据 AlphaMoat 统计,截至 2026-09,Adversarial Prompting 累计下载 4,056 次、获 4 个星标,在全部 5,078 个 AI 技能中排名第 2,510 位,在「AI 智能体」分类(969 个)中排名第 488 位。
| 平台 | 累计安装 | 累计下载 | 星标 | 评论 |
|---|---|---|---|---|
| ClawHub ↗ | 124 | 4,056 | 4 | - |
| SkillHub ↗ | 155 | 3,965 | 3 | — |
各平台的计数口径不同,统计时间不一致。
它按流程生成多个方案,检查弱点,提出并验证修正,再整理为排序建议。完整分析会自动保存到用户主目录;处理机密问题前应审阅导出步骤,并改为专用私有目录或选择性导出。 导出应使用专用私有目录,并避免文件名冲突或覆盖。
资料发布于 2026-10-27
以下是根据技能文档生成的示例,不代表实际运行结果。
2026-09 起统计方法调整:同名技能按作者分别统计,并覆盖全部技能。图中虚线为调整前的月份,与之后的数据不直接比较,也不计算跨越调整的增长。
| 月份 | 累计下载 | 环比 | 星标 |
|---|---|---|---|
| 2026-09 | 4,056 | — | 4 |
| 2026-08 | 3,905 | +5.7% | 3 |
| 2026-07 | 3,694 | +11.3% | 3 |
| 2026-06 | 3,320 | +5.5% | 3 |
| 2026-05 | 3,146 | — | 3 |
| 2026-03 | 2,535 | — | 3 |
以下是作者发布的原始文件,按纯文本显示,本站未做修改或审核;其中的链接不可点击,命令请核实后再运行。抓取于 2026-10-23。
--- name: adversarial-prompting description: Applies rigorous adversarial analysis to generate, critique, fix, and consolidate solutions for any problem (technical or non-technical). Use when facing complex problems requiring thorough analysis, multiple solution approaches, and validation of proposed fixes before implementation. --- # Adversarial Prompting This skill applies a structured adversarial methodology to problem-solving by generating multiple solutions, rigorously critiquing each for weaknesses, developing fixes, validating those fixes, and consolidating into ranked recommendations. The approach forces deep analysis of failure modes, edge cases, and unintended consequences before committing to a solution. ## When to Use This Skill
Use this skill when: - Facing complex technical problems requiring thorough analysis (architecture decisions, debugging, performance optimization) - Solving strategic or business problems with multiple viable approaches - Needing to identify weaknesses in proposed solutions before implementation - Requiring validated fixes that address root causes, not symptoms - Working on high-stakes decisions where failure modes must be understood - Seeking comprehensive analysis with detailed reasoning visible throughout Do not use this skill for: - Simple, straightforward problems with obvious solutions - Time-sensitive decisions requiring immediate action without analysis - Problems where exploration and iteration are more valuable than upfront analysis ## How to Use This Skill ### Primary Workflow When invoked, apply the following 7-phase process to the user's problem: #### Phase 1: Solution Generation Generate 3-7 distinct solution approaches. For each solution: - Explain the reasoning behind the approach - Describe the core strategy - Outline the key steps or components #### Phase 2: Adversarial Critique For each solution, rigorously identify critical weaknesses. Show thinking while examining: - Edge cases and failure modes - Security vulnerabilities or risks - Performance bottlenecks - Scalability limitations - Hidden assumptions that could break - Resource constraints (time, money, people) - Unintended consequences - Catastrophic failure scenarios Be creative and thorough in identifying what could go wrong. #### Phase 3: Fix Development For each identified weakness: - Propose a specific fix or mitigation strategy - Explain why this fix addresses the root cause - Describe how the fix integrates with the original solution #### Phase 4: Validation Check Review each fix to verify it actually solves the weakness: - Confirm the fix addresses the root cause - Check for new problems introduced by the fix - Flag any remaining concerns or trade-offs #### Phase 5: Consolidation Synthesize all solutions and validated fixes into comprehensive approaches: - Integrate complementary elements from different solutions - Eliminate redundancies - Show how solutions can be combined for stronger approaches - Present the final set of viable options #### Phase 6: Summary of Options Present all viable options in priority order, ranked by: - **Feasibility**: Can this actually be implemented with available resources? - **Impact**: How well does this solve the problem? - **Risk Level**: What could still go wrong? - **Resource Requirements**: Cost in time, money, and effort For each option, provide a one-paragraph summary highlighting key trade-offs. #### Phase 7: Final Recommendation State the top recommendation (single option or combination): - Clear rationale for why this is the best path - Concrete next steps for implementation - Key success metrics to track - Early warning signs to monitor for problems ### Output Format Present the complete analysis in three sections: 1. **Detailed Walkthrough**: Show all phases (1-5) with full reasoning visible 2. **Summary of Options**: Ranked list of viable approaches (Phase 6) 3. **Final Recommendation**: Top choice with implementation guidance (Phase 7) After presenting the analysis, automatically export the complete output to a markdown file using `scripts/export_analysis.py`. ## Implementation Notes - Show reasoning throughout the process for transparency - Be thorough in adversarial critique—surface uncomfortable truths - Validate fixes rigorously to avoid creating new problems - Consolidation should create stronger solutions, not just list options - Final recommendation should be actionable with clear next steps - Export results to markdown for future reference and sharing
把开发过程中的经验、错误与纠正记录为 Markdown 文件,供后续复用并晋升为工作区记忆。
用自然语言描述需求,在本地与远程技能市场里找技能并给出推荐的技能。
给 AI agent 用的浏览器自动化命令行技能。
把用户纠正与自我复盘沉淀成分层记忆、并按使用情况升降级的技能。
在安装第三方技能之前,按清单审查来源、权限与危险模式的技能。
把 agent 的记忆与跨技能状态存成带类型和约束的知识图谱的技能。
一份为 AI 代理规划主动跟进、工作记忆与复盘流程的工作区配置指南。
指导如何创建与更新有效 Claude 技能的写作指南。
数据月份:2026-09 · 下载/星标/安装数聚合自公开技能注册库(ClawHub、SkillHub),按月更新。口径说明见数据方法。