技能列表

Structured improvement system for learnable skills (programming, design, languages, instruments). Use when tracking progress, identifying bottlenecks, or optimizing practice routines for any skill you want to master.

Unlock dramatically better AI responses by automatically diagnosing and elevating prompt quality. Use this skill when the user wants more accurate, actionable, or rigorous answers—especially when their request is vague, underspecified, or missing critical context. Applies a silent 10-point quality checklist covering output clarity, methodology fit, information completeness, success criteria, and more. If the prompt passes, answer directly. If not, enter Enhancement Mode: surface specific gaps wi

Documentation-first skill and workflow toolkit for intent-based security. Provides templates, examples, and local helper scripts for capturing intent, reviewing actions, documenting rollbacks, and recording learnings. Use when: (1) designing or prototyping intent validation workflows, (2) documenting high-risk operations, (3) creating audit trails and rollback records, (4) building your own runtime enforcement layer.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you discover a better approach; (5) the user explicitly installs or references the skill for the current task.

>

LLM 通用内部自裁决技能。在关键节点判断"当前这一层最优的下一步动作是什么"，再让主链继续执行。触发条件：(1) 路径分叉时——多个可行方案且无明显优先级；(2) 高代价动作前——搜索/生成/发布等消耗军费或不可逆操作；(3) 连续两步无明显增益时——进展停滞、输出质量未提升。禁止：改写主任务、输出并列动作、长篇规划、变成审批器、连续两轮要求补资料。适用于战略分析/搜索补全/研究/代码/多步工作流等agent。

增强型自我进化技能，集成自动技能提取、根因分析、知识图谱、跨会话同步、自动晋级机制。触发词：'总结这个经验'、'保存为技能'、'自我进化'、'学习这个'、'记录教训'。相比原版self-improving-agent，新增自动提取、多维度分析、进化追踪功能。

Autonomous self-improvement engine that learns from interactions, identifies patterns, and evolves behavior over time. Use when: (1) Analyzing interaction patterns for improvement, (2) Running periodic self-assessment, (3) Extracting reusable patterns from workflows, (4) Optimizing decision-making processes, (5) Integrating feedback into behavioral changes. Triggers on '自我进化', 'self-evolution', '自我改进', '学习模式', 'pattern analysis', 'optimize behavior'.

多 agent 自我进化系统，自动记录学习、错误和功能需求，支持多 agent 统计和自动提升

>-