MarchTalk/ai-content-skills / skills/adversarial-gate
adversarial-gate
Verified独立上下文的怀疑式审核,两种模式,串行调用(不要并行起两个 Agent,会撞速率限制): · mode=judgment-stress(命题定稿后、写正文前)——起一个全新上下文的 agent, 对刚定稿的判断做压力对抗:逻辑链有没有断裂、有没有明显反例、是不是只停在表面没挖到机制/人性层、 是不是新瓶装旧酒。测的是论证站不站得住,不是立场讨不讨喜——反共识判断不因为"反共识"被扣分。 · mode=post-draft-audit(终稿、quality-gate 通过后)——独立上下文核验终稿有没有真的把判断往深处 逼了还是只是包装了已有想法(内容层面的谄媚检测),并核对 judgment-stress 阶段提出的质疑有没有 被真正解决,同时可选做结构查重(比对你自己的历史稿件记录)。 两种模式默认姿态:先假定平庸,除非稿子自己证明不是。禁止清单打勾式审查——每次质疑必须从这条内容本身 现场生成,不能套固定题库。 触发:/adversarial-gate、「压力对抗这个判断」「这条是不是谄媚我」「独立审核一下」、 写稿流程里命题定稿后/终稿质检后自动调用
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 14.0 KB |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |