Skills Explorer Add Skills

devils-advocate

An agent skill by daymade, from daymade/claude-code-skills. Tags: analysis, review, risk, strategy, validation.

What it does

结构化压力测试一个论点(devil's advocate / 魔鬼代言人):把论点拆成显性断言与隐性假设(A1/A2 编号), 逐条在用户给定的证据材料里检索带出处的反方论证,标 High/Medium/Low 风险等级,补基础比率外部视角, 最后给出「可监测的证伪信号」清单;输出结构化 findings + 人读叙事双层结果。找不到反证时如实声明「未找到」, 绝不编造。复刻自 LinqAlpha(对冲基金 AI 产品)公开的 Devil's Advocate 架构,叠加 CIA 结构化分析技术与 RAND 假设规划。当用户要「压力测试 / 唱反调 / 找盲点 / 拆假设 / 挑战这个论点 / bear case / 红队这个方案 / 上投委会前过一遍 / pressure test my thesis」,或拿着投资论点、IC memo、研究结论、商业决策要人挑刺时, 用本 skill——即使用户没说出"魔鬼代言人"这个词。

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill devils-advocate

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-financial/devils-advocate ~/.claude/skills/devils-advocate

Safety box score

Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-16. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This is a documentation-only analysis skill: it takes a thesis plus evidence materials, then produces structured counterarguments and a local report. The main blast radius is limited to reading user-supplied URLs and writing two report files in the working directory; there is no shipped code execution, credential handling, or privilege escalation.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)No shell commands, scripts, or code evaluation are shipped; the repository contents are plain markdown.
Network access1 (low)The skill explicitly accepts evidence as "文件/目录/URL" and says to "逐个确认可读", so it may contact user-supplied remote documents.
Filesystem reach1 (low)It explicitly writes `da_findings.json` and `da_report.md` in the current working directory, with an optional user-specified output path.
Secrets & credentials0 (none)It does not ask for tokens, keys, passwords, `.env` files, browser sessions, or other credential stores.
Privilege & persistence0 (none)There is no sudo, global install, service registration, shell startup editing, or OS-level configuration change.
Instruction hijack surface0 (none)The skill contains only self-contained workflow instructions and does not tell the agent to ignore higher-priority rules or follow remote instructions.
Irreversible actions0 (none)It only analyzes and reports; it does not post, deploy, pay, book, delete, or otherwise act externally.
Transparency0 (none)All shipped files are readable markdown; there are no binaries, minified blobs, or runtime-downloaded installers.

Before installing

Rated 2026-10-16 by an automated review of 3 files from the skill's repository.

Source

Repository
daymade/claude-code-skills (all skills from this repository)
Path
daymade-financial/devils-advocate/SKILL.md
Branch
main
Updated
2026-09-20