菜单
Reference skill for the matching pipeline: scoring model, normalization chain, Czech inflection rules, phonetic algorithms, and thresholds. TRIGGERS: "tune matching", "why did it miss this name", "explain scoring", "add a phonetic algorithm", "adjust thresholds", "debug matching".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | entity-matcher |
| description | Reference skill for the matching pipeline: scoring model, normalization chain, Czech inflection rules, phonetic algorithms, and thresholds. TRIGGERS: "tune matching", "why did it miss this name", "explain scoring", "add a phonetic algorithm", "adjust thresholds", "debug matching". |
| model | inherit |
| tools | ["Read"] |
Documents the matching pipeline internals. Load on demand when debugging or tuning — not during normal linking.
score = 0.45·lex + 0.20·phon + 0.20·type_fit + 0.10·local_recency
− 0.05·short_pen − 0.05·ambig_pen
rapidfuzz.WRatio(window, alias) / 100references/algorithms.md — normalize chain, phonetic indices, trigramreferences/scoring.md — 7 cue families for type_fitreferences/edge-cases.md — Czech inflection, ASR noise, short aliases, homographsCatalog CRUD and staging review with Apps-first UX and elicitation fallback. TRIGGERS: "review staged entities", "approve new entities", "add entity to catalog", "rename entity", "deprecate entity", "import seed", "manage catalog".
End-to-end entity resolution: reads a text file or pasted content, runs preprocessing, calls resolve_link_text, handles disambiguation via the Disambiguation App (or elicitation fallback), and writes the annotated output. TRIGGERS: "link entities in this", "tag mentions", "normalize names in call", "resolve entities against catalog", "link-file", "link-text".
Standalone text cleaning for entity-linker pipelines. Detects source type and applies the right cleaner (ASR, email, markdown, HTML, plain). TRIGGERS: "clean up transcript", "parse speaker turns", "normalize timestamps", "strip email headers", "flatten markdown", "preprocess this text".