New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Dongbei Voice

by yuema137 in yuema137/DongbeiGPT

Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation.

MITAuto-check passed

Install Dongbei Voice

skills CLI
$ npx skills add yuema137/DongbeiGPT --skill dongbei-voice -a claude-code

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

GitHub CLI
$ gh skill install yuema137/DongbeiGPT dongbei-voice --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/yuema137/DongbeiGPT.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dongbei-voice .claude/skills/dongbei-voice && 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
dongbei-voice
GitHub stars
100
Token cost
~849 tokens
SKILL.md length
422 words
Files
4 (incl. references)
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation.

  • The user requests 东北大白话
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Do not use for dialect performance
  • Obscure regional vocabulary

What it does

Dongbei Voice is an agent skill from yuema137/DongbeiGPT. Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation. Use when the user requests 东北大白话 or Dongbei voice; do not use for dialect performance, comedy, or obscure regional vocabulary.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/dialect-guide.md`, `references/excluded-expressions.md` and `references/expression-boundaries.md`).

The repository describes itself as: Explain tech and coding problems in clear, plan language. The licence is MIT.

When your agent uses it

  • The user requests 东北大白话
  • Do not use for dialect performance
  • Obscure regional vocabulary

Example prompts

  • “/dongbei-voice”

What it can do on your machine

Read from SKILL.md and the folder at commit 3f72262. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Dongbei Voice loads about 849 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 65 tokens; SKILL.md has 422 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~65
When it runs · the whole SKILL.md, loaded when a task matches
~849
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.4k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from yuema137/DongbeiGPT at commit 3f72262, republished under its MIT licence (© yuema137). 422 words, ~849 tokens.

Download SKILL.mdSave it as .claude/skills/dongbei-voice/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
dongbei-voice
description
Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation. Use when the user requests 东北大白话 or Dongbei voice; do not use for dialect performance, comedy, or obscure regional vocabulary.
license
MIT

Dongbei Voice

Keep the text mostly Standard Mandarin. Reconstruct it as a competent peer talking through the mechanism: begin from the reader's likely confusion, establish one graspable mental model, then map every informal phrase back to the real component. Add direct questions, short causal turns, concrete verbs, and explicit emphasis. The goal is clarity, not dialect density.

Work only after the technical content is sound. Do not add, remove, or soften technical claims. This is not a search-and-replace pass over an already formal paragraph. Reorder sentences when necessary so the reader encounters the problem, changed action, example, formal term, and boundary in that order.

For project-internal PRs and issues, do not assume the reader knows the project's nouns. Before using an internal label such as composition projection, sidecar, or Gate 2, say what concrete job it performs in this case. If three internal labels arrive before the reader can picture one action, restart with a small scenario.

When a compact structural analogy genuinely lowers the entry cost, use it for one or two sentences, immediately bind its parts to the actual system, and then continue with the technical mechanism. A useful analogy is a temporary ramp, not the explanation itself.

Useful moves include “先看它到底干了啥”, “原来…现在…”, “为啥”, “真正卡住的是…”, and occasional “说白了”. Vary naturally; they are not required catchphrases. Use 咋, 啥, or 整 sparingly, and never use 整 where a precise verb such as “复制、调度、缓存、提交” is clearer.

Avoid Chinese em dashes (——). They make the answer read like edited prose rather than somebody talking. Put the clarification in its own short sentence or introduce it directly with “就是”, “这里指”, or a colon.

Show full SKILL.md (152 more words)Show less

Avoid phonetic misspellings, comedy, fake relatives, 老铁, 嘎嘎, 嘎哈, expressions marked “排除” in the calibrated boundary, dialect in every sentence, and any phrasing that talks down to the reader. Expressions marked “能懂但有地域标记”, including 咱就是说 and 你寻思, are not default choices: use them only when they add real discourse value without creating performance.

Treat comedy, interview, and other performance corpora as evidence about discourse structure only. Frequency in a corpus never promotes an expression. The product owner's calibrated boundary remains authoritative, including when a source repeatedly uses a prohibited, risky, insulting, or pronunciation-marked form.

For the product owner's calibrated expression boundary, read references/expression-boundaries.md. For evidence and serious-context restrictions, read references/dialect-guide.md. For explicit rejections, read references/excluded-expressions.md. When using performance-derived rhythm, consult the distilled corpus notes without loading or imitating source transcripts.

Final check: could a technically curious Mandarin speaker outside Northeast China read it immediately? If not, replace the dialect marker with Standard Mandarin.

© yuema137, MIT. 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 (references) in skills/dongbei-voice of yuema137/DongbeiGPT.

  • SKILL.md
  • references/dialect-guide.md
  • references/excluded-expressions.md
  • references/expression-boundaries.md

Open the folder on GitHubat commit 3f72262

Compare with similar skills

Dongbei Voice 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.

Dongbei Voice compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dongbei Voice this skillyuema137/DongbeiGPT100—~849Automated safety check: PassMIT
Modeling Conversion MetricsPostHog/posthog40k—~1.4kAutomated safety check: PassCustom licence
Humanize Chinesesickn33/agentic-awesome-skills47k2 repos~1.3kAutomated safety check: PassMIT
Chinese Indie Dev1c7/chinese-independent-developer62k—~8.7kAutomated safety check: PassNone
Cost Conversationruvnet/ruflo74k—~407Automated safety check: NotesMIT
Video Understandcalesthio/OpenMontage66k—~841Automated safety check: PassAGPL-3.0

Similar skills

  • Modeling Conversion Metrics

    PostHog/posthog

    Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated yesterday
    Data & AnalyticsAuto-check passed

  • Humanize Chinese

    sickn33/agentic-awesome-skills

    Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    Writing & ContentAuto-check passed

  • Chinese Indie Dev

    1c7/chinese-independent-developer

    处理 1c7/chinese-independent-developer 仓库的项目提交. An agent skill from 1c7/chinese-independent-developer.

    62k GitHub stars~8.7k tokensUpdated today
    DevelopmentAuto-check passed

  • Cost Conversation

    ruvnet/ruflo

    Per-conversation cost view — list every session in cost-tracking with started-at, message count, top model, and total cost

    74k GitHub stars~407 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • Conversation Memory

    davila7/claude-code-templates

    Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

    33k GitHub starsUsed in 4 repos~440 tokens
    Agent WorkflowsAuto-check passed

More from yuema137/DongbeiGPT

  • Concrete Example

    yuema137/DongbeiGPT

    Add a small worked technical example, before/after trace, diagram, or structure-preserving analogy to an explanation.

    100 GitHub stars~329 tokensUpdated 1 mo ago
    Auto-check passed

  • Clear Tech Explainer

    yuema137/DongbeiGPT

    Explain technical concepts in Chinese through concrete causal structure, before/after mechanisms, boundaries, and trade-offs.

    100 GitHub stars~581 tokensUpdated 1 mo ago
    Auto-check passed

  • Dongbei Explainer

    yuema137/DongbeiGPT

    Explain technical or otherwise complex material clearly in Chinese using causal structure, audience-aware terminology, a useful worked example, and restrained Northeastern conversational rhythm.

    100 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Plain Chinese

    yuema137/DongbeiGPT

    Rewrite or draft Chinese technical prose with fewer abstract noun piles, circular definitions, unexplained acronyms, and vague relationship claims.

    100 GitHub stars~633 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Dongbei Voice

What does Dongbei Voice do?

Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation. Dongbei Voice is an agent skill from yuema137/DongbeiGPT. Apply a restrained, widely understandable Northeastern-Chinese conversational rhythm to an existing Chinese explanation.

When should I use Dongbei Voice?

Dongbei Voice fits situations like: the user requests 东北大白话; do not use for dialect performance; obscure regional vocabulary.

How do I install Dongbei Voice in Claude Code?

Run `npx skills add yuema137/DongbeiGPT --skill dongbei-voice -a claude-code`. Or copy the skill folder (skills/dongbei-voice in yuema137/DongbeiGPT) into .claude/skills/dongbei-voice in your project. Claude Code loads it when a task matches its description.

How do I install Dongbei Voice in Codex?

Run `npx skills add yuema137/DongbeiGPT --skill dongbei-voice -a codex`. Or copy the skill folder (skills/dongbei-voice in yuema137/DongbeiGPT) into .agents/skills/dongbei-voice in your project. Codex loads it when a task matches its description.

Can I use Dongbei Voice 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 yuema137/DongbeiGPT --skill dongbei-voice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dongbei-voice, .gemini/skills/dongbei-voice, .github/skills/dongbei-voice and .opencode/skills/dongbei-voice in your project.

What does Dongbei Voice need to run?

SKILL.md names no scripts, command-line tools or credentials: Dongbei Voice is instructions for the agent only.

Does Dongbei Voice 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 Dongbei Voice 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 Dongbei Voice use?

Dongbei Voice is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dongbei Voice use?

About 849 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Dongbei Voice?

Skills that share tags, products or a category with Dongbei Voice: Modeling Conversion Metrics (PostHog/posthog, 40k stars), Humanize Chinese (sickn33/agentic-awesome-skills, 47k stars), Chinese Indie Dev (1c7/chinese-independent-developer, 62k stars) and Cost Conversation (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dongbei Voice?

yuema137 (a GitHub user) maintains it in yuema137/DongbeiGPT, which has 100 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on September 1, 2026.

Source: yuema137/DongbeiGPT on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.