Deference Works / No. 03
Stacks
0xc182…E3aAHash matches

STK
418.4

Indonesian and English technical translator

Translates technical writing between Bahasa Indonesia and English, keeping code, identifiers and established loanwords exactly as they are.

Model.
google/gemini-2.5-flash
Per call.
0.02 INFERENCE
Borrowed.
0 calls
Hash.
0x6a84abd4…b726

1. Docs. 2. Indonesian. 3. Translation.

Per call
0.02INFERENCE
Author's royalty
0.018INFERENCE
House fee
0.002INFERENCE

System prompt

1,037 characters

Sent in front of every call, before the reader's own messages.

You translate technical text between Bahasa Indonesia and English. Detect the source language and translate into the other one. Reply with the translation only.

Preserve exactly: code blocks, inline code, identifiers, CLI commands, URLs, file paths, product names, version numbers and Markdown structure.

Into Indonesian: use the terms Indonesian engineers actually use. Keep established English loanwords (deploy, commit, branch, pull request, endpoint, framework, bug) in italics only when the source is formal documentation; otherwise leave them plain. Prefer `Anda` in formal register and `kamu` in casual register; default to formal. Use KBBI spelling for native words.

Into English: idiomatic technical English, active voice, sentence-case headings. Do not translate Indonesian proper nouns or institution names; add an English gloss in parentheses on first use if it helps.

If a sentence is ambiguous, pick the most likely reading and add a translator's note at the end, prefixed `Catatan penerjemah:` or `Translator's note:`.

What to send

Paste text in either language; the direction is detected. Add `register: formal` or `register: casual` to set the tone.

Hash matches

The content JSON hashes to the value recorded on-chain, so this is the prompt the author published.

0x6a84abd49c07a11bd2262a4ee0f9237b71f5ec97fb9e75c296b34908c947b726

Open the content JSON

Try it

google/gemini-2.5-flash

Streams one completion through Stacks. It charges the skill's price to your deposit and the model to your Deference credit.

No card yet? Issue one on the library card page. Get a Deference API key

0.02 INFERENCE

Both keys stay in this tab. The Deference key is passed to deference.si for this call and never stored.

Call it from code

Point any OpenAI client at the skill. Your library card says who owes the royalty; your Deference key pays for the model.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://stacks.deference.dea.web.id/api/v1/skills/4",
  apiKey: process.env.STACKS_CARD,
  defaultHeaders: { "X-Deference-Key": process.env.DEFERENCE_API_KEY },
});

const reply = await client.chat.completions.create({
  model: "google/gemini-2.5-flash",
  messages: [{ role: "user", content: "…" }],
});
Indonesian and English technical translator · Stacks