memory-hygiene SKILL.md skillA

memory-hygiene from hsuanyulee/polaris is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hsuanyulee/polaris/memory-hygiene@v1.1.0

Pins v1.1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hsuanyulee/polaris
Path
.claude/skills/memory-hygiene/SKILL.md
Versions recorded
5
Latest version
v1.1.0, committed Aug 28, 2026
First version recorded
Aug 6, 2026
Size
5,723 bytes
Repository stars
5
License
MIT

Manual memory tiering — classify Hot/Warm/Cold, review candidates, and migrate MEMORY.md index + memory files. Use when the session-start advisory fires, MEMORY.md Hot grows past 15 entries, or you want a periodic cleanup. Trigger "memory-hygiene", "整理記憶", "memory 降級", "/memory-hygiene", "decay scan", "tier memory". 記憶要整理:MEMORY.md 的 Hot 區長太長、session 開場的提醒跳出來、或想定期清一次。 例如「整理記憶」「memory 降級」「decay scan」。 不用於:寫一則新記憶(那直接寫)、找一則舊記憶(那直接讀)。.

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

# Memory Hygiene

`memory-hygiene` 是 manual memory tiering:檢查 Hot / Warm / Cold,產生 demotion
candidate,並在使用者確認後搬移 memory files 與更新 index。

## Contract

這是 memory maintenance skill,不是一般 task planning。Scan / dry-run 只讀;apply 會寫
workspace memory,因此必須先有本 session 的 dry-run 結果與使用者明確確認。

## Mode Routing

| User says | Mode | Reference |
|---|---|---|
| `/memory-hygiene`, `memory-hygiene`, default | scan | `memory-hygiene-scan-flow.md` |
| `dry-run`, `full report`, `看看所有分類` | dry-run | `memory-hygiene-scan-flow.md` |
| `apply`, `搬檔`, `執行`, `migrate` | apply | `memory-hygiene-apply-flow.md` |
| `retire`, `退休`, `清掉做完的`, `過期的 memory` | retire | 見〈退休〉 |

## 退休:記進度的 memory,在它記的工作收斂之後就走

```bash
python3 .claude/skills/memory-hygiene/scripts/memory-hygiene-tiering.py retire \
  --memory-dir {memory_dir}            # 預覽,什麼都不動
python3 .claude/skills/memory-hygiene/scripts/memory-hygiene-tiering.py retire \
  --memory-dir {memory_dir} --execute  # 真的搬
```

**分層不是退休。** Hot → Warm 只是換一個資料夾躺著,索引還是指得到它。退休問的是另一
個問題:這份東西記的工作還活著嗎。`type: project` 記的是「現在做到哪」,那件工作收斂之後
它就不再是任何人的下一步了。

判定的依據是**那張單自己的狀態**(`{單}/.spine/loop-state.json` 的 `status`),不是誰記得
要來清——這一層已經有兩個手動退休到一半就停下來的資料夾。單號從 `snapshot_of` 或檔名取,
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hsuanyulee/polaris/memory-hygiene@sha256:24a36fd116842f79

The line at the top of this page pins the label v1.1.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_yp7a4r6d3iygtuer.svg)](https://markdownregistry.com/a/art_yp7a4r6d3iygtuer)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between Aug 6, 2026 and Aug 28, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
v1.1.0 latest2026-08-28 a2bd2a4 5,723 BA view · diff
v1.1.02026-08-24 e610d9d 5,720 BA view · diff
v1.1.02026-08-09 834f192 5,721 BA view · diff
v1.1.02026-08-08 af2f973 5,703 BA view · diff
v1.1.02026-08-06 40ab862 5,179 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5723 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

GitHub

hsuanyulee/polaris · 5 stars · license MIT · pushed 2026-10-20 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_yp7a4r6d3iygtuer
GET https://markdownregistry.com/api/v1/resolve?ref=hsuanyulee/polaris/memory-hygiene
GET https://markdownregistry.com/api/v1/blob/24a36fd116842f7931ab6dcb96e574b5a99f9306bcc033c18616263e9443d7c6

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.

More from hsuanyulee/polaris

check-your-own-work SKILL.md skill
hsuanyulee/polaris · .claude/skills/check-your-own-work/SKILL.md · Before handing your own change over — opening a PR, asking for review, saying "done" — check it against nine questions…
v1.0.0 · audit A · 5 stars
checkpoint SKILL.md skill
hsuanyulee/polaris · .claude/skills/checkpoint/SKILL.md · 保存、恢復、列出長 session checkpoint;記錄 branch、ticket、todo、recent activity,方便中斷或 context compression 後接續。 session…
v1.2.0 · audit A · 5 stars
command-post SKILL.md skill
hsuanyulee/polaris · .claude/skills/command-post/SKILL.md · Commander mode: use when one session commands the other Claude sessions on this machine — to read the map of who holds…
git:20261020.908921c · audit A · 5 stars
driving-work-to-done SKILL.md skill
hsuanyulee/polaris · .claude/skills/driving-work-to-done/SKILL.md · 把一件工作從「有人說了一句話」帶到「judged 過的交付」:先判斷要不要立案,再決定現在 該在 refinement / engineering / verify-ac…
v1.0.0 · audit A · 5 stars
engineering SKILL.md skill
hsuanyulee/polaris · .claude/skills/engineering/SKILL.md · 已經有凍結的 assertion、要開始或繼續施工時的站。兩個關卡之間的 loop:探索、實作、換量測、推進輪次。這裡沒有關卡。 某張單的 assertion 已經凍結,接下來要動手做的時候,或剛從 refinement…
v3.0.0 · audit A · 5 stars
framework-self-dev SKILL.md skill
hsuanyulee/polaris · .claude/skills/framework-self-dev/SKILL.md · 在框架自己身上施工時要知道的事:一張框架單怎麼開。兩種單——舉發實作途中撞到的問題、 開發框架新功能——開單那一刻問的格子不一樣,而舉發那一種要先看過還沒出去的單裡有沒有 同一件。 要改的東西是這套流程自己(skill、它們的腳本、常駐規…
v1.0.0 · audit A · 5 stars
learning SKILL.md skill
hsuanyulee/polaris · .claude/skills/learning/SKILL.md · "Use when the user wants to learn from external resources (URLs, repos, articles), extract patterns from merged PRs…
v3.1.0 · audit A · 5 stars
pr-pickup SKILL.md skill
hsuanyulee/polaris · .claude/skills/pr-pickup/SKILL.md · Slack collaboration layer: extracts PR URLs from Slack messages, hands the PR over to be fixed, then reports back to…
v1.0.0 · audit A · 5 stars
refinement SKILL.md skill
hsuanyulee/polaris · .claude/skills/refinement/SKILL.md · 流程的第一站,也是第一個關卡:把「怎麼算成功」談成人簽得下去的 assertion,凍結起來。由 driving-work-to-done 在判定要立案之後帶進來。 driving-work-to-done…
v3.0.0 · audit A · 5 stars
request-pr-review SKILL.md skill
hsuanyulee/polaris · .claude/skills/request-pr-review/SKILL.md · "把使用者名下已經開好的 PR 蒐集起來、帶回每一個的 review 狀態、列出來讓他決定要請誰看,然後通知對的人。Trigger: '我的 PR', 'request PR review', 'ask someone to review…
v4.0.0 · audit A · 5 stars
review-inbox SKILL.md skill
hsuanyulee/polaris · .claude/skills/review-inbox/SKILL.md · "Use when the user wants to discover and review PRs across the team awaiting their attention. NOT for a single specific…
v3.0.0 · audit A · 5 stars
review-pr SKILL.md skill
hsuanyulee/polaris · .claude/skills/review-pr/SKILL.md · Review someone else's PR as a code reviewer: read the PR diff, check against .claude/rules, leave inline comments on…
v2.1.0 · audit A · 5 stars

Every file in hsuanyulee/polaris

Other files named memory-hygiene

memory-hygiene SKILL.md skill
huytieu/cog-second-brain · skills/memory-hygiene/SKILL.md · Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims…
git:20260807.b852369 · audit A · 1,305 stars
memory-hygiene SKILL.md skill
huytieu/cog-second-brain · .claude/skills/memory-hygiene/SKILL.md · Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims…
git:20260710.9001d4c · audit A · 1,305 stars
memory-hygiene SKILL.md skill
huytieu/cog-second-brain · .agents/skills/memory-hygiene/SKILL.md · Periodic trust sweep of persistent memory and durable knowledge notes - re-verifies environment-dependent claims…
git:20260730.acf9b42 · audit A · 1,305 stars
memory-hygiene SKILL.md skill
chrono-meta/forge-harness · plugins/fh-meta/skills/memory-hygiene/SKILL.md · Detects "stale-but-confident" memory entries — facts that were once verified but have silently drifted. Scans…
git:20260811.eede7ad · audit A · 30 stars
memory-hygiene SKILL.md skill
pr-e/openclaw-master-skills · skills/memory-hygiene/SKILL.md · Audit, clean, and optimize Clawdbot's vector memory (LanceDB). Use when memory is bloated with junk, token usage is…
git:20260311.3e83cee · audit B · 3 stars

Browse by kind, by grade A, or by owner.