Skip to content
Agentmart
Submit a tool

memory-distill

Learn from user feedback to improve future content.

Skill by alextangson

IndexedMIT★ 10
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/alextangson-memory-distill

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Learn from user feedback to improve future content. Activate when user approves, rejects, edits, or gives feedback on topics or content drafts. Also runs periodically to consolidate learnings.

Use cases: writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/memory-distill

What's inside

Skill name
memory-distill
Description
Learn from user feedback to improve future content. Activate when user approves, rejects, edits, or gives feedback on topics or content drafts. Also runs periodically to consolidate learnings.
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# 记录创作者反馈

把用户对这篇稿的真实评价与修改要求保留下来,避免下一轮又犯同样的问题。模型审稿结论不能冒充用户反馈。

1. 用户说“好”时先识别对象:可能是在同意继续、选角或确认理解,不自动当作成稿采纳。仅明确评价当前稿件时记录 verdict。
2. 对目标稿调用 `autocrew_editorial {action:"inspect", content_id}`,读取当前 `draft_hash` 与已有反馈,确保意见指向用户正在看的版本。
3. 使用一次稳定的 `event_id`,带原话与准确范围提交:

```json
{
  "action":"feedback",
  "content_id":"…",
  "draft_hash":"…",
  "event_id":"feedback-20260922-01",
  "feedback":"用户的原话",
  "scope":"draft",
  "user_confirmed":true
}
```

调用 `autocrew_editorial`,event_id 只用字母、数字、下划线或连字符;示例标识应换成这次反馈的唯一稳定值。重试复用同一 event_id 和同一载荷;不要每轮轮询都造新反馈。稿件已经变化时重新 inspect 并确认意见仍对应新版本,不把旧稿认可套到新稿。

4. 范围:默认 `draft`,只约束当前文章。“以后小红书都这样”才用 `platform` 并带正确 platform;用户明确说跨平台的长期表达才用 `voice`。本篇“短一点”不能自动变成永久偏好。
5. 仅按用户明确结果设置 `verdict`:`adopted`(直接能用)、`light_edit`(小改能用)、`rewritten`(基本重写)、`rejected`(打回)。不从模型分数、工具成功或发布数据推定采纳。
6. 读取返回结果,说明记录了哪条、作用哪里;如没有成功,不能说“我已记住”。反馈不自动等于改稿或批准发布;需要改稿时保留该反馈进完整 requirements,带原 content_id、topic_id、platform 和 force:true 重新领包并按 `write-script` 提交,保留同一篇稿件。

创作者档案和校准走 `autocrew_editorial profile/update_profile`;不直接追加本地 MEMORY 或 profile 文件。性能表现只作为带来源的数据事实,单篇高赞不能证明某种写法普遍有效。

From alextangson/AutoCrew, MIT.

More from alextangson/AutoCrew

Signals

Stars
10
Forks
2
Open issues
0
Last commit (this folder)
Sep 25, 2026 (1 month ago)
Last release
Oct 2, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from alextangson

Cite this page

memory-distill skill. Agent Mart. https://agentmart.dev/skills/alextangson-memory-distill (last updated 2026-10-24)