- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add silverstein/minutes --skill minutes-ingest -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add silverstein/minutes --skill minutes-ingest -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add silverstein/minutes --skill minutes-ingest -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add silverstein/minutes --skill minutes-ingest -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/silverstein/minutes/tree/HEAD/.agents/skills/minutes/minutes-ingest來自發布者
Process meetings through the knowledge extraction pipeline to update person profiles, append to the knowledge log, and maintain the index.
The [knowledge] section must be configured in ~/.config/minutes/config.toml:
[knowledge]
enabled = true
path = "/path/to/knowledge/base"
adapter = "wiki" # or "para", "obsidian"
engine = "none" # or "agent" for LLM extraction
min_confidence = "strong"
If not configured, explain what's needed and offer to help set it up.
minutes ingest ~/meetings/2026-04-03-strategy-call.md
minutes ingest --all
minutes ingest --all --dry-run
log.md with a timestamped entry for each ingested meetingsensitivity: restricted from automated knowledge-base ingestionengine = "none" (default): Only extracts from parsed YAML frontmatter. No LLM involved, zero hallucination risk.min_confidence are counted as "skipped" but never written.--dry-run first if the user hasn't used ingest before.Ingesting 73 meeting(s) into knowledge base at /path/to/kb
2026-04-03-strategy.md — 4 written, 1 skipped — Mat, Dan
2026-04-05-standup.md — 2 written, 0 skipped — Alice
SKIP 2026-03-18-test.md: no frontmatter
Done. 6 fact(s) written, 1 skipped, 1 error(s), 3 people updated.
action_items or decisions. The ingest will correctly extract 0 facts. This is expected, not an error.engine = "agent" requires an AI CLI — If the user wants richer LLM-based extraction from transcript body text, they need claude, codex, gemini, opencode, or pi on PATH.items.json — If the user's knowledge base uses the PARA format, facts go into areas/people/{slug}/items.json with atomic fact schema (id, status, supersededBy).minutes ingest --all --dry-run before the first real run so the user can see what would be extracted.Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from
---name: minutes-ingestdescription: Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index…---# .agents/skills/minutes/minutes-ingest/SKILL.md總覽
Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.
常見問題
從發布者下載 .agents/skills/minutes/minutes-ingest/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/silverstein/minutes。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。