ime-lexicon-bridge skillA
ime-lexicon-bridge is agent-read markdown (skill) from taxueseek/ime-lexicon: 素材库 ↔ 创作词库 ↔ 画像：harvest 用去 AI 味筛子抽专属词， guide 出用词包，acquire 按画像缺口出搜索计划。只读，不 apply。 触发：抽创作词、用词包、金句抽词、写之前看词、素材库词库打通、画像补词。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# bridge — 素材库 ↔ 创作词库 ↔ 画像
父技能：`ime-lexicon`。脚本：`scripts/bridge.py`（确定性，不调 LLM）。
素材库 = 你写过什么；词库 = 你会怎么写；画像 = 你该补哪块行业。
筛子反过来：先拒套话，再留声音/话题，缺口交给 acquire 去搜。
## 三层筛子
1. **拒**：writing-standards / humanize-ai 套话（值得注意的是、至关重要、深度赋能…）一律不进表
2. **留**：话题标签；口头禅（金句/洞见里同一术语 ≥3 次）；按标点+功能字切开的 3–6 字完整术语。不滑窗、不贪心切 8 字
3. **补**：知乎画像 `expertise_domains` 关键词 − 已有词表 = acquire 查询，走 search/build
## harvest
只读素材库的金句 / 洞见文件（`IME_MATERIAL_DIR`，默认 `~/Documents/ime-lexicon/素材库`）。
产物：`创作词库.tsv`（写入 `IME_DICT_DIR`）。禁止 apply，禁止灌全量词库。
```bash
python3 "$HOME/.agents/skills/ime-lexicon/scripts/ime_lexicon.py" harvest
python3 "$HOME/.agents/skills/ime-lexicon/scripts/ime_lexicon.py" harvest --speech
```
`--speech` 读语音转写数据源的转写 / 纠错历史（`IME_SPEECH_DIR` / `IME_XIGUA_DIR`）。
## guide
- `use`：行业/创作词
- `voice`：material 惯用词
- `gap`：素材里抽出、词库还没有的术语（最多 20）
```bash
python3 "$HOME/.agents/skills/ime-lexicon/scripts/ime_lexicon.py" guide --topic 投资理财
```
## acquire
画像 + 素材好词 − 已有词表。默认只打印 `have` / `gap` / `seek`。
`--out` 把 gap 写成一行一词，供 `build --from`。
`--run` 才真搜，append 到 `--out`（没有就写 `_acquire_{topic}.txt`）。不覆盖 `行业词库_*.txt`，不 apply。
```bash
…Read the whole file at its exact version.
How to install
mdr add taxueseek/ime-lexicon/ime-lexicon-bridge@git:20260825.cca86d0mdr add taxueseek/ime-lexicon/ime-lexicon-bridge@sha256:288858a8f03d62dfPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_dnfnhnwselcxigdl)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260825.cca86d0 latest | 2026-08-25 | cca86d0 | 2,670 B | A | view · diff |
| git:20260822.a9f9084 | 2026-08-22 | a9f9084 | 2,840 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (2670 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
taxueseek/ime-lexicon · 5 stars · license MIT · pushed 2026-09-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dnfnhnwselcxigdl GET https://markdownregistry.com/api/v1/resolve?ref=taxueseek/ime-lexicon/ime-lexicon-bridge GET https://markdownregistry.com/api/v1/blob/288858a8f03d62df0a0aa369078b4e9e5a026118dffc02bb21f122a1c41b4ce1
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.