agentleFS
Sign inStart free
Sophon-KrSophon-Kr/thai-native/skills/thai-translate/SKILL.md

thai-translate

Skill0 starsChanged 22 days agoMITView on GitHub

Translate English (or another language) into natural Thai for a specific reader. Plans the meaning first, follows the team's tech-term policy, then checks accuracy against the source. Pass a file path or text, optionally with who will read it.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. Boom-Vitt/claude-thai-skills★ 58same name
    2. ntaffzii/Skill-Agents★ 4same name
    3. Aether-GenesiZ/thai-agent-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check: … lint --genre <genre> --file <draft> and … check-source --source <source> --target <draft> (numbers, code, links, placeholders, …

    line 19

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

thai-translate

Source: $ARGUMENTS

Script: python3 "${CLAUDE_SKILL_DIR}/../thai-writing/scripts/thai_native.py"

  1. Load the thai-writing skill if it is not loaded yet, then run … prep --file <source> (or pass the text) before drafting. It prints translate.core (steps and meaning traps from ../thai-writing/references/translation.md), the policy of every tech term in the source, and a card for each English construction in it that tends to come out as translationese (, which, passives, make sure…). Read the full translation.md when the source has constructions without a card or you are unsure.
  2. Purpose first: who reads the Thai version, through which channel, and what they should do after reading. Infer from the arguments and the text type (UI strings, release notes, README, email, contract). That decides register, pronouns, particles and how much English stays.
  3. Terms: use the policies prep printed (… terms "<text>" for anything else). Code, commands, product names, UI paths that stay English in the app, and placeholders like {name} stay untouched.
  4. Translate by meaning units, not sentence by sentence: plan who does what and why, turn English noun phrases back into Thai verbs, then write the Thai.
  5. Check: … lint --genre <genre> --file <draft> and … check-source --source <source> --target <draft> (numbers, code, links, placeholders, negation, must/should/might, terms; pasted source: save it to a temp file first). Fix the real issues; info is a judgment call.
  6. Over ~150 words or for external readers, one refinement pass: … compare --snapshot <draft>, revise only the flagged spans (at most 2 per paragraph, source side by side, add or drop nothing), then … compare --revised <draft> --source <source> --merged <draft>. That restores every paragraph marked revert; recheck review ones against the source. Do not loop.
  7. Output: for a file, write <name>.th.<ext> next to the source unless told otherwise. For text, return the translation. Add a note only for real decisions (an ambiguous source sentence, a term kept in English on purpose).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free