Skip to content
cccskills
FreePublished on GitHub

ime-lexicon-bridge

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。

The English summary is being prepared. Showing the original description.

Run score Not tested

See how to install

Files included (1)

  • SKILL.md2.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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。

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)
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。

python3 "$HOME/.agents/skills/ime-lexicon/scripts/ime_lexicon.py" acquire --topic 投资理财
python3 "$HOME/.agents/skills/ime-lexicon/scripts/ime_lexicon.py" acquire --topic 投资理财 --out /tmp/缺口.txt

画像路径:IME_PERSONA,未设时用默认(见 paths.py)。输出不含 user_id。

纪律

  • harvest/guide/acquire 只出表,永远不 apply、不写 usr.dat / WeType
  • 素材只取金句/洞见两句型,不抽正文、不抽已删除(~~)段
  • 词库逻辑在 ime-lexicon,shili-material / shili-content / humanize-ai 不复制

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

豆包 / 微信输入法个人词库:识别、导出、导入、备份;纠错优化; 搜索并生成行业/专业/定制词库(并入归档 industry-dict)。 不走官方导入页。搜索优先 argo,没有就走通用搜索兜底。本技能只出查询、抽词、改表、写回副本。 生态定位:直接操作豆包 / 微信输入法词库文件层(usr.dat / WeType LevelDB)的 agent skill, 文件层识别、批量导出、槽位感知注入、整表替换消错、行业词库造词后直接 apply; 格式互转工具和语音输入插件都不做词库管理。 触发:个人词库、词库导出、词库导入、反向注入、行业词库、专业词库、定制词库、 生成行业词库、做词库、行业术语、industry-dict、拼写纠正、豆包词库、 微信输入法词库、WeType、usr.dat、ime-lexicon、/ime-lexicon

The English summary is being prepared. Showing the original description.

taxueseek/ime-lexicon12Updated Sep 20, 2026

合并多份词表,自动改明显英文笔误和「词对、拼音错」,剔除 v2u / 拼音当词。 吃不准的进待确认,不写回输入法。

The English summary is being prepared. Showing the original description.

taxueseek/ime-lexicon12Updated Sep 20, 2026

See all skills by taxueseek

Report a problem with this skill