skills: rename dharma-translation→translation, delete mpi-project-conventions, move references

- dharma-translation → translation: stripped conventions, kept only technique
- Deleted mpi-project-conventions: all content now in AGENTS.md
- References moved: meditation-translation, markdown-to-djot → translation/
  translation-pitfalls, proofreading-patterns → translation-review/
- Updated AGENTS.md, readme.dj, memory, pdf skill cross-reference
- 7 skills → 6 skills

skills/translation/SKILL.md

@@ -0,0 +1,59 @@
+---
+name: translation
+description: Translate Chinese↔English Buddhist/Dharma content — register guidance from Mindfulness Bell corpus, tone, voice, cultural bridging technique.
+---
+
+# Translation
+
+Core translation technique for Buddhist/Dharma content. Conventions (djot format,
+terms DB query, workflows, output format) are in AGENTS.md.
+
+## Mindfulness Bell Corpus
+
+Register/style patterns in English Buddhist prose.
+
+- Location: `/home/user/meta/www.files/public/The Mindfulness Bell/`
+- 6 issues: MB92–MB97 (2023–2026), each ~84–116 pages
+- Index: `index.yaml` (article titles, authors, pages)
+- **Articles**: `~/documents/jingxin-lessons/Mindfulness Bell/articles/MB{92..97}/*.md` — 93 individual markdown files with YAML frontmatter. Read directly with `read_file`.
+- Extraction script: `/tmp/extract_mb_articles.py` (re-run if PDFs change)
+
+## Register Reference
+
+Four registers observed, useful as style targets:
+
+| Register | Example | Key features |
+|----------|---------|-------------|
+| Dharma talk | Thầy (MB94 "Roses and Garbage", MB97 "Go as a River") | Short sentences, concrete images, coined terms ("interbeing"), oral address ("It's clear?"), Sanskrit kept with narrative explanation |
+| Teaching lineage | Sister Đoan Nghiêm (MB93 "Our Patriarch Liễu Quán") | "We" voice, terms explained, cultural bridging ("like Jesus"), dates woven into narrative, still oral |
+| Personal narrative | Mick McEvoy (MB94 "Touching the True Nature") | First-person, confessional, borrowed Dharma vocabulary, emotional directness, vernacular |
+| Editorial | Brother Pháp Lưu (MB94 welcome letter) | Polished but warm, conceptual framing, "we" address |
+
+## Translation Principles
+
+1. **Terms**: Either keep Sanskrit w/ narrative explanation (bodhisattva, Māra) OR coin new English (interbeing, inter-are). Avoid clunky calques.
+2. **Cultural bridging**: Add bridges for Western readers. A Chinese text mentioning 孔子 can stay; explain the function. Đoan Nghiêm's "like Jesus" is the pattern.
+3. **Tone**: Chinese Dharma texts are typically more formal than English equivalents. Decide consciously: keep formality or warm up (Thầy style).
+4. **Voice**: Direct address ("you"), concrete images, and oral rhythm make Dharma land in English. Abstract noun chains (common in Chinese→English translationese) kill it.
+5. **Sutra quotes**: Use standard English Buddhist idiom. Check terse-idiom conventions (e.g., Diamond Sutra "lives" not "bodies").
+
+For register decisions: consult the register table above (scanning MB articles is optional).
+
+## Quick-Find in MB Corpus
+
+Common article types to search for register examples:
+- Thầy's Dharma talks: search index for "Thích Nhất Hạnh" + page ≤ 10
+- Sister/brother teachings: search for "Sister" or "Brother" + "DHARMA TEACHING"
+- Personal narratives: first-person voice, often pages 8–60
+- Lineage/history: "Patriarch," "ancestor," dates in text
+
+## Meditation / Mindfulness Content
+
+When translating guided meditation scripts, exercise guides, or posture instructions
+(rather than Dharma talks), use a lighter workflow. See `references/meditation-translation.md`.
+
+## References
+
+- `references/meditation-translation.md` — lighter workflow for meditation/mindfulness content
+- `references/markdown-to-djot.md` — converting .docx.md to .dj for translation prep
+- `references/diacritics-convention.md` — diacritics rules

skills/translation/references/diacritics-convention.md

@@ -0,0 +1,13 @@
+# Diacritics Convention
+
+When in doubt, search the terms DB and use the highest-priority source's form.
+
+| Rule | Examples |
+|---|---|
+| No diacritics (default) | `Mahasthamaprapta` (佛教术语), `Yogacarabhumi-Sastra` (经论名), `Guanyin` (佛教术语), `Pabongkhapa` (nti) |
+| With diacritics | `Kṣitigarbha` (DoT定稿 uses this form) |
+| Sanskrit terms | Keep standard romanization: `bodhicitta`, `bardo`, `Amitabha`, `prajñā` |
+
+The DB uses simplified romanization. DoT定稿 is the authority — if it uses diacritics for a term, follow it. Otherwise strip them.
+
+Pitfall: academic/pedantic diacritics (`Mahāsthāmaprāpta`, `Yogācārabhūmi Śāstra`, `Avalokiteśvara`) are common in general knowledge but wrong per MPI conventions.

skills/translation/references/markdown-to-djot.md

@@ -0,0 +1,48 @@
+# Markdown to Djot Conversion
+
+When source material arrives as `.docx.md` (pandoc-converted from docx), convert to `.dj` for translation workflows.
+
+## Splitting combined articles
+
+If a single markdown file contains multiple articles (common when docx has two talks in one file), split at the article boundary before converting. Use `sed` by line number:
+
+```bash
+sed -n '1,218p' combined.md > a1.md
+sed -n '220,282p' combined.md > a2.md
+```
+
+## Heading anchor cleanup
+
+Pandoc's docx→md conversion adds `{#heading-id}` anchors to every heading:
+
+```markdown
+## 1．安宁疗护 {#1．安宁疗护}
+```
+
+These must be stripped before markdown→djot conversion, otherwise pandoc's djot writer leaves stray `{#...}` lines in the output:
+
+```bash
+sed 's/ {#[^}]*}//g' input.md > clean.md
+```
+
+## Conversion command
+
+```bash
+pandoc clean.md -f markdown -t djot --wrap=none -o output.dj
+```
+
+`--wrap=none` prevents reflow of long paragraphs.
+
+## Post-conversion cleanup
+
+Pandoc may still leave stray `{#...}` lines in djot output. Remove them:
+
+```bash
+sed -i '/^{#.*}$/d' output.dj
+```
+
+## Pandoc artifacts
+
+- Unicode `——` (U+2014 × 2) → `------` in djot (two em dashes, `---` each). This is correct djot syntax.
+- Markdown hard line breaks (trailing `  `) → `\\\n` in djot. Preserves original paragraph structure.
+- Pandoc normalizes heading IDs (strips `、` and other punctuation). Ignore; the stray-line cleanup handles it.

skills/translation/references/meditation-translation.md

@@ -0,0 +1,43 @@
+# Meditation / Mindfulness Content Translation
+
+When the source is a guided meditation script, exercise guide, posture instruction,
+or breathing practice (rather than a Dharma talk, sutra commentary, or teaching text),
+use a lighter workflow than the full dharma-translation pipeline.
+
+## Register
+
+Default to warm, direct instructional voice (Thầy-adjacent):
+- Second-person address ("you")
+- Concrete images, sensory details
+- Oral rhythm, short sentences
+- Present tense, imperative mood
+
+MB corpus consultation is NOT needed for register — this content type has its own
+well-established English conventions (yoga/meditation instructional voice).
+
+## Terms
+
+Terms DB lookup for Buddhist-mindfulness vocabulary is useful but limited to key terms:
+- 正念 → mindfulness
+- 觉知 → awareness
+- 无我 → depends on context: "non-self" for philosophical/Dharma content; "selflessly" for embodied/movement instruction where the sense is no separate controller imposing on the action
+- 中道 → Middle Way
+- 丹田 → dantian (keep as-is; well-known in meditation/qigong)
+
+Context-sensitive terms:
+- 心 (xīn): in meditation/movement contexts it often means "mind/attention" not emotional "heart." 持心 means holding the mind with focused attention, not holding with emotion.
+- 念 (niàn): mindfulness/attention/recollection — context between these.
+- Buddhist philosophical terms (无我, 空, 缘起) in non-philosophical contexts (movement instruction, body scans) may need practical/concrete translations rather than doctrinal ones.
+
+Skip deep terms alignment unless dense Dharma vocabulary (emptiness, dependent origination,
+Buddha-nature, etc.) appears in the text.
+
+## Comparison files
+
+Still create 对照.dj as usual. See comparison file format in this skill.
+
+## Pitfalls
+
+- **Don't add formatting the source doesn't have**: sub-section labels using `【】` in Chinese should become plain `[label]` in English, not `*[label]*` or `**[label]**`. Match the source's formatting level exactly.
+- **`**text**` is Markdown, not Djot**: Djot emphasis uses single asterisks (`*text*`). Never use double asterisks in `.dj` files.
+- **心 ≠ heart by default**: in meditation/movement contexts, 持心 = holding the mind with attention, not holding with emotion. Translate based on context, not dictionary defaults.