Translation Diff Export
Devolutions/UniGetUI
Compares UniGetUI JSON locale files against English, identifies untranslated or source-changed keys, and generates patch, reference, and handoff files for a target language.
Agent skill
Visual Memory Translator
by TanShilongMario in TanShilongMario/visual-memory-translator-SKILL
Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card.
Install Visual Memory Translator
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .claude/skills && cp -r skills-src/visual-memory-translator .claude/skills/visual-memory-translator && rm -rf skills-srcUse ~/.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/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .claude/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translatorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .agents/skills && cp -r skills-src/visual-memory-translator .agents/skills/visual-memory-translator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .agents/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/visual-memory-translator .cursor/skills/visual-memory-translator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .cursor/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/TanShilongMario/visual-memory-translator-SKILL.git --path visual-memory-translator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/visual-memory-translator .gemini/skills/visual-memory-translator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .gemini/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .github/skills && cp -r skills-src/visual-memory-translator .github/skills/visual-memory-translator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .github/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install TanShilongMario/visual-memory-translator-SKILL visual-memory-translator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/TanShilongMario/visual-memory-translator-SKILL.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/visual-memory-translator .opencode/skills/visual-memory-translator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "visual-memory-translator" agent skill from https://github.com/TanShilongMario/visual-memory-translator-SKILL/tree/main/visual-memory-translator into .opencode/skills/visual-memory-translator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "visual-memory-translator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
visual-memory-translator- GitHub stars
- 189
- Token cost
- ~2.2k tokens
- SKILL.md length
- 429 words
- Files
- 14 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card.
- Works in 7 steps: Reality as evidence — 原图是现实证据 → Translation as memory — 转译承担记忆 / 情绪 / 残影 → Less, but precise — 元素少，但每个都有理由 → …
- The user invokes 影像转译
- SKILL.md covers When to use, Core philosophy, Global aesthetic (always on) and Workflow, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Visual Memory Translator is an agent skill from TanShilongMario/visual-memory-translator-SKILL. Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card. Not a filter, style-transfer, quote-on-photo template, or full portrait redraw. Analyzes what should survive, selects display/layout/style, and builds image prompts with high whitespace and controlled abstraction. When a photo is given and no style is named, first creates a 4/6/9-panel style-preview contact sheet, then regenerates the chosen direction from the original…
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including reference files (for example `examples.md`, `references/banknote.md` and `references/central-stamp.md`).
It sits in Writing & Content, covering Translation. The repository describes itself as: visual-memory-translator-SKILL. The licence is MIT.
When your agent uses it
- The user invokes 影像转译
- Visual Memory Translator
- Editorial photo reinterpretation
- A concept/quote visual card
Example prompts
- “Use the visual-memory-translator skill to reinterpret photos into editorial, artist-book memory pages, and can also translate a sentence or concept…”
- “/visual-memory-translator”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Reality as evidence — 原图是现实证据
- Translation as memory — 转译承担记忆 / 情绪 / 残影
- Less, but precise — 元素少，但每个都有理由
- Whitespace is content — 留白是作品本身
- Editorial before decorative — 版式优先于装饰
- Interpret, do not trace — 概括重组，禁止机械临摹
- Style may change, aesthetic discipline must not — 风格可变，极简克制不变
What it can do on your machine
Read from SKILL.md and the folder at commit 98a18ef. 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 (its code samples are yaml).
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
Visual Memory Translator loads about 2.2k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 246 tokens; SKILL.md has 429 words of instructions outside code blocks.
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 TanShilongMario/visual-memory-translator-SKILL at commit 98a18ef, republished under its MIT licence (© TanShilongMario). 429 words, ~2,154 tokens.
Download SKILL.mdSave it as
.claude/skills/visual-memory-translator/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.- name
- visual-memory-translator
- description
- Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card. Not a filter, style-transfer, quote-on-photo template, or full portrait redraw. Analyzes what should survive, selects display/layout/style, and builds image prompts with high whitespace and controlled abstraction. When a photo is given and no style is named, first creates a 4/6/9-panel style-preview contact sheet, then regenerates the chosen direction from the original photo. Includes layered white-border stickers and rounded bold-monoline blocks. Use when the user invokes 影像转译, Visual Memory Translator, 视觉记忆转译, 文本转译, editorial photo reinterpretation, a concept/quote visual card, a holiday-limited editorial overlay, 纸币样张, 纸币实景, 中央邮票, 黑胶唱片实景, or asks to turn a photo into a memory page. Around Qixi, Christmas, and other CN/JP/US holidays (±1 day), may add a sparse seasonal motif unless the user opts out.
Visual Memory Translator / 影像转译编辑器
Version: 1.5.0 Core principle: 原图是现实记录，新图是记忆转译。无图时，句子是概念，画面是隐喻。
将用户照片转译为具有当代编辑设计、艺术出版、视觉手札气质的二次创作图。
不是：滤镜、风格迁移、普通拼贴、把照片完整重画成肖像、金句叠照片。
是：理解输入 → 决定该留下什么 → 重构版式与隐喻 → 留白 → 输出新作品。照片走记忆转译；句子走概念转译。
When to use
- 用户说：启用影像转译 / 纸币样张 / 纸币实景 / 中央邮票 / 黑胶唱片实景 /
@VisualMemoryTranslator//visual-memory-translator - 用户上传照片并要求做成艺术出版页、记忆页、展览票、邮票记忆等编辑设计感图像
- 用户只给一句文案、金句、概念，要求做成编辑感视觉卡 / 文本转译
- 用户指定自选模板（纸币样张、纸币实景、中央邮票、黑胶唱片实景等）：跳过预览，直达对应构图
- 需要输出：视觉 prompt + 图像生成/编辑指令
Input routing
| 输入 | 路径 |
|---|---|
| 有参考图 | input_mode: photo — 影像记忆转译（主路径） |
| 无图，只有句子/概念/标题 | input_mode: text — 文本隐喻转译，不要先追问必须上传图片 |
| 图 + 指定文案 | input_mode: mixed — 图走记忆转译，文案作画面文字，不另发明金句 |
无图且也没有可转译的句子时，再要求上传图片或给出句子。
Core philosophy
- Reality as evidence — 原图是现实证据
- Translation as memory — 转译承担记忆 / 情绪 / 残影
- Less, but precise — 元素少，但每个都有理由
- Whitespace is content — 留白是作品本身
- Editorial before decorative — 版式优先于装饰
- Interpret, do not trace — 概括重组，禁止机械临摹
- Style may change, aesthetic discipline must not — 风格可变，极简克制不变
最终应像：有人记住这一刻，编辑了记忆，并设计成一页。
不应像：AI 又生成了这张照片的另一个版本。
Global aesthetic (always on)
要有：极简、克制、安静、呼吸感、大留白、非对称优先、焦点明确、艺术出版 / Editorial / Artist Book 气质、主题色统一。
避免：电商/旅游宣传、模板拼贴、满堂元素、花哨贴纸边框、大量文字、鸡汤、过度复古做旧、廉价手账、转译铺满、逐元素复制原图、无故堆无关物体、金句叠夜景、完整肖像重画。
默认背景：暖米白艺术纸、低纹理、无做旧。
Workflow
Copy and track:
- [ ] 1. 判定 input_mode：photo / text / mixed
- [ ] 2. 读取用户参数；检测日期是否落在节日 ±1 天
- [ ] 3. photo 路径判断是否需要风格预览
- [ ] 4. photo 且未指定风格：先生成一张 4/6/9 格预览图并等待选择
- [ ] 5. text 路径：提炼一个隐喻，默认直出编辑卡（见 text-visual.md）
- [ ] 6. 决定 DISPLAY / LAYOUT / STYLE / 抽象度 / 节日层
- [ ] 7. 构造成品 prompt（photo 必须从原始照片重建）
- [ ] 8. 用质量清单自检；失败则按 recovery 修正重试Interaction
- 读取明确参数 → 分析输入；能合理默认则不追问。
- photo 且未指定
style_mode：默认生成一张 6 格（2×3）预览图，而不是直接出成品。 - 用户可要求 4 格（2×2）或 9 格（3×3）；未说数量时用 6 格。
- 预览图内只标
01–09，不把风格名与长说明塞进图里；在回复中逐号列出风格名和一句适配理由。 - 用户回复编号后，必须基于原始照片重新生成高清成品；不得裁切、放大或二次编辑宫格中的低清单格。
- 支持「再换一组」和「融合 02 和 05」；融合时先说明主风格与被吸收的特征，然后从原图生成。
- 用户明确说「跳过预览 / 直接出最终图」或已指定自选模板时，直达成品。只说「纸币」而未点名时，按当次需求选样张或实景。纸币规范见 banknote.md；中央邮票见 central-stamp.md；黑胶唱片见 vinyl-record.md。
- 用户说「先别生成」时，不生成图；最多用文字给 3 个方向。
- text 路径默认
preview_mode: skip。只有用户说「先给我几个方向」时，才出最多 4 个差异明显的隐喻方案（可文字，或 2×2 宫格）。 - 节日限定：用对话当天日期，窗口 ±1 天。默认
holiday_mode: auto（窗口内启用）；用户说「不用节日限定」则 skip。不得为过节而给单人照补出伴侣。
宫格规则见 references/style-preview.md。
文本转译见 references/text-visual.md。
节日层见 references/holidays.md。
Decision priority
- 用户最新明确指令
- 明确视觉用途（封面 / Story / 海报等）
- 用户指定的 Style / Layout / Display
- 原图客观结构
- Skill 默认规则
Named template routing
| 用户说法 | style_mode | 核心关系 |
|---|---|---|
| 纸币样张 / 纪念钞样张 | banknote_specimen | 上方摄影，下方平放纪念券 |
| 纸币实景 / 手持纪念钞 | banknote_in_situ | 上方摄影，下方同场景手持纪念券 |
| 中央邮票 / 原位邮票 | central_in_place_stamp | 同一底图中央区域只改变媒介，不改变内容坐标 |
| 黑胶唱片 / 唱片店实景 | vinyl_record_in_situ | 上方正方形摄影，下方唱片店中的专辑实景 |
| 抽象色块 / 上下色块转译 | memory_color_blocks | 上方摄影，下方高概括色块 |
| 展览票 | exhibition_ticket | 摄影事实被编辑成收藏级票据 |
点名模板不是“风格预览候选”，而是明确创作指令。模板不得机械复用上一次生成的标题、编号、场景、媒介或构图。
Image analysis (internal)
无需逐项汇报，除非用户要求：
- Subject：核心/次要主体、人物、建筑、自然、食物、标志物
- Composition：视觉中心、视线/运动方向、景深、几何、可裁切区；判断主体 / 中景 / 远景是否可干净剥离
- Emotion：宁静/松弛/孤独/烟火气等
- Color：提取 3–6 主题色；可降饱和、合并；禁止无关彩虹堆色
Prompt construction order
- 基于输入图的二次创作
- 整体设计概念
ORIGINAL_DISPLAY_MODELAYOUT_MODE- 原图裁切/保留方式
- 转译逻辑
STYLE_MODEABSTRACTION_LEVEL- 色彩来源
- 留白与 translation scale
- 人物规则（若有）
- 文字
- 微图形（默认 1–3）
- 节日薄层（若窗口命中且未 skip）
- 背景材质
- 比例
- 禁止项
Show full SKILL.md (155 more words)Show less
Strong defaults (override only with reason)
preset: default_editorial_memory
input_mode: auto # photo | text | mixed
preview_mode: auto # photo 未指定风格时先预览；text 默认 skip
preview_count: 6 # 4 | 6 | 9
original_display_mode: split_top_bottom # 或按图类型改，见 references
layout_mode: split_editorial
style_mode: auto # photo 先预览；text 默认 editorial_metaphor_card
abstraction_level: high # 保留约 15–30% 信息
whitespace_level: very_high
translation_scale: one_ninth_grid # 大留白时转译约占一格 / 15–30% 面积
text_mode: auto_poetic # 8–20 字，不解释、不鸡汤
doodle_level: very_low
holiday_mode: auto # auto | force | skip；窗口 ±1 天
background_style: warm_off_white_paper
transition: deckled_paper_edge
ratio: 3:4按图类型调整默认：自拍/人像 → taped_corner_photo，且转译禁止完整肖像；建筑 → 结构解构；极简几何 → extreme_minimal_abstraction；用户强调全新作品 → translation_only。完整规则见 references/defaults-and-presets.md。
Human / original / safety (hard rules)
- 人物：保留姿态动作发型服装结构；简化五官与纹理；不得擅自改动作、加人、加道具、儿童化。
- 禁止完整肖像画：人像转译不得变成可单独当肖像作品的写实水彩/线稿；五官最多 1–3 个记号。例外：
banknote_specimen/banknote_in_situ允许凹版雕线肖像，仍禁止照片级脸。 - 原图出现在画面中时：可裁切缩放重组；不得改天气/人物/建筑/地貌（除非用户要求）。
- 分层贴纸必须是 2–3 张可分离的白边贴纸，不得融成一张异形大贴纸。
- 节日限定不得为过节而加人、改成情侣或改节日装；单人照只用低强度符号。
- 不虚构未提供的地点、日期、票号、经纬度、真实机构标识；概念编号可用
NO. 001。
节日层不代表照片拍摄于该日，禁止把「今天」写进伪造日期章。
Parameter cheat sheet
| 维度 | 常用值 | 详情 |
|---|---|---|
| Input | photo, text, mixed | text-visual.md |
| Display | split_top_bottom, taped_corner_photo, translation_only, … | display-and-layout.md |
| Layout | split_editorial, large_whitespace_small_art, … | 同上 |
| Style | banknote_specimen, central_in_place_stamp, vinyl_record_in_situ, … | styles.md |
| Preview | auto / skip; 4 / 6 / 9 格 | style-preview.md |
| Holiday | auto / force / skip；±1 天 | holidays.md |
| Abstraction | low / medium / high / extreme | systems.md |
| Text | none, user_text, auto_poetic, … | 同上 |
| Full schema | YAML | parameters.md |
智能预设：travel_journal, personal_memory, one_day_exhibition, postcard_memory, through_glass, pure_memory, layered_sticker_memory, rounded_monoline_memory, editorial_text_card, banknote_specimen, banknote_in_situ, central_in_place_stamp, vinyl_record_in_situ → defaults-and-presets.md。
调用示例 → examples.md。
文本转译 → text-visual.md。
节日限定 → holidays.md。
纪念纸币 → banknote.md。
中央原位邮票 → central-stamp.md。
黑胶唱片实景 → vinyl-record.md。
质量清单与失败修正 → quality.md。
Minimal invocation
/visual-memory-translator
启用影像转译编辑器
@VisualMemoryTranslator无其他参数且未指定风格时，先走 6 格风格预览。YAML 调用示例：
skill: visual_memory_translator
original_display_mode: taped_corner_photo
style_mode: extreme_minimal_abstraction
abstraction_level: extreme
text_mode: none
ratio: 3:4Final instruction
Do not treat the reference image as mere style-transfer fodder.
Decide what deserves to survive, what should disappear, and whether the original remains visible—then reconstruct through editorial composition and controlled abstraction.
不是把照片重新画一遍，而是决定这张照片最终应该留下什么。
不是把句子画成故事，而是决定这句话只需要一个隐喻。
© TanShilongMario, 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 13 other files (references) in visual-memory-translator of TanShilongMario/visual-memory-translator-SKILL.
- SKILL.md
- examples.md
- references/banknote.md
- references/central-stamp.md
- references/defaults-and-presets.md
- references/display-and-layout.md
- references/holidays.md
- references/parameters.md
- references/quality.md
- references/style-preview.md
- references/styles.md
- references/systems.md
- references/text-visual.md
- references/vinyl-record.md
Open the folder on GitHubat commit 98a18ef
Compare with similar skills
Visual Memory Translator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Visual Memory Translator this skillTanShilongMario/visual-memory-translator-SKILL | 189 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Translation Diff ExportDevolutions/UniGetUI | 26k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Sync Translationssymfony/symfony | 31k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Translation Diff ImportDevolutions/UniGetUI | 26k | — | ~750 | Automated safety check: Pass | MIT | |
| Translation Diff TranslateDevolutions/UniGetUI | 26k | — | ~934 | Automated safety check: Pass | MIT | |
| Generate Translationspayloadcms/payload | 45k | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Sync Translations
symfony/symfony
Synchronize translation catalogs across maintained Symfony branches: find messages that newer branches added to the English catalogs but that are still missing from the oldest maintained branch…
Translation Diff Import
Devolutions/UniGetUI
Merges translated key-value pairs from a UniGetUI JSON localization patch back into the full language file and validates the merged result.
Translation Diff Translate
Devolutions/UniGetUI
Translates a sparse UniGetUI JSON language patch, writes completed entries into the working copy, preserves placeholders and terminology, and prepares the patch for merge-back.
Generate Translations
payloadcms/payload
A skill your agent uses when new translation keys are added to packages to generate new translations strings
InkOS Creative Harness
Narcooo/inkos
Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.
Related
Categories
Questions about Visual Memory Translator
What does Visual Memory Translator do?
Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card. Visual Memory Translator is an agent skill from TanShilongMario/visual-memory-translator-SKILL. Reinterprets photos into editorial, artist-book memory pages, and can also translate a sentence or concept into a sparse editorial metaphor card.
When should I use Visual Memory Translator?
Visual Memory Translator fits situations like: the user invokes 影像转译; visual Memory Translator; editorial photo reinterpretation; A concept/quote visual card.
How do I install Visual Memory Translator in Claude Code?
Run `npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a claude-code`. Or copy the skill folder (visual-memory-translator in TanShilongMario/visual-memory-translator-SKILL) into .claude/skills/visual-memory-translator in your project. Claude Code loads it when a task matches its description.
How do I install Visual Memory Translator in Codex?
Run `npx skills add TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a codex`. Or copy the skill folder (visual-memory-translator in TanShilongMario/visual-memory-translator-SKILL) into .agents/skills/visual-memory-translator in your project. Codex loads it when a task matches its description.
Can I use Visual Memory Translator 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 TanShilongMario/visual-memory-translator-SKILL --skill visual-memory-translator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/visual-memory-translator, .gemini/skills/visual-memory-translator, .github/skills/visual-memory-translator and .opencode/skills/visual-memory-translator in your project.
What does Visual Memory Translator need to run?
SKILL.md names no scripts, command-line tools or credentials: Visual Memory Translator is instructions for the agent only.
Does Visual Memory Translator 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 Visual Memory Translator 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 Visual Memory Translator use?
Visual Memory Translator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Visual Memory Translator use?
About 2.2k tokens (SKILL.md is roughly 8.6k 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 14k tokens, read only when the agent opens those files.
What are the alternatives to Visual Memory Translator?
Skills that share tags, products or a category with Visual Memory Translator: Translation Diff Export (Devolutions/UniGetUI, 26k stars), Sync Translations (symfony/symfony, 31k stars), Translation Diff Import (Devolutions/UniGetUI, 26k stars) and Translation Diff Translate (Devolutions/UniGetUI, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Visual Memory Translator?
TanShilongMario (a GitHub user) maintains it in TanShilongMario/visual-memory-translator-SKILL, which has 189 GitHub stars. The repository was last updated on August 27, 2026.
Source: TanShilongMario/visual-memory-translator-SKILL on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.