菜单
Extracts structured action items from a meeting transcript or notes, identifying the task description, assigned owner name, due date or relative deadline, and priority level for each item. Returns a sorted action_items list and a one-paragraph meeting summary.
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
| id | meeting-action-extractor |
| name | Meeting Action Extractor |
| version | 1.0.0 |
| description | Extracts structured action items from a meeting transcript or notes, identifying the task description, assigned owner name, due date or relative deadline, and priority level for each item. Returns a sorted action_items list and a one-paragraph meeting summary. |
| capability | {"type":"data-transform","inputs":["transcript:string","meeting_date:string"],"outputs":["action_items:list","summary:string","owner_list:list"]} |
| graph | {"depends_on":[],"complements":["calendar-event-creator","slack-message-sender"],"co_used_with":["meeting-notes-formatter","email-draft-writer"]} |
| compatibility | {"claude_code":true,"gemini":true,"codex":false,"cursor":false,"mcp":true} |
| risk | safe |
Parses raw meeting transcript text and extracts every action item mentioned, whether stated explicitly ("I'll do X by Friday") or implied ("can you send that report?"). For each action item, identifies: what needs to be done, who is responsible, when it's due, and the priority level. Also generates a 2–3 sentence meeting summary.
transcript — raw text of the meeting transcript, notes, or chat logmeeting_date — date the meeting occurred in YYYY-MM-DD format; used to resolve relative deadlines like "next Thursday" into absolute datesaction_items — list of {task, owner, deadline, priority, source_quote} objectssummary — 2–3 sentence plain-English summary of the meeting discussionowner_list — deduplicated list of people who were assigned at least one taskhigh — explicit deadline pressure or blocking other worknormal — standard task with a clear ownerlow — mentioned but not urgently ownedSarah: I'll update the landing page copy by end of week.
John: Can you also send the budget numbers to finance by Thursday?
Sarah: Sure. Mike, can you follow up with the vendor on the Q3 contract?
{
"action_items": [
{"task": "Update landing page copy", "owner": "Sarah", "deadline": "2025-05-02", "priority": "normal"},
{"task": "Send budget numbers to finance", "owner": "Sarah", "deadline": "2025-04-29", "priority": "high"},
{"task": "Follow up with vendor on Q3 contract", "owner": "Mike", "deadline": null, "priority": "normal"}
],
"summary": "Team reviewed landing page and budget timelines. Three action items assigned to Sarah and Mike with two deadlines this week.",
"owner_list": ["Sarah", "Mike"]
}
Activates ultra-compressed response mode that reduces token usage by approximately 75% by eliminating filler words, articles, and pleasantries while preserving full technical accuracy and substance. Invoke when the user requests "caveman mode", "talk like caveman", "less tokens", "be brief", or uses the /caveman command.
Builds an interactive knowledge graph from any mix of code, docs, papers, images, and video/audio files. Extracts concepts, relationships, call graphs, and design rationale via AST (code) and Claude subagents (docs/media). Outputs interactive HTML, queryable JSON, and a plain-language audit report. Supports incremental updates, cross-repo merging, MCP server mode, and always-on assistant hooks for Claude Code, Cursor, Gemini CLI, Codex, and others.
Conducts a structured, relentless interview of the user's plan or system design, resolving each branch of the decision tree until full shared understanding is reached. Provides a recommended answer for each question asked. Invoke when the user wants to stress-test a plan, validate architecture decisions, or explicitly requests "grill me".
Guides the creation of new agent skills with correct structure, progressive disclosure, and bundled reference resources. Produces a SKILL.md with a routing-optimized description, optional reference files, and utility scripts where deterministic operations are needed. Invoke when the user wants to create, write, or build a new skill file.
Parses a git diff or patch file and produces a structured summary of changes: files modified, lines added and removed per file, a plain-English description of what changed, and a suggested conventional commit message following the feat/fix/chore/refactor/docs prefix convention.
Scans a git repository or file path for hardcoded secrets, API keys, tokens, and credentials using Gitleaks SAST rules. Returns findings with file path, line number, secret type (AWS key, GitHub token, Slack webhook, etc.), and a redacted preview. Returns clean=true when no secrets are detected.