Memory Lint
Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project state, duplicate / conflicting feedback rules, naming violations, frontmatter gaps, and oversized files. Phase 1 is a read-only scan and report. Phase 2 applies fixes only for findings the user explicitly picks. Phase 3 verifies with an independent process and rolls back if it fails.
Install
npx skills add KerberosClaw/kc_ai_skills --skill memory-lintgit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills.git /tmp/kc_ai_skills
mkdir -p ~/.claude/skills
cp -r /tmp/kc_ai_skills/memory-lint ~/.claude/skills/memory-lintPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# memory-lint — Memory 品質健檢
```
Phase 1 唯讀掃描 ──► 報告(預設只做這段,不動任何檔案)
│ user 逐條拍板要修哪些
Phase 2 執行修正 ──► commit(開工前先記回退點)
│ 改完全部提交 = 凍結
Phase 3 獨立複驗 ──► 過 → 收工 / 不過 → 回退到 Phase 2 前
```
🔴 **收到 lint 觸發詞的預設動作是出報告。** user 必須明確點名要修哪幾條
(或明說「全部修掉」)才准進 Phase 2。Phase 1 期間不准順手合併、順手刪、順手歸檔。
**跟 llm-wiki-lint 差異**:本 skill 針對 memory 目錄(prefix-based 平鋪結構);
`llm-wiki-lint` 針對 Karpathy LLM Wiki repo(`wiki/` + `raw/` + `SCHEMA.md` 三層)。
---
# Phase 1 — 唯讀掃描
## Step 1: 找到 memory 目錄
依序嘗試,命中第一個就用:
| 順序 | 來源 |
|------|------|
| 1 | `$ARGUMENTS` 第一個位置參數 |
| 2 | 環境變數 `$CLAUDE_MEMORY_DIR` |
| 3 | `settings.json` 的 `autoMemoryDirectory` |
| 4 | `~/.claude/memory/` |
| 5 | 都找不到 → **停止**,告訴 user「偵測不到 memory 目錄」,不要瞎猜 |
第 3 條要看**當前設定目錄**(多帳號並存時 `$CLAUDE_CONFIG_DIR` 會指到別處):
```bash
CFG="${CLAUDE_CONFIG_DIR:-$HOME/.claude}"
MEMORY_PATH=$(jq -r '.autoMemoryDirectory // empty' "$CFG/settings.json" | envsubst)
```
## Step 2: 跑機械掃描
```bash
# <skill_dir> = 本 SKILL.md 所在的目錄;掃描標的由參數帶入,
# 所以在哪個工作目錄呼叫都不影響結果
python3 <skill_dir>/scripts/scan.py "$MEMORY_PATH"
```
只用標準函式庫、唯讀、輸出 JSON。**目標目錄由參數帶入**,所以在哪個工作目錄呼叫都一樣。
沒有 `MEMORY.md` 會回 `{"fatal": ...}` 並以 exit 1 結束。
腳本已經處理掉幾個會讓檢查靜默失效的坑,**不要自己在對話裡改寫成 shell 一行流**:
- 不用 shell glob(zsh 未匹配 glob 會在指令執行前中止,而且 `2>/dev/null` 擋不住)
- 不用固定路徑暫存檔(並行執行會互相覆蓋、失敗留髒資料)
- 不 import 第三方套件(唯讀階段不該動 user 的 Python 環境;離線環境也裝不了)
- `[[...]]` 掃描先剝掉 fenced 與行內 code,且**檔名與 frontmatter `name` 兩種都算解析成功**
- 索引目標的 `./` 前綴會正規化
輸出欄位:
| 欄位 | 意義 |Details
- Skill name
memory-lint- Repository
- KerberosClaw/kc_ai_skills
- Path
memory-lint/SKILL.md- License
- MIT
- Repo updated
- 14 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Memory Lint skill do?
Use when the user wants to lint a Claude Code memory directory (~/.claude/memory or custom path) for index inconsistency, broken cross-links, stale project state, duplicate / conflicting feedback rules, naming violations, frontmatter gaps, and oversized files. Phase 1 is a read-only scan and report. Phase 2 applies fixes only for findings the user explicitly picks. Phase 3 verifies with an independent process and rolls back if it fails.
How do I install the Memory Lint skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add KerberosClaw/kc_ai_skills --skill memory-lint. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Memory Lint popular?
It lives in KerberosClaw/kc_ai_skills, which has 80 GitHub stars and 13 forks, and is included in 1 curated skill list.
Related skills
Adr
80KerberosClaw/kc_ai_skills
Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or rewriting historical decisions; preserve their text, allow evidence-backed current-state notes, and record change
Align
80KerberosClaw/kc_ai_skills
Reconcile existing repository documentation with the current implementation, especially after verified hotfixes or after QA in an unattended task. A manual run first asks whether to align only the docs a specific change touched (trigger scope) or rescan the whole repo; unattended runs use the scope the dispatch states and default to the whole repo. Follow cross-repo references for evidence; edit only documentation in the authorized repo, annotating conflicting historical records. Not for fixing code, deploying, inventing requirements, or building a new documentation suite.
Character Lora
80KerberosClaw/kc_ai_skills
Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.
Permissioning CI Workflows
115wdm0006/python-skills
Give a CI job exactly the credentials it needs and know when it has none — declaring `permissions:` explicitly because the default GITHUB_TOKEN scope is a repo setting, reading the 403's x-accepted-github-permissions header instead of guessing the missing scope, one API call needing two scopes, a fork pull request getting a read-only token and no repository secrets, event-conditioned steps that skip on the re-run and turn a job green without fixing it, why `pull_request_target` is not the workaround, and preferring a check that needs no credential at all. Use when a workflow step comments on a
Productionize App with Services
107Dimon94/skills
Productize a working prototype by adding a bounded set of explicitly requested operational or product services. Use only when the user asks for a broad productization pass or names product-service gaps such as permissions, API access, audit history, admin operations, or production operability as the primary task. Do not trigger for ordinary feature work, a single service integration, generic "make this production ready" phrasing without concrete scope, or routine security, observability, testing, and release tasks covered by narrower skills.
Prd Create
80KerberosClaw/kc_ai_skills
Use when user wants to draft a PRD (Product Requirements Document) from raw input (meeting transcripts, hand-waved descriptions, scattered decisions). Workflow: load org's PRD Guideline + writing discipline → lock execution mode (human-run vs unattended-agent-run) → ingest raw input → quiz user numbered-list iterate to fill §1-§15 → draft v0.1 → handle stakeholder merge (review feedback, surface conflicts) → lock v1.0 + sanitize per ADO publication contract → publish to ADO Wiki. For an agent-run PRD, §13 carries the unattended-execution discipline (machine-checkable AC + traffic-light + 3-exi
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.