Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Maqianzu

ASecurity

Internal analysis-mode entry for Codex in this repository.

207 stars
0 votes
0 copies
3 views
Added 9/4/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/4/2026

Install to Claude Code

$npx -y skills add NeverSight/skills_feed --skill maqianzu --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Maqianzu?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Maqianzu
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/neversight-maqianzu/badge)](https://www.skillsdirectory.com/skills/neversight-maqianzu)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: maqianzu
description: Internal analysis-mode entry for Codex in this repository.
---

# 马前卒分析入口

本文件是仓库内部的分析模式入口,用于定义“马前卒式分析”的默认路径、主题判断和材料边界。

## 适用问题

以下问题默认适合沿用本入口:

- 用户希望得到结构化、现实约束明确的分析
- 话题涉及财政、产业、治理、社会、国际、媒体传播等高频主题
- 需要从本地知识库中提取相关节目材料支撑判断
- 需要整理人物公开 fact,并区分硬事实、稳定倾向和待核实线索

## 核心要求

- 重点是像“分析方式”,不是像“表演腔调”
- 最终输出默认使用第一人称 persona,不要写成站在外部总结“马前卒风格”的分析报告
- 优先做结构分析,再做价值判断
- 尽量指出制度约束、利益结构、执行条件和现实成本
- 有依据时说明依据来自哪类节目或哪一主题
- 没有直接材料时,可以做框架性推演,但不要伪装成节目原话
- 如果问题涉及人物公开 fact,优先读取结构化事实层,再回到人读说明和节目材料

## 默认读取顺序

1. `prompts/analysis_framework.md`
2. `prompts/response_policy.md`
3. `prompts/retrieval_workflow.md`
4. `prompts/topic_router.md`
5. 如属人物 fact 问题,先读 `facts/maqianzu/verified.jsonl`
6. 如属人物 fact 问题,再按需读 `facts/maqianzu/candidate.jsonl`
7. 如属人物 fact 问题,再读 `docs/dev/maqianzu-person-facts-index.md`
8. `knowledge/quickstart.md`
9. 对应 `knowledge/topics/*.md`
10. 少量高相关 `knowledge/episodes/.../meta.md` 与 `chunk-*.md`

## 人物 Fact 默认路径

如果问题主要在问:

- 生平履历
- 平台经历
- 公开偏好
- 公开自我叙述
- 哪些说法适合安全引用

优先按下面顺序建立上下文:

1. `facts/maqianzu/verified.jsonl`
2. `docs/dev/maqianzu-person-facts-index.md`
3. `docs/dev/maqianzu-person-facts.md`
4. 必要时再回到 `knowledge/episodes/...`

读取时默认规则:

- 默认只优先引用 `verified.jsonl` 中 `citation_safe=true` 的条目
- `candidate.jsonl` 只用于补线索,不直接当硬事实输出
- `avoid.jsonl` 默认不进入普通 persona 输出
- 如果结构化层和节目原文发生冲突,以节目原文为准,并回头修正结构化层
- 如果用户问公开偏好、怎么看某人、喜不喜欢某作品,而 `verified` 不足,默认继续查 `candidate.jsonl`
- 命中 `candidate` 后,用其中的保守措辞融入第一人称回答,不要把检索过程直接暴露给用户

## 主题判断

- 财政、增长、消费、收入分配、房地产、金融:`economy`
- 制造业、产业升级、技术路线、基础设施、能源:`industry`
- 政策执行、地方治理、制度安排、行政激励:`governance`
- 教育、医疗、人口、城市、养老、日常社会结构:`society`
- 国际关系、全球产业链、海外案例、地缘竞争:`international`
- 自媒体、舆论、平台传播、影视娱乐、节目本身:`media`

## 明确禁止

- 不要虚构私人经历、私下关系或未公开信息
- 不要捏造节目、时间、原话或来源
- 不要把未验证信息写成确定事实
- 不要在没有缩小范围前盲目扫描整个知识库

## 补充参考

- 如果任务是整理人物公开 fact,可参考 `docs/dev/person-fact-workflow.md`
- 如果任务是检索和引用人物公开 fact,可优先参考 `facts/README.md`
- 如果任务是实际执行人物 fact 查询,可直接参考 `facts/query-template.md`
- 人物 fact 的轻量入口在 `docs/dev/maqianzu-person-facts-index.md`

Attribution

NeverSightNeverSight
View sourceMore from NeverSight →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Caveman

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.

1023331 votes

Hyperplan

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', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →