hello-reflect
SkillDocs & knowledgeUse after completing a task, generates a session reflection, extracting lessons learned and appending them to the relevant module documentation for reference in future sessions.
Use hello-reflect in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add hello-reflect and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the hello-reflect skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by hellowind777/helloagents in skills/hello-reflect/SKILL.md and read by ahel’s review.
任务完成后,执行会话反思。
触发条件
以下场景完成后应生成反思(kb_create_mode ≥ 1 时):
- 经历了 2+ 次验证循环才通过
- 调试超过 3 次尝试才修复
- 执行过程中方案发生变更
- 用户纠正了错误的假设或方向
反思产出
将反思内容追加到相关 modules/*.md 的"经验"章节(增量追加,不重写)。
追加格式:
- [{日期}] {经验教训} — 背景: {什么有效/什么失败的简述}
如果涉及多个模块,分别追加到各自的 modules/*.md。 如果不属于任何特定模块(如项目级经验),追加到 context.md 末尾新增的"## 经验"章节。
质量要求
- 经验教训必须是抽象指导,不是具体代码模板(具体模板会导致 AI 锚定在错误细节上)
- 每条经验 ≤2 行,精简有力
- 只记录真正有价值的发现,不记录显而易见的事情
交付检查
- 经验已追加到相关 modules/*.md 的经验章节
- 经验教训是抽象指导而非具体模板
- 适用场景从上下文可推断
Signals
- GitHub stars
- 704
- Forks
- 97
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
hello-reflect- Source
- github.com/hellowind777/helloagents
github.com/hellowind777/helloagents
Related picks
Skill · larksuite
The pick for Markdownmarkdown-formatter
Skill · nvidia
The pick for Markdownhandoff
Skill · mattpocock
More in Docs & knowledgecanvas-design
Skill · anthropics
More in Docs & knowledgedoc-coauthoring
Skill · anthropics
More in Docs & knowledgepopups
Skill · coreyhaines31
More in Docs & knowledge