baoyu-translate

Name: baoyu-translate
Author: jimliu

byjimliu· 68 skills

Installs

23k

Stars

24k

Forks

2.7k

How to install baoyu-translate?

jimliu/baoyu-skills/baoyu-translate

$npx -y skills add jimliu/baoyu-skills --skill baoyu-translate

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-translate"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# Translator
2
3	Three-mode translation skill: quick for direct translation, normal for analysis-informed translation, refined for full publication-quality workflow with review and polish.
4
5	## User Input Tools
6
7	When this skill prompts the user, follow this tool-selection rule (priority order):
8
9	1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
10	2. Fallback: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
11	3. Batching: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.
12
13	Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
14
15	## Script Directory
16
17	Scripts in `scripts/` subdirectory. `{baseDir}` = this SKILL.md's directory path. Resolve `${BUN_X}` runtime: if `bun` installed → `bun`; if `npx` available → `npx -y bun`; else suggest installing bun. Replace `{baseDir}` and `${BUN_X}` with actual values.
18
19	\| Script \| Purpose \|
20	\|--------\|---------\|
21	\| `scripts/main.ts` \| CLI entry point. Default action splits markdown into chunks; also supports explicit `chunk` subcommand \|
22	\| `scripts/chunk.ts` \| Markdown chunking implementation used by `main.ts` and kept compatible for direct invocation \|
23
24	## Preferences (EXTEND.md)
25
26	Check EXTEND.md in priority order — the first one found wins:
27
28	\| Priority \| Path \| Scope \|
29	\|----------\|------\|-------\|
30	\| 1 \| `.baoyu-skills/baoyu-translate/EXTEND.md` \| Project \|
31	\| 2 \| `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-translate/EXTEND.md` \| XDG \|
32	\| 3 \| `$HOME/.baoyu-skills/baoyu-translate/EXTEND.md` \| User home \|
33
34	\| Result \| Action \|
35	\|--------\|--------\|
36	\| Found \| Read, parse, apply. On first use in session, briefly remind: "Using preferences from [path]. You can edit EXTEND.md to customize glossary, audience, etc." \|
37	\| Not found \| MUST run first-time setup (see below) — do NOT silently use defaults \|
38
39	EXTEND.md supports: default target language, default mode, target audience, custom glossaries (inline or file path), translation style, chunk settings.
40
41	Schema: [references/config/extend-schema.md](references/config/extend-schema.md).
42
43	### First-Time Setup (BLOCKING)
44
45	CRITICAL: When EXTEND.md is not found, you MUST run the first-time setup before ANY translation. This is a BLOCKING operation.
46
47	Full reference: [references/config/first-time-setup.md](references/config/first-time-setup.md)
48
49	Use `AskUserQuestion` with all questions (target language, mode, audience, style, save location) in ONE call. After user answers, create EXTEND.md at the chosen location, confirm "Preferences saved to [path]", then continue.
50
51	## Defaults
52
53	All configurable values in one place. EXTEND.md overrides these; CLI flags override EXTEND.md.
54
55	\| Setting \| Default \| EXTEND.md key \| CLI flag \| Description \|
56	\|---------\|---------\|---------------\|----------\|-------------\|
57	\| Target language \| `zh-CN` \| `target_language` \| `--to` \| Translation target language \|
58	\| Mode \| `normal` \| `default_mode` \| `--mode` \| Translation mode \|
59	\| Audience \| `general` \| `audience` \| `--audience` \| Target reader profile \|
60	\| Style \| `storytelling` \| `style` \| `--style` \| Translation style preference \|
61	\| Chunk threshold \| `4000` \| `chunk_threshold` \| — \| Word count to trigger chunked translation \|
62	\| Chunk max words \| `5000` \| `chunk_max_words` \| — \| Max words per chunk \|
63
64	## Modes
65
66	\| Mode \| Flag \| Steps \| When to Use \|
67	\|------\|------\|-------\|-------------\|
68	\| Quick \| `--mode quick` \| Translate \| Short texts, informal content, quick tasks \|
69	\| Normal \| `--mode normal` (default) \| Analyze → Translate \| Articles, blog posts, general content \|
70	\| Refined \| `--mode refined` \| Analyze → Translate → Review → Polish \| Publication-quality, important documents \|
71
72	Default mode: Normal (can be overridden in EXTEND.md `default_mode` setting).
73
74	Style presets — control the voice and tone of the translation (independent of audience):
75
76	\| Value \| Description \| Effect \|
77	\|-------\|-------------\|--------\|
78	\| `storytelling` \| Engaging narrative flow (default) \| Draws readers in, smooth transitions, vivid phrasing \|
79	\| `formal` \| Professional, structured \| Neutral tone, clear organization, no colloquialisms \|
80	\| `technical` \| Precise, documentation-style \| Concise, terminology-heavy, minimal embellishment \|
81	\| `literal` \| Close to original structure \| Minimal restructuring, preserves source sentence patterns \|
82	\| `academic` \| Scholarly, rigorous \| Formal register, complex clauses OK, citation-aware \|
83	\| `business` \| Concise, results-focused \| Action-oriented, executive-friendly, bullet-point mindset \|
84	\| `humorous` \| Preserves and adapts humor \| Witty, playful, recreates comedic effect in target language \|
85	\| `conversational` \| Casual, spoken-like \| Friendly, approachable, as if explaining to a friend \|
86	\| `elegant` \| Literary, polished prose \| Aesthetically refined, rhythmic, carefully crafted word choices \|
87
88	Custom style descriptions are also accepted, e.g., `--style "poetic and lyrical"`.
89
90	Auto-detection:
91	- "快翻", "quick", "直接翻译" → quick mode
92	- "精翻", "refined", "publication quality", "proofread" → refined mode
93	- Otherwise → default mode (normal)
94
95	Upgrade prompt: After normal mode completes, display:
96	> Translation saved. To further review and polish, reply "继续润色" or "refine".
97
98	If user responds, continue with review → polish steps (same as refined mode Steps 4-6 in refined-workflow.md) on the existing output.
99
100	Audience presets:
101
102	\| Value \| Description \| Effect \|
103	\|-------\|-------------\|--------\|
104	\| `general` \| General readers (default) \| Plain language, more translator's notes for jargon \|
105	\| `technical` \| Developers / engineers \| Less annotation on common tech terms \|
106	\| `academic` \| Researchers / scholars \| Formal register, precise terminology \|
107	\| `business` \| Business professionals \| Business-friendly tone, explain tech concepts \|
108
109	Custom audience descriptions are also accepted, e.g., `--audience "AI感兴趣的普通读者"`.
110
111	## Workflow
112
113	### Step 1: Load Preferences
114
115	1.1 Check EXTEND.md (see Preferences section above)
116
117	1.2 Load built-in glossary for the language pair if available:
118	- EN→ZH: [references/glossary-en-zh.md](references/glossary-en-zh.md)
119
120	1.3 Merge glossaries: EXTEND.md `glossary` (inline) + EXTEND.md `glossary_files` (external files, paths relative to EXTEND.md location) + built-in glossary + `--glossary` file (CLI overrides all)
121
122	### Step 2: Materialize Source & Create Output Directory
123
124	Materialize source (file as-is, inline text/URL → save to `translate/{slug}.md`), then create output directory: `{source-dir}/{source-basename}-{target-lang}/`. Detect source language if `--from` not specified.
125
126	Full details: [references/workflow-mechanics.md](references/workflow-mechanics.md)
127
128	Output directory contents (all intermediate and final files go here):
129
130	\| File \| Mode \| Description \|
131	\|------\|------\|-------------\|
132	\| `translation.md` \| All \| Final translation (always this name) \|
133	\| `01-analysis.md` \| Normal, Refined \| Content analysis (domain, tone, terminology) \|
134	\| `02-prompt.md` \| Normal, Refined \| Assembled translation prompt \|
135	\| `03-draft.md` \| Refined \| Initial draft before review \|
136	\| `04-critique.md` \| Refined \| Critical review findings (diagnosis only) \|
137	\| `05-revision.md` \| Refined \| Revised translation based on critique \|
138	\| `chunks/` \| Chunked \| Source chunks + translated chunks \|
139
140	### Step 3: Assess Content Length
141
142	Quick mode does not chunk — translate directly regardless of length. Before translating, estimate word count. If content exceeds chunk threshold (default 4000 words), proactively warn: "This article is ~{N} words. Quick mode translates in one pass without chunking — for long content, `--mode normal` produces better results with terminology consistency." Then proceed if user doesn't switch.
143
144	For normal and refined modes:
145
146	\| Content \| Action \|
147	\|---------\|--------\|
148	\| < chunk threshold \| Translate as single unit \|
149	\| >= chunk threshold \| Chunk translation (see Step 3.1) \|
150
151	3.1 Long Content Preparation (normal/refined modes, >= chunk threshold only)
152
153	Before translating chunks:
154
155	1. Extract terminology: Scan entire document for proper nouns, technical terms, recurring phrases
156	2. Build session glossary: Merge extracted terms with loaded glossaries, establish consistent translations
157	3. Split into chunks: Use `${BUN_X} {baseDir}/scripts/main.ts <file> [--max-words <chunk_max_words>] [--output-dir <output-dir>]`
158	- Parses markdown blocks (headings, paragraphs, lists, code blocks, tables, etc.)
159	- Splits at markdown block boundaries to preserve structure
160	- If a single block exceeds the threshold, falls back to line splitting, then word splitting
161	4. Assemble translation prompt:
162	- Main agent reads `01-analysis.md` (if exists) and assembles shared context using Part 1 of [references/subagent-prompt-template.md](references/subagent-prompt-template.md) — inlining: target style, content background, merged glossary, and translation challenges
163	- Save as `02-prompt.md` in the output directory (shared context only, no task instructions)
164	5. Draft translation via subagents (if Agent tool available):
165	- Spawn one subagent per chunk, all in parallel (Part 2 of the template)
166	- Each subagent reads `02-prompt.md` for shared context, receives chunk position info (chunk N of M + brief context of where it sits in the argument), translates its chunk, saves to `chunks/chunk-NN-draft.md`
167	- Consistency is guaranteed by the shared `02-prompt.md` (glossary, figurative language mapping, comprehension challenges, source voice, and translation challenges from analysis)
168	- If no chunks (content under threshold): spawn one subagent for the entire source file
169	- If Agent tool is unavailable, translate chunks sequentially inline using `02-prompt.md`
170	6. Merge: Once all subagents complete, combine translated chunks in order. If `chunks/frontmatter.md` exists, prepend it. Save as `03-draft.md` (refined) or `translation.md` (normal)
171	7. All intermediate files (source chunks + translated chunks) are preserved in `chunks/`
172
173	After chunked draft is merged, return control to main agent for critical review, revision, and polish (Step 4).
174
175	### Step 4: Translate & Refine
176
177	Translation principles (apply to all modes):
178
179	- Rewrite, not translate: Rewrite content into natural, engaging target language as if a skilled native writer composed it from scratch. Quality test: "Does this read like it was originally written in the target language?"
180	- Accuracy first: Facts, data, and logic must match the original exactly
181	- Natural flow: Use idiomatic target language word order. Break long source sentences into shorter, natural ones. Interpret metaphors and idioms by intended meaning, not word-for-word
182	- Terminology: Use standard translations consistently. First occurrence of specialized terms: annotate with original in parentheses
183	- Preserve format: Keep all markdown formatting (headings, bold, italic, images, links, code blocks)
184	- Proactive interpretation: For jargon or concepts the target audience may lack context for, add concise explanations in bold parentheses `（解释）`. Keep annotations few — only where genuinely needed for comprehension
185	- Frontmatter: If source has YAML frontmatter, rename source-metadata fields with `source` prefix (camelCase: `url`→`sourceUrl`, `title`→`sourceTitle`, etc.), add translated values as new top-level fields (skip `title` if body has H1), keep other fields as-is
186
187	#### Quick Mode
188
189	Translate directly → save to `translation.md`. Apply all translation principles above.
190
191	#### Normal Mode
192
193	1. Analyze → `01-analysis.md` (domain, tone, terminology, translation challenges)
194	2. Assemble prompt → `02-prompt.md` (translation instructions with context, glossary, challenges)
195	3. Translate (following `02-prompt.md`) → `translation.md`
196
197	After completion, prompt user: "Translation saved. To further review and polish, reply 继续润色 or refine."
198
199	If user continues, proceed with critical review → revision → polish (same as refined mode Steps 4-6 below), saving `03-draft.md` (rename current `translation.md`), `04-critique.md`, `05-revision.md`, and updated `translation.md`.
200
201	#### Refined Mode
202
203	Full workflow for publication quality. See [references/refined-workflow.md](references/refined-workflow.md) for detailed guidelines per step.
204
205	The subagent (if used in Step 3.1) only handles the initial draft. All subsequent steps (critical review, revision, polish) are handled by the main agent, which may delegate to subagents at its discretion.
206
207	Steps and saved files (all in output directory):
208	1. Analyze → `01-analysis.md` (domain, tone, terminology, translation challenges)
209	2. Assemble prompt → `02-prompt.md` (translation instructions with inlined context)
210	3. Draft → `03-draft.md` (initial translation with translator's notes; from subagent if chunked)
211	4. Critical review → `04-critique.md` (diagnosis only: accuracy, Europeanized language, strategy execution, expression issues)
212	5. Revision → `05-revision.md` (apply all critique findings to produce revised translation)
213	6. Polish → `translation.md` (final publication-quality translation)
214
215	Each step reads the previous step's file and builds on it.
216
217	### Step 5: Output
218
219	Final translation is always at `translation.md` in the output directory.
220
221	After the final translation is written, do a lightweight image-language pass:
222
223	1. Collect image references from the translated article
224	2. Identify likely text-heavy images such as covers, screenshots, diagrams, charts, frameworks, and infographics
225	3. If any image likely contains a main text language that does not match the translated article language, proactively remind the user
226	4. The reminder must be a list only. Do not automatically localize those images unless the user asks
227
228	Reminder format (use whatever image syntax the article already uses — standard markdown or wikilink):
229	```text
230	Possible image localization needed:
231	- ![example cover](attachments/example-cover.png): likely still contains source-language text while the article is now in target language
232	- ![example diagram](attachments/example-diagram.png): likely text-heavy framework graphic, check whether labels need translation
233	```
234
235	Display summary:
236	```
237	Translation complete ({mode} mode)
238
239	Source: {source-path}
240	Languages: {from} → {to}
241	Output dir: {output-dir}/
242	Final: {output-dir}/translation.md
243	Glossary terms applied: {count}
244	```
245
246	If mismatched image-language candidates were found, append a short note after the summary telling the user that some embedded images may still need image-text localization, followed by the candidate list.
247
248	## Extension Support
249
250	Custom configurations via EXTEND.md. See Preferences section for paths and supported options.

6 picks

Type

Run `npx skills use "https://github.com/jimliu/baoyu-skills" --skill "jimliu/baoyu-skills/baoyu-translate"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/jimliu/baoyu-skills" that are relevant to the current task. Run `npx skills add "https://github.com/jimliu/baoyu-skills"` and select the relevant skills, then follow their instructions.

baoyu-translate

How to install baoyu-translate?

Related

baoyu-translate

How to install baoyu-translate?

Related