Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/daymade/claude-code-skills/devils-advocatenpx skills add daymade/claude-code-skills --skill devils-advocategit clone --depth 1 https://github.com/daymade/claude-code-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/daymade/claude-code-skills/devils-advocate)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/devils-advocate"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/devils-advocate.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00269 | $0.04332 |
| Opus 5 | $0.00134 | $0.02166 |
| Sonnet 5 | $0.00054 | $0.00866 |
| Haiku 4.5 | $0.00027 | $0.00433 |
Grade A, and why
devils-advocate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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：
- 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。
- 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。
- 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。
两个 references 常规执行不需要读：需要向使用者解释设计依据、或对某一步的做法产生疑问时才加载——完整谱系与逐字步骤见 references/structured_analytic_techniques.md；被复刻产品的原始 prompt 与 schema 见 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 |
| 假设超过 8 条，或材料超大（总量超过约 20 万字 / 单文件读不完） | 主会话中用 fan-out 模式（见文末），全部负重假设进入检索；在子代理里运行本 skill 时只能单上下文，按负重排序取前 8 条 |
Step 0 · 输入确认
三样东西，缺一样就先补齐：
- 论点：一句核心断言 + 它的支撑推理。用户给的是长文时，提炼成「X 将因为 Y 而 Z」形态并请用户确认——拆错了论点，后面全白做。在子代理内运行、没有用户可确认时：写出规范化论点，放进两份产物的头部并标注「未经确认」，然后继续。
- 证据材料清单：具体的文件路径 / 目录 / URL。逐个确认可读；不可读的当场报告，不静默跳过。
- 用途：上会前自查、还是评估别人的方案？决定人读层的语气与详略。
Step 1 · 拆假设
把论点分解为两类，统一编号 A1、A2、A3……：
- 显性断言（explicit assertions）：论点里直接写出来的。
- 隐性假设（implicit assumptions）：没写出来、但论点要成立就必须为真的前提。这一类才是盲点的主产区——确认偏误让人看不见自己依赖了什么。
每条假设标两个属性：
- 类型：事实性（现在就能核对）/ 预测性（关于未来）/ 机制性（关于因果链）。类型决定 Step 2 用什么反证。
- 负重（load-bearing，RAND ABP 的判据）：把这条假设推翻，结论会不会实质改变？不会 → 降级，不进入反证检索，只在附录列出。
枚举不设上限，照实列全；「8 条」约束的是进入反证检索的条数。一条假设里若藏着结论可能相反的两个子命题（例如「壁垒存在」与「壁垒的收益归属某一家」——前者可能幸存、后者可能被反转），拆成两条分别检索，再一起参加负重排序。单上下文模式下超过 8 条进入检索时按负重取前 8，其余明确列为「未检索」——宁可深挖 6 条也不要浅扫 15 条；主会话 fan-out 模式不受此限，全部负重假设进入检索。
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 159 lines · 269 tokens per session scan A 58e42d232730
devils-advocate is a skill published in the GitHub repository daymade/claude-code-skills (1,375 stars, last pushed yesterday), licensed MIT. It adds 269 tokens to every session and 4,332 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…