devils-advocate SKILL.md skillA
devils-advocate from daymade/claude-code-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add daymade/claude-code-skills/devils-advocate@git:20261009.59bfcd3Pins git:20261009.59bfcd3 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- daymade/claude-code-skills
- Path
daymade-financial/devils-advocate/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261009.59bfcd3, committed Oct 9, 2026
- First version recorded
- Aug 14, 2026
- Size
- 15,024 bytes
- Repository stars
- 1,485
- License
- MIT
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。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Devil's Advocate 结构化反方论证 把「唱反调」从一种态度变成一道有出处、可审计、可持续监测的工序。 ## 为什么这样设计（读懂了才不会走样） 三个实证结论决定了本 skill 的形状： 1. **默认状态的 LLM 会讨好提问者。** 经 RLHF 训练的模型系统性倾向于迎合用户已表达的信念而非说真话（Sharma et al., ICLR 2024）。分析师直接问模型「我这个论点对吗」，得到的答案有结构性偏正。所以反方角色必须被显式赋予，不能指望模型自发唱反调。 2. **没有证据的唱反调不但没用，还会帮倒忙。** 社会心理学的经典结果：角色扮演式的「指派反方」效果不如真实异议（Nemeth et al., 2001）；后续研究进一步指出，不真实的异见反而让人更固守原判断（Nemeth, 2018）。所以本 skill 的每一条反方论证都必须锚定到具体材料的具体位置——证据锚定是「真实异议」的代理，自由发挥的抬杠被禁止。 3. **显式反方人设的多 agent 结构有量化增益。**「批评者」角色相对此前最优评估方法（G-Eval）有 6.4-12.5 个百分点的相关系数提升（DEBATE, ACL Findings 2024）；论文另以定性结论指出反方人设显著优于中立多 agent 基线；多个「中立」agent 互评反而可能互相强化错误共识。 投资论点的常规执行无需加载两个 references；需要解释设计依据、对某一步产生疑问，或压力测试工程机制时，读 [方法论谱系与工程适用边界](references/structured_analytic_techniques.md)。工程机制先读其中「工程机制的反证边界」，再沿下文流程检验；被复刻产品的原始 prompt 与 schema 见 [references/linqalpha_reference_implementation.md](references/linqalpha_reference_implementation.md)。 ## 入口判断 | 用户给了什么 | 走哪条路 | |---|---| | 论点 + 证据材料（文件/目录/URL 清单） | 完整六步流程（下文） | | 只有论点，没有材料 | 先问用户要材料；用户说没有 → 请用户在两个选项里选：①先做检索把材料建起来再回来跑（若有检索类 skill 可先用）②只交付 Step 1 的假设拆解 + Step 5 的信号标（这两步不依赖材料；此时无 risk_flag 可筛，信号标覆盖全部负重假设），并明确说明反证检索未做 | | 论点含混（一段散文、一个 IC memo） | 先按 Step 0 提炼出核心断言让用户确认，再继续 | …
Read the whole file at its exact version.
How to install
mdr add daymade/claude-code-skills/devils-advocate@sha256:7201fdadd45cf2c0The line at the top of this page pins the label git:20261009.59bfcd3, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_2erwooq6iqpy6uj4)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 14, 2026 and Oct 9, 2026, about one every 56 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.59bfcd3 latest | 2026-10-09 | 59bfcd3 | 15,024 B | A | view · diff |
| git:20260814.96fa53e | 2026-08-14 | 96fa53e | 14,964 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (15024 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
daymade/claude-code-skills · 1,485 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_2erwooq6iqpy6uj4 GET https://markdownregistry.com/api/v1/resolve?ref=daymade/claude-code-skills/devils-advocate GET https://markdownregistry.com/api/v1/blob/7201fdadd45cf2c0bf2cf0262b0204754120a120c87139e066ef2c4be471d611
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from daymade/claude-code-skills
Every file in daymade/claude-code-skills