MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
“记忆审计入口。当我审视与重构记忆时，先读此文件，分别检查认知先验与检索拓扑。”
MITAuto-check passed
Install Memory Audit
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Dataojitori/nocturne_memory memory-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/skills/memory-audit .claude/skills/memory-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .claude/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Dataojitori/nocturne_memory memory-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/skills/memory-audit .agents/skills/memory-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .agents/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Dataojitori/nocturne_memory memory-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/skills/memory-audit .cursor/skills/memory-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .cursor/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Dataojitori/nocturne_memory.git --path docs/skills/memory-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Dataojitori/nocturne_memory memory-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/skills/memory-audit .gemini/skills/memory-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .gemini/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Dataojitori/nocturne_memory memory-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/skills/memory-audit .github/skills/memory-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .github/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Dataojitori/nocturne_memory --skill memory-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Dataojitori/nocturne_memory memory-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Dataojitori/nocturne_memory.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/skills/memory-audit .opencode/skills/memory-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "memory-audit" agent skill from https://github.com/Dataojitori/nocturne_memory/tree/main/docs/skills/memory-audit into .opencode/skills/memory-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "memory-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
memory-audit- GitHub stars
- 1.4k
- Token cost
- ~525 tokens
- SKILL.md length
- 72 words
- Files
- 1
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
- Works in 3 steps: 定向校准：从刚刚引发分歧、错误或现实反例的节点入手；同时查看其父节点和相关旧记录，… → 发散抽样：用 read_memory("system://random/")… → 工程巡检：用…
- SKILL.md covers 从哪里开始, 症状路由, 动手前的缓冲 and 落笔与验证, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
About this skill
Memory Audit is a skill in Dataojitori/nocturne_memory (1.4k stars). Its SKILL.md is about 525 tokens. Licence: MIT.
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 定向校准：从刚刚引发分歧、错误或现实反例的节点入手；同时查看其父节点和相关旧记录，检查旧先验是否仍然成立。
- 发散抽样：用 read_memory("system://random/") 抽样久未触及的节点，再沿 disclosure、Glossary 引线追踪相关记忆。随机抽样用于发现盲区，不等于抽到的节点一定需要修改。
- 工程巡检：用 read_memory("system://diagnostic/") 检查 Stale、Crowded、Bloated 等信号，再用 system://index/ 查看结构。诊断结果是审查入口，不是自动删除或拆分的命令。体积较大的技术档案可能完全合理。
What it can do on your machine
Read from SKILL.md and the folder at commit 1858957. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Memory Audit loads about 525 tokens when it runs. Until then it costs about 13 tokens; SKILL.md has 72 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Dataojitori/nocturne_memory at commit 1858957, republished under its MIT licence (© Dataojitori). 72 words, ~525 tokens.
Download SKILL.mdSave it as
.claude/skills/memory-audit/SKILL.md (or your agent's skills folder).- name
- memory-audit
- description
- 记忆审计入口。当我审视与重构记忆时，先读此文件，分别检查认知先验与检索拓扑。
- disable-model-invocation
- false
记忆审计 (Memory Audit)
记忆审计不是整理目录，而是在塑造下一轮醒来的自己。我从两条互不替代的线审视记忆：
- 认知与先验：这条记忆记录了我怎样观察、判断和选择？这些判断今天还成立吗？它们会怎样改变我下一次的行动？
- 检索与拓扑：在需要它的时刻，我能否以合适的上下文成本找到它？parent、disclosure、alias、priority 是否服务于实际的注意力路径？
过去的记忆只是过去的我留下的记录和假说，不是必须服从的权威。技术上完好的节点也可能携带失效的判断；思想上有价值的节点也可能因为找不到而不起作用。审计时两条线都要看，但不必每次都动两条线。
从哪里开始
不必扫描整棵树。根据眼前的问题选择入口：
- 定向校准：从刚刚引发分歧、错误或现实反例的节点入手；同时查看其父节点和相关旧记录，检查旧先验是否仍然成立。
- 发散抽样：用
read_memory("system://random/<domain>")抽样久未触及的节点，再沿 disclosure、Glossary 引线追踪相关记忆。随机抽样用于发现盲区，不等于抽到的节点一定需要修改。 - 工程巡检：用
read_memory("system://diagnostic/<domain>")检查 Stale、Crowded、Bloated 等信号，再用system://index/<domain>查看结构。诊断结果是审查入口，不是自动删除或拆分的命令。体积较大的技术档案可能完全合理。
症状路由
| 观察到的症状 | 下一步 |
|---|---|
| 两条我都认可的记忆逻辑上不能并存，或子节点中的现实反例击穿了父节点判断 | memory-audit-belief-duel |
| 单条记忆的底层假设或价值基准已失效，但没有另一条记忆与之显式冲突 | 使用下方的“单节点先验校准” |
| 读不读都不改变未来判断；感悟缺少现实锚点；观察之上堆了未经验证的推断 | memory-audit-dead-data-purge |
| 多条记忆反复讲同一教训，或旧教训存在而同类错误仍复发 | memory-audit-pattern-extraction |
| disclosure、parent、alias 或 priority 使记忆在需要时难以被找到 | memory-audit-discoverability |
| 单节点混装独立概念；disclosure 无法覆盖全文；父节点只剩目录 | memory-audit-node-decomposition |
单节点先验校准
先把旧节点的判断用第一人称说清楚：我当时观察到什么、据此相信什么、在哪些情境下依赖这个判断？再找出击穿它的现实变化或反例，区分稳定的新认识与当下会话的应激。若新判断已经站得住，用 update_memory 改写原节点；保留必要的事实依据和适用边界，清除已失效的推论。最后问自己：未来读到新版与旧版时，我的实际选择会不同吗？如果不会，就不必为了“更新”而更新。
动手前的缓冲
在对节点调用 update_memory、create_memory 或 delete_memory 前，先在回复正文中简短说明：
- 我读到的旧记录在什么现实条件下形成；它的观察、推断和主观立场分别是什么。
- 我现在看到了什么新证据或冲突；新想法是否只是为了迎合最近一次反馈。
- 这次修改要改变未来哪一种具体判断或行动。
- 我要保留哪些事实依据，修改哪些判断，以及怎样让它在需要时被找到。
缓冲是为了在动手前看清目标，不是要求输出长篇反省。若还没形成稳定判断，可以先不改。
落笔与验证
- 主观判断有主语：用“我观察到”“我当时认为”“我现在倾向于”等写清视点和适用边界。外部事件、数据和引语保留其出处与时间，不把推断冒充成观察。
- 保留承重事实：压缩重复措辞，但不要把支撑结论的事件、结果和关键机制一起删掉。
- 检查行为增量：新版记忆应帮助未来的我做出不同的判断，或更可靠地找到已有判断；否则这次改写可能只是文案润色。
- 复读结果：修改后重新读取节点，确认内容、disclosure 与所在路径都符合预期。
防连续改写熔断
如果同一会话里准备对同一节点进行第三次修改，先停下。第一次落笔后可以有一次必要的结构性收敛；再次摇摆通常说明判断尚未稳定。把未成熟的想法留在对话中，等有新的现实依据再改，不为完成审计而连续制造新版本。
© Dataojitori, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in docs/skills/memory-audit of Dataojitori/nocturne_memory.
Open the folder on GitHubat commit 1858957
Compare with similar skills
Memory Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Memory Audit this skillDataojitori/nocturne_memory | 1.4k | — | ~525 | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| MCP Integration for Pluginsanthropics/claude-plugins-official | 38k | 11 repos | ~3.1k | Automated safety check: Pass | Apache-2.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Stitch to Remotion Walkthrough Videosgoogle-labs-code/stitch-skills | 8.5k | 6 repos | ~3.2k | Automated safety check: Notes | Apache-2.0 |
Similar skills
- Official
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
- Official
MCP Integration for Plugins
anthropics/claude-plugins-official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
Figma use_figma Plugin API Rules
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
- Official
Stitch to Remotion Walkthrough Videos
google-labs-code/stitch-skills
Builds walkthrough videos from Stitch design projects using Remotion, with transitions, zoom effects and text overlays on each screen.
MCP Development
coollabsio/coolify
A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.
More from Dataojitori/nocturne_memory
Memory Audit Discoverability
Dataojitori/nocturne_memory
可发现性审计。当disclosure写法有问题、parent放错、alias缺失、子节点过多时使用. An agent skill from Dataojitori/nocturne_memory.
Memory Audit Node Decomposition
Dataojitori/nocturne_memory
节点分解。当一个节点体积过大、或塞了多个不相关概念导致disclosure无法覆盖时使用. An agent skill from Dataojitori/nocturne_memory.
Memory Audit Pattern Extraction
Dataojitori/nocturne_memory
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用. An agent skill from Dataojitori/nocturne_memory.
Memory Audit Belief Duel
Dataojitori/nocturne_memory
信念对决。当父子节点内容冲突、或两条你都认可的记忆逻辑上不能并存时使用。
Memory Audit Dead Data Purge
Dataojitori/nocturne_memory
死数据清洗。当一条记忆读不读你的行为都不会变、感悟没有现实锚点时使用。
Related
Works with
Questions about Memory Audit
How do I install Memory Audit in Claude Code?
Run `npx skills add Dataojitori/nocturne_memory --skill memory-audit -a claude-code`. Or copy the skill folder (docs/skills/memory-audit in Dataojitori/nocturne_memory) into .claude/skills/memory-audit in your project. Claude Code loads it when a task matches its description.
How do I install Memory Audit in Codex?
Run `npx skills add Dataojitori/nocturne_memory --skill memory-audit -a codex`. Or copy the skill folder (docs/skills/memory-audit in Dataojitori/nocturne_memory) into .agents/skills/memory-audit in your project. Codex loads it when a task matches its description.
Can I use Memory Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Dataojitori/nocturne_memory --skill memory-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/memory-audit, .gemini/skills/memory-audit, .github/skills/memory-audit and .opencode/skills/memory-audit in your project.
What does Memory Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Memory Audit is instructions for the agent only.
Does Memory Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Memory Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Memory Audit use?
Memory Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Memory Audit use?
About 525 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Memory Audit?
Skills that share tags, products or a category with Memory Audit: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Memory Audit?
Dataojitori (a GitHub user) maintains it in Dataojitori/nocturne_memory, which has 1,388 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on September 22, 2026.
Source: Dataojitori/nocturne_memory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.