lov-feedback-loop SKILL.md skillA
lov-feedback-loop from lovstudio/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add lovstudio/skills/lov-feedback-loop@v0.3.0Pins v0.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- lovstudio/skills
- Path
skills/feedback-loop/SKILL.md- Versions recorded
- 2
- Latest version
- v0.3.0, committed Sep 11, 2026
- First version recorded
- Sep 11, 2026
- Size
- 6,399 bytes
- Repository stars
- 72
- License
- MIT
把用户对 Agent 的被动情绪与主动点赞、点踩、评分变成可统计的反馈事件， 按任务、技能、规则、全局 Prompt 的最小作用域迭代，并生成满意度复盘报告。 Use when the user rates a run, asks for satisfaction stats, or installs the feedback loop into another agent.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 反馈飞轮 · Feedback Flywheel 四个用户可见的入口：评价、回扫、复盘、接入。 自动链路（情绪感知 → 落账 → 规则迭代）不经过 skill 路由，由根 Prompt 的 反馈与迭代规则加上 `references/protocol.md` 直接驱动；本 Skill 提供主动入口， 同时为自动链路提供协议与脚本。 ## Triggers ### Activate when - 用户对上一轮结果表态：“做得很棒”“太差了”“还是不行”“这次可以”。 - 用户主动 judge：`👍`、`👎`、`❤️`、`🎉`、`🤔`、“这次我给 4 分”、“rate this run”。 - 用户要回扫：“回扫我最近的会话，找出还没闭环的不满”。 - 用户要看统计：“给我一份满意度报告”“看看我最近对 AI 哪里不满意”。 - 用户要接入：“把反馈飞轮装进我的 AI”“install the feedback loop into my agent”。 ### Do not activate when - 用户只是在描述常规业务需求，没有对结果表态；直接执行原任务。 - 用户要长期记住偏好而不是评价本轮结果；交给记忆或 Profile 机制。 ## 能力与脚本 | 入口 | 做什么 | 脚本 | | --- | --- | --- | | 评价 | 表情、短评、打分归一成事件，回一行收据 | `scripts/feedback_store.py append` | | 回扫 | 从会话 JSONL 提取用户消息，供判定 | `scripts/scan_session.py` | | 复盘 | 趋势、未闭环清单、修复时长 | `scripts/report.py` | | 接入 | 托管块 + 技能链 + 账本，先 dry-run | `scripts/install_feedback_loop.py` | 判定口径、作用域阶梯与状态机见 [references/protocol.md](references/protocol.md)， 字段定义见 [references/store-schema.md](references/store-schema.md)， 宿主路径见 [references/host-adapters.md](references/host-adapters.md)。 ## Workflow (MANDATORY) ### Step 0: 定位 - 在 Skill 根目录运行脚本；账本默认 `~/.feedback-loop/`，可用 `FEEDBACK_LOOP_HOME` 或 `--store` 覆盖（`--store` 写在子命令前后都可以）。 …
Read the whole file at its exact version.
How to install
mdr add lovstudio/skills/lov-feedback-loop@sha256:eda022057061a4b5The line at the top of this page pins the label v0.3.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_lry5bida3z2wcnrn)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Sep 11, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.3.0 latest | 2026-09-11 | 5a85428 | 6,399 B | A | view · diff |
| v0.2.0 | 2026-09-11 | e646ad3 | 2,481 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6399 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
lovstudio/skills · 72 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lry5bida3z2wcnrn GET https://markdownregistry.com/api/v1/resolve?ref=lovstudio/skills/lov-feedback-loop GET https://markdownregistry.com/api/v1/blob/eda022057061a4b5955fc856813d2979b5365d718b4626b9c3c99cb50e9f0a71
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.