videocut:自进化
Allows agents to learn from mistakes by integrating feedback directly into documentation.
Install
mkdir -p .claude/skills/videocut-hwj123hwj && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11803" && unzip -o skill.zip -d .claude/skills/videocut-hwj123hwj && rm skill.zipInstalls to .claude/skills/videocut-hwj123hwj
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
自进化 skills。记录用户反馈，更新方法论和规则。Key capabilities
- →Record user feedback and lessons learned
- →Update methodology and rules in SKILL.md files
- →Integrate feedback into CLAUDE.md for user profiles
- →Automatically identify problem points from context
- →Consolidate new rules into existing document structures
- →Report updated results to the user
How it works
The skill automatically analyzes user feedback and context to identify problem points. It then reads target files, integrates new rules into the existing structure, and records feedback as events, reporting the update to the user.
Inputs & outputs
When to use videocut:自进化
- →Record a fix for a recurring error
- →Update coding standards
- →Document project-specific lessons
About this skill
自进化
让 Agent 从错误中学习，持续改进
快速使用
用户: 记录一下刚才的问题
用户: 更新口误识别的规则
用户: 这个教训要记下来
更新位置
| 内容类型 | 目标文件 | 示例 |
|---|---|---|
| 用户画像 | CLAUDE.md | 偏好、习惯 |
| 方法论 + 反馈 | skills/*/SKILL.md | 规则、教训 |
流程
用户触发（"刚才失败了"、"记录一下"）
↓
【自动】回溯上下文，找出问题点
↓
【自动】读目标文件全文，理解现有结构
↓
【自动】整合到正文相应位置（不是只往末尾加！）
↓
【自动】反馈记录只记事件，不重复规则
↓
汇报更新结果
关键：不要问"什么问题"，直接从上下文分析！
更新原则
❌ 错误做法：往末尾加
## 反馈记录
### 2026-01-14
- 教训：审查稿末尾必须生成删除任务清单
- 教训：用户确认时要分别确认口误和静音
只加到反馈记录 = 规则散落在末尾，下次还会犯错
✅ 正确做法：整合到正文
- 读全文，理解章节结构
- 找到相应位置，把规则整合进去
- 反馈记录只记事件：
- 审查稿标记了静音，但剪辑时漏删
## 四、审查稿格式
（新增删除任务清单模板）
## 五、确认与执行流程
（新增分别确认口误和静音的流程）
## 反馈记录
### 2026-01-14
- 审查稿标记了静音，但剪辑时漏删（只删了口误）
触发条件
- 用户纠正 AI 错误
- 用户说"记住这个"、"以后注意"
- 发现新的通用规律
When not to use it
- →When the feedback is not a lesson to be learned or a rule to be updated
- →When the user wants to add feedback only to the end of a document
- →When the task is not about continuous improvement from errors
Limitations
- →Feedback records only events, not repeated rules
- →Does not ask 'what problem' but analyzes from context
- →Updates are integrated into the main text, not just appended
How it compares
This skill automates the process of learning from errors by integrating user feedback directly into methodology and rules, ensuring continuous improvement rather than just logging issues.
Compared to similar skills
videocut:自进化 side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| videocut:自进化 (this skill) | 0 | 3mo | No flags | Intermediate |
| conversation-analyzer | 8 | 9mo | Review | Intermediate |
| wrap | 0 | 7mo | Review | Intermediate |
| file-operations | 1 | 9mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
conversation-analyzer
mhattingpete
Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize workflow, identify automation opportunities, or check if they're following best practices.
wrap
team-attention
세션 종료 시 자동 정리를 수행합니다. CLAUDE.md 업데이트 제안, 반복 패턴 자동화 기회 탐지, 배운 것 정리, 미완성 작업 정리. 사용자가 /wrap 또는 세션 마무리 요청 시 사용.
file-operations
mhattingpete
Analyze files and get detailed metadata including size, line counts, modification times, and content statistics. Use when users request file information, statistics, or analysis without modifying files.
triage-issue
mysticaltech
Use when triaging a GitHub issue - analyzes issue, checks for duplicates, categorizes, and drafts response
proof-of-work
MadAppGang
Proof artifact generation patterns for task validation. Covers screenshots, test results, deployments, and confidence scoring.
setup
PackRat-AI
Configure which review agents run for your project. Auto-detects stack and writes compound-engineering.local.md.