Agent skill

Ok Script OCR Lang

by AliceJump in AliceJump/ok-end-field

Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings.

AGPL-3.0Auto-check passedFrontend & Design

Install Ok Script OCR Lang

skills CLI
$ npx skills add AliceJump/ok-end-field --skill ok-script-ocr-lang -a claude-code

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

GitHub CLI
$ gh skill install AliceJump/ok-end-field ok-script-ocr-lang --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/AliceJump/ok-end-field.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ok-script-ocr-lang .claude/skills/ok-script-ocr-lang && 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
ok-script-ocr-lang
GitHub stars
556
Token cost
~753 tokens
SKILL.md length
370 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings.

  • Works in 3 steps: Edit assets/lang/.json with a semantic… → Run uv run --locked python -m unittest… → Regenerate src/data/lang/_lang_typed.py…
  • Assets/lang modules
  • SKILL.md covers Matcher schema and locales, Add or change a key and OCR confusion map
  • Calls uv

What it does

Ok Script OCR Lang is an agent skill from AliceJump/ok-end-field. Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings. Use for assets/lang modules, active OCR locales, matcher references, or assets/ocrfix/ocrtextfix.json; GUI gettext belongs to ok-script-i18n.

Its SKILL.md is about 750 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 Frontend & Design, covering Internationalization. It works with Python. The repository describes itself as: 终末地 End Field Automation 基于ok-script开发的自动化. The licence is AGPL-3.0.

When your agent uses it

  • Assets/lang modules
  • Active OCR locales
  • Matcher references
  • Assets/ocrfix/ocrtextfix.json

Example prompts

  • “/ok-script-ocr-lang”

Requirements

  • Python 3

Workflow steps

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

  1. Edit assets/lang/.json with a semantic key (legacy k_* hash keys can remain). Supply both active OCR locales. Reference it as self.lang...
  2. Run uv run --locked python -m unittest tests.TestCheckLang -v. It checks code references in active locales and node shape, nonempty…
  3. Regenerate src/data/lang/_lang_typed.py with uv run --locked python scripts/i18n/gen_lang_stubs.py and inspect its diff.

What it can do on your machine

Read from SKILL.md and the folder at commit a8af4e8. 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:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

Ok Script OCR Lang loads about 753 tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 370 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~60
When it runs · the whole SKILL.md, loaded when a task matches
~753

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 AliceJump/ok-end-field at commit a8af4e8, republished under its AGPL-3.0 licence (© AliceJump). 370 words, ~753 tokens.

Download SKILL.mdSave it as .claude/skills/ok-script-ocr-lang/SKILL.md (or your agent's skills folder).
name
ok-script-ocr-lang
description
Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings. Use for assets/lang modules, active OCR locales, matcher references, or assets/ocr_fix/ocr_text_fix.json; GUI gettext belongs to ok-script-i18n.

OK Script OCR Language Resources

assets/lang/<module>.json supplies task OCR matchers and localized business data; assets/ocr_fix/ocr_text_fix.json extends matching for known OCR confusion. GUI text belongs to gettext ($ok-script-i18n). See docs/dev/i18n_OCR配置流程.md for the full project convention.

Matcher schema and locales

  • Runtime reads one file per module, not assets/lang/<module>/<locale>.json. A top-level business key contains locale nodes; each node has exactly one of {"string": "..."}, {"pattern": "..."}, or {"terms": [...]}. The accessor returns a string, compiled regex, or list respectively. Do not mix types in one node.
  • src/data/lang/__init__.py defines ACTIVE_LOCALES_CONFIG. Currently zh_CN and zh_TW are active for task OCR. Unknown or inactive locales normalize to zh_CN; a missing locale node falls back to zh_TW for Traditional Chinese, otherwise zh_CN, then the first available node.
  • Missing files or keys yield an empty module or None. First check exact module/key spelling and locale before changing matcher code.

Add or change a key

  1. Edit assets/lang/<module>.json with a semantic key (legacy k_* hash keys can remain). Supply both active OCR locales. Reference it as self.lang.<module>.<key>.
  2. Run uv run --locked python -m unittest tests.TestCheckLang -v. It checks code references in active locales and node shape, nonempty values, and regex syntax across all lang JSON nodes. Review the actual OCR region in a game window when behavior depends on visual matching.
  3. Regenerate src/data/lang/_lang_typed.py with uv run --locked python scripts/i18n/gen_lang_stubs.py and inspect its diff.
Show full SKILL.md (147 more words)Show less

Tracked full-locale business text belongs in assets/lang/; maintain the six core locales zh_CN, zh_TW, en_US, ja_JP, ko_KR, and es_ES, preserving extra locale nodes too. Structured canonical data belongs in assets/data/. Keep local generated files at their existing paths and preserve their ignored status; do not change ignore rules to commit them. When adding a data-only module, update DATA_ONLY_MODULES in the stub generator; task OCR modules stay in the generated accessor hints.

OCR confusion map

ocr_text_fix.json maps complete misread text to correct text. The patch uses only same-length pairs to derive character substitutions and extends the caller's match after the framework's regex fix. It does not normalize OCR output or change Box.name. Use language patterns or business parsing for length-changing and word-order errors. The old src/data/ocr_normalize_map.py is gone.

For a mismatch, confirm the runtime locale, key/node type, regex, search region, and generated hint before adding a confusion pair.

© AliceJump, AGPL-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/ok-script-ocr-lang of AliceJump/ok-end-field.

Open the folder on GitHubat commit a8af4e8

Compare with similar skills

Ok Script OCR Lang 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.

Ok Script OCR Lang compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ok Script OCR Lang this skillAliceJump/ok-end-field556—~753Automated safety check: PassAGPL-3.0
Claude Desktop Chinese Localizationjavaht/claude-desktop-zh-cn7.5k—~1.6kAutomated safety check: PassMIT
I18n Development4thfever/cultivation-world-simulator2.1k—~451Automated safety check: PassCustom licence
Fluent MigrationBrowserWorks/waterfox-android3791 repos~4.2kAutomated safety check: PassCustom licence
Ok Script I18nbaoxin1100/ok-kes100—~903Automated safety check: PassNone
I18nbrickbots/PiFinder250—~2.8kAutomated safety check: PassGPL-3.0

Similar skills

  • Claude Desktop Chinese Localization

    javaht/claude-desktop-zh-cn

    Adds missing Simplified and Traditional Chinese translations to the Claude Desktop Chinese patch across three layers, then checks how many mappings actually hit.

    7.5k GitHub stars~1.6k tokensUpdated 3 days ago
    Frontend & DesignAuto-check passed
  • I18n Development

    4thfever/cultivation-world-simulator

    国际化 (i18n) 开发指南。在添加新文本、创建物品/事件、修改翻译或管理 PO/MO 文件时使用. An agent skill from 4thfever/cultivation-world-simulator.

    2.1k GitHub stars~451 tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Fluent Migration

    BrowserWorks/waterfox-android

    A skill your agent uses when a patch or local changes rename, restructure, move, or replace Fluent (.ftl) strings - or migrate legacy .properties strings to Fluent - and you need a migration recipe…

    379 GitHub starsUsed in 1 repo~4.2k tokens
    Frontend & DesignAuto-check passed
  • Ok Script I18n

    baoxin1100/ok-kes

    Add, sync, repair, and compile gettext translations for ok-script Python task classes and task metadata.

    100 GitHub stars~903 tokensUpdated 7 days ago
    Frontend & DesignAuto-check passed
  • I18n

    brickbots/PiFinder

    PiFinder's internationalization (i18n) workflow — marking strings for translation, running the Babel extract/update/compile pipeline, adding or updating language translations, and filling in missing…

    250 GitHub stars~2.8k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Odoo 16

    unclecatvn/agent-skills

    Odoo 16 development reference for Python models and ORM (search, domain, readgroup, compute fields), XML/CSV data and views, OWL/JS client code, QWeb reports, security (ACL, record rules, groups)…

    143 GitHub stars~1.4k tokensUpdated 14 days ago
    Frontend & DesignAuto-check passed

More from AliceJump/ok-end-field

All 14 skills in this repo
  • Ok Script I18n

    AliceJump/ok-end-field

    Maintain gettext translations for ok-script task UI and runtime messages.

    556 GitHub stars~828 tokensUpdated today
    Auto-check passed
  • Deploy

    AliceJump/ok-end-field

    Commit validated changes, calculate an annotated stable/beta/alpha version tag, and push the release to the publishing remote.

    556 GitHub stars~625 tokensUpdated today
    Auto-check passed
  • GitHub Rulesets

    AliceJump/ok-end-field

    Diagnose or configure GitHub branch/tag rulesets on ok-script repos.

    556 GitHub stars~595 tokensUpdated today
    Auto-check passed
  • Use Local Venv

    AliceJump/ok-end-field

    Prefer the repository-local Python virtual environment for coding-agent work.

    556 GitHub stars~688 tokensUpdated today
    Auto-check passed
  • Ok Script PR Review

    AliceJump/ok-end-field

    Triage CodeRabbit reviews on ok-script pull requests. An agent skill from AliceJump/ok-end-field.

    556 GitHub stars~904 tokensUpdated today
    Auto-check passed
  • Ok Script Tasks

    AliceJump/ok-end-field

    Create, modify, register, or review ok-script BaseTask and TriggerTask classes.

    556 GitHub stars~619 tokensUpdated today
    Auto-check passed

Works with

Questions about Ok Script OCR Lang

What does Ok Script OCR Lang do?

Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings. Ok Script OCR Lang is an agent skill from AliceJump/ok-end-field. Maintain ok-end-field OCR matcher language JSON and OCR text-fix mappings.

When should I use Ok Script OCR Lang?

Ok Script OCR Lang fits situations like: assets/lang modules; active OCR locales; matcher references; assets/ocrfix/ocrtextfix.json.

How do I install Ok Script OCR Lang in Claude Code?

Run `npx skills add AliceJump/ok-end-field --skill ok-script-ocr-lang -a claude-code`. Or copy the skill folder (.agents/skills/ok-script-ocr-lang in AliceJump/ok-end-field) into .claude/skills/ok-script-ocr-lang in your project. Claude Code loads it when a task matches its description.

How do I install Ok Script OCR Lang in Codex?

Run `npx skills add AliceJump/ok-end-field --skill ok-script-ocr-lang -a codex`. Or copy the skill folder (.agents/skills/ok-script-ocr-lang in AliceJump/ok-end-field) into .agents/skills/ok-script-ocr-lang in your project. Codex loads it when a task matches its description.

Can I use Ok Script OCR Lang 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 AliceJump/ok-end-field --skill ok-script-ocr-lang -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ok-script-ocr-lang, .gemini/skills/ok-script-ocr-lang, .github/skills/ok-script-ocr-lang and .opencode/skills/ok-script-ocr-lang in your project.

What does Ok Script OCR Lang need to run?

Going by SKILL.md and its folder, Ok Script OCR Lang needs the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Ok Script OCR Lang access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ok Script OCR Lang 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 Ok Script OCR Lang use?

Ok Script OCR Lang is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ok Script OCR Lang use?

About 753 tokens (SKILL.md is roughly 3k 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 Ok Script OCR Lang?

Skills that share tags, products or a category with Ok Script OCR Lang: Claude Desktop Chinese Localization (javaht/claude-desktop-zh-cn, 7.5k stars), I18n Development (4thfever/cultivation-world-simulator, 2.1k stars), Fluent Migration (BrowserWorks/waterfox-android, 379 stars) and Ok Script I18n (baoxin1100/ok-kes, 100 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ok Script OCR Lang?

AliceJump (a GitHub user) maintains it in AliceJump/ok-end-field, which has 556 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 8, 2026.

Source: AliceJump/ok-end-field on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.