Agent skill

Hai Simplified Technical

by Genshin-bots in Genshin-bots/gsuid_core

Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague…

GPL-3.0Auto-check passedDevelopment

Install Hai Simplified Technical

skills CLI
$ npx skills add Genshin-bots/gsuid_core --skill hai-simplified-technical -a claude-code

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

GitHub CLI
$ gh skill install Genshin-bots/gsuid_core hai-simplified-technical --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/Genshin-bots/gsuid_core.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/human-talk .claude/skills/hai-simplified-technical && 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
hai-simplified-technical
GitHub stars
356
Used in
1 other repo
Token cost
~2.5k tokens
SKILL.md length
1,481 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
GPL-3.0

At a glance

Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague…

  • Works in 5 steps: Check the scope. Confirm that the text… → Find the project conventions. Look for a… → Write or rewrite. Follow the summary… → …
  • Migration guides
  • SKILL.md covers Overview, Scope, Language and Workflow, plus 4 more sections
  • Calls python3

What it does

Hai Simplified Technical is an agent skill from Genshin-bots/gsuid_core. Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague words or hidden verbs, imperative steps with the condition first, warnings before the step. Use for design docs, READMEs, API docs, runbooks, migration guides, commit and PR text, code comments and error messages, or when asked for STE, controlled language or plainer docs(按 STE 写、受控中文、写得干净点、去掉翻译腔). Not for marketing…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Technical documentation. The repository describes itself as: 💖一套业务逻辑,多个平台支持!异步核心框架GsCore,为插件编写提供完善平台支持、核心数据库统一、复用游戏查询逻辑、网页控制台,支持Bot列表: NoneBot2 & HoshinoBot & ZeroBot & YunZaiBot & Koishi. The licence is GPL-3.0.

When your agent uses it

  • Migration guides
  • Commit and PR text
  • Code comments and error messages
  • Controlled language

Example prompts

  • “/hai-simplified-technical”

Requirements

  • Python 3

Workflow steps

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

  1. Check the scope. Confirm that the text is technical (see Scope).
  2. Find the project conventions. Look for a glossary and a style guide (section 10 of the rule
  3. Write or rewrite. Follow the summary below. Open the rule file of the language when a rule
  4. Run the mechanical check. python3 /scripts/check.py (add --lang en or
  5. Deliver. Follow references/output-template.md.

What it can do on your machine

Read from SKILL.md and the folder at commit 9a6a264. 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

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Hai Simplified Technical loads about 2.5k tokens when it runs. Until then it costs about 160 tokens; SKILL.md has 1,481 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~160
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Genshin-bots/gsuid_core at commit 9a6a264, republished under its GPL-3.0 licence (© Genshin-bots). 1,481 words, ~2,481 tokens.

Download SKILL.mdSave it as .claude/skills/hai-simplified-technical/SKILL.md (or your agent's skills folder).
name
hai-simplified-technical
description
Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague words or hidden verbs, imperative steps with the condition first, warnings before the step. Use for design docs, READMEs, API docs, runbooks, migration guides, commit and PR text, code comments and error messages, or when asked for STE, controlled language or plainer docs(按 STE 写、受控中文、写得干净点、去掉翻译腔). Not for marketing, posts, speeches or fiction. Use hai-rewrite-doc to rebuild content and hai-audit-docs to check facts.

Hai Simplified Technical

For Chinese readers, see SKILL.zh_CN.md. The English SKILL.md is the execution source of truth.

Overview

Make a technical document readable in one way only: one word for one concept, one topic in one sentence, a named actor for each action, and a fixed set of words for requirements. The rules come from the nine sections of ASD-STE100 Part 1. The English rules keep the STE grammar rules that matter for software text. The Chinese rules drop the English-only grammar and add the faults of Chinese technical writing: hidden verbs (进行, 加以), long pre-noun modifiers, missing subjects, unclear pronouns.

Both languages share one rule numbering. references/rules-en.md and references/rules-zh.md hold the full rules with reasons, examples and checks.

Scope

Technical documents only: text that a reader uses to understand a system, do an operation or make a technical decision. Design docs, READMEs, API references, runbooks, troubleshooting and migration guides, commit messages, PR descriptions, code comments, error messages and UI help text are in scope.

Not marketing or creative text: marketing copy, brand stories, blog and social posts, launch announcements, speeches, fiction. That text works through rhythm, emotion and rhetoric. These rules make it flat and defeat its purpose. Write it normally and do not apply this skill.

Mixed documents: release notes and announcements often mix promotion and technical content. Apply the rules to the technical parts only (what changed, how to upgrade, what breaks).

If the user explicitly asks for these rules on non-technical text, do it, and say once that the text will lose its persuasive tone.

Language

  • Write each part in the rules of its own language. Detect the language from the document, not from the conversation.
  • A Chinese document with English terms uses the Chinese rules; 9.1 decides how the terms appear.
  • A bilingual document applies each language's rules to its own text.
  • A translation is not part of this skill. When the user asks for one, translate first, then apply the rules of the target language.

Workflow

  1. Check the scope. Confirm that the text is technical (see Scope).
  2. Find the project conventions. Look for a glossary and a style guide (section 10 of the rule files says where). Project conventions win over these rules, for example a quotation style or a fixed translation.
  3. Write or rewrite. Follow the summary below. Open the rule file of the language when a rule is unclear or when you need an example.
  4. Run the mechanical check. python3 <skill dir>/scripts/check.py <file> (add --lang en or --lang zh to force one language). It lists places to look at, not verdicts: quoted examples, names next to code, and soft rules kept for a reason can stay.
  5. Deliver. Follow references/output-template.md.

Rule summary

Obey every hard rule. Obey about 80% of the soft rules, and have a reason for each one you break.

1 Words

  • 1.1 hard: One word for one concept. Do not vary words for style.
  • 1.2 hard: One meaning for each word.
  • 1.3 hard: Use the glossary. Name a new concept before you use it.
  • 1.4 hard: No vague words. EN: appropriate, relevant, various, significant, fairly, basically. ZH: 适当、有关的、一定程度上、较为、基本上、若干、显著、大幅、明显. Give a number, a name or a condition.
  • 1.5 soft: Verbs that say what happens. EN: handle, process, manage, optimize. ZH: 处理、操作、支持、优化、调整.

2 Noun phrases

  • 2.1 soft: At most two modifiers before a noun. ZH: at most two 的.
  • 2.2 soft: At most three nouns together.
  • 2.3 hard: Modifier markers. EN: hyphenate a compound modifier before a noun. ZH: use 的/地/得 correctly.

3 Verbs

  • 3.1 hard: Do not hide the verb in a noun. EN: perform, carry out, conduct, make an adjustment. ZH: 进行、加以、予以、做出、实现了对……的.
  • 3.2 soft: Active voice; name the actor. EN: passive. ZH: 被, 由……做.
  • 3.3 soft: State facts in the simple tense. EN: no "is sending". ZH: no 正在, no 着 for state.
  • 3.4 hard: Fixed requirement words. EN: must / must not / should / should not / can / need not (or the project's RFC 2119 words). ZH: 应 / 不应 / 宜 / 不宜 / 可 / 不必.
  • 3.5 soft, EN only: A one-word verb when one exists ("find", not "find out").

4 Sentences

  • 4.1 hard: One topic in each sentence.
  • 4.2 hard: Name the actor. EN: no empty "It is / There is", no dangling modifiers. ZH: write the subject when it changes.
  • 4.3 hard: Each pronoun points to one thing. EN: no bare "this". ZH: 它、这、该、其.
  • 4.4 soft: Show the connection: because, so, if, but / 因为、所以、如果、但.
  • 4.5 soft: A vertical list for three or more items.
  • 4.6 hard, EN only: Do not leave out articles or "that" (no telegraph style).

5 Procedures

  • 5.1 hard: Numbered list, one instruction in each step.
  • 5.2 hard: Start each step with an imperative verb.
  • 5.3 hard: Condition before instruction ("If X, do Y").
  • 5.4 soft: Step sentences at most 20 words (EN) or 40 characters (ZH).
  • 5.5 soft: Reasons before the list; each result after its step.

6 Descriptive writing

  • 6.1 hard: Conclusion first in each paragraph.
  • 6.2 soft: One topic in each paragraph, at most six sentences.
  • 6.3 soft: Descriptive sentences at most 25 words (EN) or 50 characters (ZH).
  • 6.4 hard: Every measured number has its conditions and date.
  • 6.5 hard: Keep what is done apart from what is planned.

7 Warnings

  • 7.1 hard: A warning comes before the step it applies to.
  • 7.2 hard: The instruction first, then the risk.
  • 7.3 soft: One risk in each warning.
  • 7.4 hard: Two levels. Warning / 警告: data loss, irreversible, wrong without an error, production impact, publishing outside. Caution / 注意: slower, rework, long wait.

8 Punctuation, numbers, length

  • 8.1 hard: EN: ASCII punctuation. ZH: full-width punctuation.
  • 8.2 hard: One quotation style in each document.
  • 8.3 hard: EN: a space between number and unit. ZH: a space between Chinese and Latin letters or digits.
  • 8.6 hard: Ranges with "–" (or "to" / "到"), never "~".
  • 8.7 hard: Dates that cannot be misread; ISO in tables and parentheses.
  • 8.8 hard: Count EN words between spaces; count ZH characters, plus one for each Latin word, number or code span.

9 Writing practices

  • 9.1 hard: One form for each term. EN: one spelling and case. ZH: the original or one fixed translation.
  • 9.2 hard: Code names in backticks, exactly as in the code.
  • 9.3 hard: Official product names; abbreviations defined at first use.
  • 9.4 soft: No idioms, filler or marketing words. EN: seamless, leverage, simply, just, easily. ZH: 开箱即用、无缝、一劳永逸、赋能.
  • 9.7 soft, EN only: No contractions; no e.g., i.e., etc., via.
Show full SKILL.md (414 more words)Show less

Do not overdo it

The rules make the reader understand one meaning. They do not make the text a telegram.

  • The 80% has limits. Keep every hard rule. Break a soft rule when obeying it would make the sentence awkward or lose information; each rule gives its reason, and where the reason does not apply, the rule need not either.
  • The rules control wording, not content. Keep every fact, condition, exception and doubt of the original. If the original misses something the reader needs (a risk, a rollback, a stale cache), still say so, as a note or an open question. Do not drop domain judgment to look plain.
  • Rewriting is not auditing. Keep each claim of the author at the strength it was written; remove only the empty intensifier ("improved significantly" → "improved", "various other services" → "other services"). Do not ask the document to prove its claims inline. List the missing evidence for the author in the report instead (references/output-template.md).
  • Inline placeholders are rare. Write "[TBD: …]" / "[待补:……]" in the document only when the reader cannot do the task without the fact (which flag to set, which key to check). Never put a guess in a placeholder, and never write a plausible number.
  • Do not touch what must stay. Quotations, code, command output, proper names and the user's own words stay as they are.
  • Keep the structure. Reorder sentences, but keep sections, headings and links unless the user asks for more.

Use a different skill when

  • The document's content is out of date and must be rebuilt from verified conclusions — use hai-rewrite-doc, then apply this skill to the wording if the user wants it.
  • The question is whether the document is true or consistent with the code — use hai-audit-docs.
  • Only the Markdown layout is wrong — use readme-beautifier.
  • The question is what to call a concept across modules — use hai-naming; record the result in the glossary.
  • The task is to write or shape a PRD — use hai-prd. This skill can polish its wording later.

Common mistakes

  • Applying the rules to marketing copy and making it flat.
  • Turning every unmeasured claim into an inline "[TBD]": the document becomes a checklist of gaps. Report the gaps to the author; keep the document readable.
  • Putting a guessed value in a placeholder, or writing a plausible number.
  • Removing a caveat or a risk because the sentence got shorter without it.
  • Changing a correct technical term to obey 1.4 or 9.4.
  • Reporting every soft-rule hit of the script as a defect.

© Genshin-bots, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/human-talk of Genshin-bots/gsuid_core.

Open the folder on GitHubat commit 9a6a264

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in Genshin-bots/gsuid_core, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Hai Simplified Technical 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.

Hai Simplified Technical compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hai Simplified Technical this skillGenshin-bots/gsuid_core3561 repos~2.5kAutomated safety check: PassGPL-3.0
Diagram Designcathrynlavery/diagram-design48k1 repos~7.6kAutomated safety check: PassMIT
Simple Englishmoeru-ai/airi50k2 repos~4.6kAutomated safety check: PassMIT
Doc SyncJetBrains/ideavim10k2 repos~2.6kAutomated safety check: PassMIT
Mailspring App ScreenshotsFoundry376/Mailspring18k—~1.5kAutomated safety check: PassGPL-3.0
Draw.io Diagram StudioAgents365-ai/drawio-skill10k—~2.4kAutomated safety check: NotesMIT

Similar skills

  • Diagram Design

    cathrynlavery/diagram-design

    Creates branded diagrams, from architecture, flowchart and sequence to charts and maps, as self-contained HTML with inline SVG, with import from draw.io, Mermaid and Excalidraw.

    48k GitHub starsUsed in 1 repo~7.6k tokens
    DevelopmentAuto-check passed
  • Simple English

    moeru-ai/airi

    Write or rewrite technical text with the rules of ASD-STE100 Simplified Technical English so it is clear, unambiguous, and free of AI slop.

    50k GitHub starsUsed in 2 repos~4.6k tokens
    DevelopmentAuto-check passed
  • Doc Sync

    JetBrains/ideavim

    Official

    Keeps IdeaVim documentation in sync with code changes. An agent skill from JetBrains/ideavim.

    10k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Mailspring App Screenshots

    Foundry376/Mailspring

    Captures screenshots of the running Mailspring dev app for docs, PRs or visual checks by launching it with a debugging port, driving the UI and clipping to an element.

    18k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Draw.io Diagram Studio

    Agents365-ai/drawio-skill

    Creates and edits editable draw.io diagrams from descriptions, code, infrastructure files, SQL and API schemas, with sync, review, test and export tools.

    10k GitHub stars~2.4k tokensUpdated 7 days ago
    DevelopmentAuto-check: notes
  • Dark Architecture Diagram Builder

    Cocoon-AI/architecture-diagram-generator

    Creates dark-themed system, cloud, security and network architecture diagrams as self-contained HTML files with inline SVG and CSS.

    7.4k GitHub starsUsed in 1 repo~2.1k tokens
    DevelopmentAuto-check passed

More from Genshin-bots/gsuid_core

  • Test Audit

    Genshin-bots/gsuid_core

    Invoke whenever writing, changing, reviewing, or sweeping tests.

    356 GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Gscore Plugin Development

    Genshin-bots/gsuid_core

    当用户要求"帮我写一个 GsCore 插件"、"给这个插件加功能"、"改造触发器支持 AI"、 "怎么用 toai"、"注册 aitools"、"写一个游戏查询插件"、"插件帮助怎么注册"、 "能力代理/代理画像"、"怎么为触发器添加AI功能"、"几个触发器的差别在哪"、"数据库和配置项怎么添加" "如何把数据库表挂到网页控制台"、"PIL/pytakumi/playwright…

    356 GitHub stars~3.1k tokensUpdated today
    Auto-check passed

Categories

Questions about Hai Simplified Technical

What does Hai Simplified Technical do?

Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague…. Hai Simplified Technical is an agent skill from Genshin-bots/gsuid_core. Writes, rewrites and reviews technical documentation in Simplified Technical English (ASD-STE100) or its Chinese adaptation (简化技术中文): one word per concept, short sentences, named actors, no vague words or hidden verbs, imperative steps with the condition first, warnings before the step.

When should I use Hai Simplified Technical?

Hai Simplified Technical fits situations like: migration guides; commit and PR text; code comments and error messages; controlled language.

How do I install Hai Simplified Technical in Claude Code?

Run `npx skills add Genshin-bots/gsuid_core --skill hai-simplified-technical -a claude-code`. Or copy the skill folder (.agents/skills/human-talk in Genshin-bots/gsuid_core) into .claude/skills/hai-simplified-technical in your project. Claude Code loads it when a task matches its description.

How do I install Hai Simplified Technical in Codex?

Run `npx skills add Genshin-bots/gsuid_core --skill hai-simplified-technical -a codex`. Or copy the skill folder (.agents/skills/human-talk in Genshin-bots/gsuid_core) into .agents/skills/hai-simplified-technical in your project. Codex loads it when a task matches its description.

Can I use Hai Simplified Technical 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 Genshin-bots/gsuid_core --skill hai-simplified-technical -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hai-simplified-technical, .gemini/skills/hai-simplified-technical, .github/skills/hai-simplified-technical and .opencode/skills/hai-simplified-technical in your project.

What does Hai Simplified Technical need to run?

Going by SKILL.md and its folder, Hai Simplified Technical needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Hai Simplified Technical access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hai Simplified Technical 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. Review the folder before installing.

What licence does Hai Simplified Technical use?

Hai Simplified Technical is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Hai Simplified Technical use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 Hai Simplified Technical?

Skills that share tags, products or a category with Hai Simplified Technical: Diagram Design (cathrynlavery/diagram-design, 48k stars), Simple English (moeru-ai/airi, 50k stars), Doc Sync (JetBrains/ideavim, 10k stars) and Mailspring App Screenshots (Foundry376/Mailspring, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hai Simplified Technical?

Genshin-bots (a GitHub organization) maintains it in Genshin-bots/gsuid_core, which has 356 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.

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