGC Detection Rate Reducer

    xiaofenggan01/aigc-reduce

    Reduces the AI-text detection rate of academic papers by scanning for templated phrasing and making small deterministic edits that keep citations, data and terminology.

    612 GitHub stars~1.5k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Chinese Official Document QA

    zhaohui-yang/official-document-drafting

    Checks the structure and quality of a finished Chinese official document with a section-checking script and a manual checklist, without rewriting it.

    139 GitHub stars~466 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • WeChat Article Compliance Reviewer

    aiworkskills/wechat-article-skills

    Local, offline pre-publish review for a WeChat official account article: sensitive words, typos and platform compliance, producing an actionable fix list.

    665 GitHub stars~1.5k tokensUpdated 14 days ago
    Productivity & AutomationAuto-check passed
  • Visual Audit

    pedrohcgs/claude-code-my-workflow

    Adversarial visual-layout audit of a Quarto .qmd or Beamer .tex deck.

    1.6k GitHub stars~651 tokensUpdated 9 days ago
    Documents & OfficeAuto-check: notes
  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    23k GitHub stars~3.5k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Story Multi-Perspective Review

    zenstory-ai/oh-story-claudecode

    Reviews Chinese web-novel text with several reviewer agents in parallel, falling back to a single-agent pass, and reports structure, character, prose and setting problems with fixes.

    7.3k GitHub starsUsed in 3 repos~3k tokens
    Writing & ContentAuto-check passed

More from iflytek/iFly-Skills

All 11 skills in this repo
  • Animated Sketch Diagram

    iflytek/iFly-Skills

    生成"黑墨手绘涂鸦"风格的动画架构图/流程图:米色纸面、针管笔墨线、极淡水洗色块、简笔涂鸦图标、序号章、连线上的流动圆点动画、图标微动效。产出单文件自包含动画 HTML(SVG+CSS),可一键导出无缝循环 GIF。当用户想画架构图、流程图、信息图、技术示意图、对比图、pipeline/workflow 可视化,或提到"手绘风""涂鸦风""动图""animated diagram""GIF…

    209 GitHub stars~999 tokensUpdated today
    Auto-check passed
  • A skill your agent uses when user asks to review contracts, detect contract risks, or perform compliance checks.

    209 GitHub stars~773 tokensUpdated today
    Auto-check passed
  • Iflytek Hyper Tts

    iflytek/iFly-Skills

    A skill your agent uses when user asks to synthesize speech, convert text to audio, or read text aloud.

    209 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Iflytek Image Understanding

    iflytek/iFly-Skills

    A skill your agent uses when user asks to analyze an image, describe image contents, or answer questions about a picture.

    209 GitHub stars~949 tokensUpdated today
    Auto-check passed
  • Iflytek OCR Invoice

    iflytek/iFly-Skills

    A skill your agent uses when user asks to recognize invoices, extract receipt data, or OCR bills and tickets.

    209 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Iflytek PDF Image OCR

    iflytek/iFly-Skills

    ifly-pdf-image-ocr skill supporting both image OCR (AI-powered LLM OCR) and PDF document recognition.

    209 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

Works with

Questions about Iflytek Text Proofread

What does Iflytek Text Proofread do?

iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types). Iflytek Text Proofread is an agent skill from iflytek/iFly-Skills. iFlytek Official Document Proofreading (公文校对) — detect and correct errors in Chinese text including typos, punctuation, word order, factual mistakes, sensitive content, and more (27 error types).

When should I use Iflytek Text Proofread?

Iflytek Text Proofread fits situations like: the user wants to proofread; correct Chinese text; especially official documents.

How do I install Iflytek Text Proofread in Claude Code?

Run `npx skills add iflytek/iFly-Skills --skill iflytek-text-proofread -a claude-code`. Or copy the skill folder (skills/iflytek-text-proofread in iflytek/iFly-Skills) into .claude/skills/iflytek-text-proofread in your project. Claude Code loads it when a task matches its description.

How do I install Iflytek Text Proofread in Codex?

Run `npx skills add iflytek/iFly-Skills --skill iflytek-text-proofread -a codex`. Or copy the skill folder (skills/iflytek-text-proofread in iflytek/iFly-Skills) into .agents/skills/iflytek-text-proofread in your project. Codex loads it when a task matches its description.

Can I use Iflytek Text Proofread in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iflytek/iFly-Skills --skill iflytek-text-proofread -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iflytek-text-proofread, .gemini/skills/iflytek-text-proofread, .github/skills/iflytek-text-proofread and .opencode/skills/iflytek-text-proofread in your project.

What does Iflytek Text Proofread need to run?

Going by SKILL.md and its folder, Iflytek Text Proofread needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named IFLY_API_KEY and IFLY_API_SECRET. Our summary lists: Python 3; A credential in IFLY_API_KEY; A credential in IFLY_API_SECRET.

Does Iflytek Text Proofread access the network?

SKILL.md names 3 domains. In commands or code: cn-huadong-1.xf-yun.com; the agent is likely to contact it when it follows the instructions. As links in the text: console.xfyun.cn and xfyun.cn. This is read from the text; nothing was executed.

Is Iflytek Text Proofread safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Iflytek Text Proofread use?

Iflytek Text Proofread is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Iflytek Text Proofread use?

About 1.4k tokens (SKILL.md is roughly 5.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Iflytek Text Proofread?

Skills that share tags, products or a category with Iflytek Text Proofread: AIGC Detection Rate Reducer (xiaofenggan01/aigc-reduce, 612 stars), Chinese Official Document QA (zhaohui-yang/official-document-drafting, 139 stars), WeChat Article Compliance Reviewer (aiworkskills/wechat-article-skills, 665 stars) and Visual Audit (pedrohcgs/claude-code-my-workflow, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Iflytek Text Proofread?

iflytek (a GitHub organization) maintains it in iflytek/iFly-Skills, which has 209 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.

Source: iflytek/iFly-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.