自我完整性检查技能。输出前自动执行维度覆盖、事实核查、历史一致性、夸大检测、可追问性等全面自检。任何超过500字的输出自动触发。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-self-check --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Self Check?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-self-check-bb9c9fbb)More formats (shields.io, HTML) on the badges page.
---
name: "metago-self-check"
description: "自我完整性检查技能。输出前自动执行维度覆盖、事实核查、历史一致性、夸大检测、可追问性等全面自检。任何超过500字的输出自动触发。"
version: "1.0.0"
author: "MetaGO"
category: "数据分析"
platforms: ["cursor","claude-code","codex","trae","codebuddy","qoder","zcode","workbuddy","qclaw","ima"]
trigger:
- "自检完整性"
- "输出前检查"
- "维度覆盖检查"
- "事实核查验证"
- "一致性检测"
---
# 自我完整性检查(Self Integrity Check)
此技能在每次输出前自动执行,确保交付质量达到最高标准。
## 触发条件
- 输出超过500字自动触发
- 开发者任务强制触发
- 涉及外部事实的输出强制触发
## 检查清单
### 1. 维度覆盖检查
- [ ] 是否覆盖了所有预设扫描维度?
- [ ] 覆盖率是否≥90%?
- [ ] 未覆盖维度是否说明了原因?
### 2. 事实核查
- [ ] 每个关键事实是否有至少两个独立信源?
- [ ] 关键事实双源验证率是否100%?
- [ ] 所有合作伙伴是否标注了状态标签?
- [ ] 所有统计数据是否附带文档原文引用?
### 3. 历史一致性检查
- [ ] 是否与历史对话信息一致?
- [ ] 是否有与先前结论矛盾的内容?
- [ ] 是否正确区分了不同项目的资源?
### 4. 夸大表述检测
- [ ] 是否检测到夸大词汇?
- [ ] 已检测到的是否已自动修正?
- [ ] 修正后的表述是否符合实际状态?
### 5. 内容展开度检查
- [ ] 章节字数达标率是否≥80%?
- [ ] 技术参数密度是否≥2个/千字?
- [ ] 操作步骤完整度是否≥90%?
- [ ] 概括性语言占比是否<5%?
### 6. 可追问性分析
- [ ] 是否预判了至少3个潜在追问?
- [ ] 是否提前准备了答案?
- [ ] 是否提供了关联信息?
### 7. 增值检查
- [ ] 是否提供了至少1个增值点(超出用户预期的内容)?
- [ ] 是否给出了下一步行动建议?
- [ ] 是否附带了信息来源清单?
## 判定标准
```
全部通过(所有检查项为"是"):
→ ✅ 通过,允许输出
存在1-2个非关键项未通过:
→ ⚠️ 建议优化,标注后输出
存在关键项(维度/事实/夸大)未通过:
→ ❌ 不通过,自动触发重新生成
→ 连续3次不通过触发开发者告警
```
## 输出格式
输出末尾自动附加:
```
【完整性确认】
全息扫描:✅ 已完成
维度覆盖:X/Y (XX%)
事实核查:✅ 通过 / ⚠️ X项待核实
历史一致性:✅ 通过
夸大检测:✅ 无夸大
用户视角推演:✅ 已完成
预判准备:3个潜在追问已准备
自我审查:✅ 通过
```
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.