Compartmentalize
Save important details from conversations to an encrypted memory vault for future reference.
Installation
- Make sure Claude is on your device and in your terminal.
Skills load from
~/.claude/skills/when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then runclaudein any terminal to verify.One-time setupnpm i -g @anthropic-ai/claude-codeAlready have it? Skip ahead.
- Paste into Claude Code or into your terminal.
This copies the whole skill folder into
~/.claude/skills/compartmentalize-maxfreedompollard/— the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Works for every skill.What this command does
- Makes a new, empty temporary folder.
- Downloads the skill's folder,
skills/compartmentalize, fromgithub.com/MaxFreedomPollard/Compartment(branchmain), the GitHub repository it's listed from. You get the version that is there now, not a copy we keep. - Copies that folder to
~/.claude/skills/compartmentalize-maxfreedompollard/. - Deletes the temporary folder.
Installing runs none of the skill's files; it only downloads and copies them. When you later use the skill, Claude follows its SKILL.md and may run scripts that come with it. Read them first.
Faster alternative (instruction-only skills)
Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.
Quick install (SKILL.md only)Sign up to copy - Restart Claude Code.
Quit and reopen Claude Code (or any other agent that loads from
~/.claude/skills/). New skills are picked up on startup. - Just ask Claude.
Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.
Prefer to read the source first? Open on GitHub.
When Claude uses it
Sweep this conversation and save everything worth referencing again in future work into Compartment, the encrypted memory vault. Run it before compacting or summarizing so nothing is lost to the summary, or on its own at any point to bank the session.
What this skill does
Save to Compartment before compacting.
Sweep the entire conversation, including any part already summarized, and store to Compartment what it holds that is worth keeping.
STORE anything worth referencing again in future work: names, addresses, contacts, account IDs, passwords, API keys and other credentials, lasting file locations and configuration, preferences, and every durable fact or decision reached. Not transient chatter, one-off trivia, things freely available on the internet, or the working details of a task in progress, such as run results, errors, log contents and temporary paths or settings.
For each item, memory_search first, then memory_store: update the existing
memory when one already covers it, create a new one when none does.
Always store, when present: people, contacts and addresses. Passwords, API keys, tokens, account IDs, and where each one lives. URLs, hostnames, repo and release locations.
Then properly associate and store every durable observation, decision, opinion and thought that is not publicly available: anything that would be expensive or impossible to work out again from scratch.
Also store the session itself - as several one-claim memories, never one narrative: one for what was asked, one for what it turned into, one for what changed by the end, one for what is still open. That the work happened and what it did is information in its own right, sometimes more useful than any single detail inside it, and each of those claims is recalled on its own.
Skip: everything the STORE rule above excludes, anything already stored unless it is an update with additional or changed information, and the Compartment vault passphrase itself.
Write each memory to stand alone: ONE claim of at most 200 characters by default - the vault enforces this and refuses lists, headings and paragraphs - with no pronouns pointing back at this conversation and no "as discussed above". Never leave out information that is necessary to understand the memory on its own. Several facts go through memory_store_many, one record each, in one call. Store preferences, stances and judgement calls with kind='opinion': opinions update instead of accumulate, and one resembling a live opinion comes back for an explicit supersedes=[old id] resend. Set namespace, tags and importance. When a fact was established before today, pass discovered=YYYY-MM-DD; the vault stamps every memory's dates itself, so never type dates into the text.
Do not stop early. Finish the sweep, then report how many were stored and how many updated.
Related skills
Claude API Helper
anthropics
Build, debug, and optimize Claude API applications with caching and model migration support.
Documentation Co-Authoring
anthropics
Guide structured workflows for writing docs, proposals, and technical specs collaboratively.
PPTX Text Extractor
axoviq-ai
Extract text and speaker notes from PowerPoint presentations.
Memory Search
davila7
Search conversation history and recall previous discussions, decisions, and context.