一键导入
hashcards-setup
Sets up a spaced repetition flashcard system that you can access through your web browser to study and memorize information
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Sets up a spaced repetition flashcard system that you can access through your web browser to study and memorize information
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
A Zo Computer skill for adding Humation avatars to agent products. It covers installing Humation npm packages into target projects, React integration, Core SVG rendering, static SVG generation, browser ESM usage in zo.space page routes, and legacy Humation SVG API compatibility.
Bootstraps the Clarion Intelligence System on Zo Computer. Run this once after installing — clones the source repo, installs the ai_buffett_zo Python library, creates the workspace data tree under /home/workspace/clarion/ (auto-detected on Zo), auto-installs all nine sibling clarion-* skills (regime-check, sec-research, single-stock-eval, expected-return-calc, value-screener, thesis-write, thesis-monitor, watchlist-update, living-letter-update) under /home/workspace/Skills/, and registers the sec-indexer background service. Idempotent (safe to re-run). The only manual step is one batched human checkpoint near the end (SEC EDGAR name + email, and creating the ZO_API_KEY secret). Persona routing for Clarion is opt-in via a separate prompt after install ("install Clarion personas and routing rules"). Use when the user asks to "set up Clarion" or "install Clarion".
Monitor the health of every active thesis in ~/clarion/theses/. For each one — refresh price, recompute Risk Environment from the current regime, check kill conditions (read from the file's status column), aggregate to an Overall score, recommend an action (EXIT / REDUCE / HOLD / ADD), and write the updated scores + history back to the thesis file. Produces a dashboard surfacing what needs attention. Use when the user asks "monitor my theses", "thesis health check", "any kill conditions triggered?", "what's the action on <TICKER>", or as part of a daily / weekly review. Requires clarion-setup to have been run.
Scaffold a new thesis document for a ticker in the canonical Clarion thesis format. Pre-fills the YAML metadata block, opens the History with an OPENED entry, and (when filings are indexed) seeds the "Why I Believe It" evidence section with draft citations from the Buffett-lens search. The user fills in the actual prose. Outputs a markdown file at ~/clarion/theses/{TICKER}.md. Use when the user says "write a thesis on <TICKER>", "scaffold a thesis for <TICKER>", "draft a thesis for <TICKER>", or after clarion-single-stock-eval returns an Add verdict and the user wants to formalize the position. Requires clarion-setup to have been run.
Compute the equity-vs-T-bill allocation for the Value bucket (50% of portfolio). Implements the Expected-Return Framework — looks up the historical 10-year forward return from the S&P 500 Shiller CAPE, computes the regime-adjusted hurdle (rf + regime premium), and produces a 5-tier verdict (STRONG EQUITY / LEAN EQUITY / NEUTRAL / LEAN T-BILLS / MAXIMUM T-BILLS) with recommended Value-bucket equity/T-bill split. Use when the user asks "should I be in stocks or bonds right now?", "what's the equity hurdle?", "is the market overvalued?", "what's the right Value bucket allocation?", or before adding any new equity to the Value bucket. Requires clarion-setup to have been run.
Update the annual investor letter at ~/clarion/letters/{YEAR}-letter.md with a new quarterly section, or finalize it at year-end. Auto-fills the system-deterministic parts (regime snapshot, thesis health table, portfolio bucket positions from active theses); marks the narrative-heavy parts (What We Did, What We Learned, Year in Context, Mistakes & Lessons, Looking Ahead) as [TODO] for the user to write with chat assistance. Append-only — refuses to overwrite an already-populated quarter without --force. Use when the user asks "update the letter", "quarterly letter update", "finalize the letter", or "write the {Q1/Q2/Q3/Q4} entry". Requires clarion-setup to have been run.
| name | hashcards-setup |
| description | Sets up a spaced repetition flashcard system that you can access through your web browser to study and memorize information |
| metadata | {"author":"rc2.zo.computer","category":"Community","display-name":"Set up hashcards spaced repetition system","emoji":"📇"} |
This file will be included in a user request. If it is, Zo should interpret this as the current task at hand and use its tools to carry out the task until completion. Zo should not ask for user confirmation to continue if it has all required parameters to execute this function. Zo should effectively treat the inclusion of this file as a user request to "run" this task.
This document codifies the procedure for setting up hashcards on Zo Computer, enabling a web-based spaced repetition system for learning through flashcards. The setup includes installing Rust/Cargo, building hashcards from source, creating a flashcards directory, and registering the service to run persistently with automatic restarts.
This guide will walk you through setting up hashcards on your Zo Computer instance, giving you a personal spaced repetition system accessible through your browser.
https://srs-<your-username>.zocomputer.io/home/workspace/flashcards/Use add-flashcards after completing this setup.
This setup will automatically install:
No manual prerequisites needed - the command handles all installations.
Ensure git is available for cloning the repository:
command -v git || apt-get update && apt-get install -y git
Verify: Check that git is installed:
git --version
Expected Result: You should see a git version number (e.g., git version 2.x.x).
Install Rust toolchain if not already present:
if ! command -v cargo &> /dev/null; then
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
source ~/.cargo/env
fi
Verify: Check that cargo is installed:
cargo --version
Expected Result: You should see a cargo version number (e.g., cargo 1.x.x).
Note: This is a one-time installation. Rust and Cargo will remain available for future use.
Before building hashcards, install the required SQLite development libraries:
apt-get update && apt-get install -y libsqlite3-dev
Note: Hashcards requires SQLite dev libraries to compile. Installing these first prevents build errors.
Clone the hashcards repository and build the binary:
# Clone to temporary directory
cd /tmp
rm -rf hashcards
git clone https://github.com/eudoxia0/hashcards.git
cd hashcards
# Build release binary (this takes 5-10 minutes)
source ~/.cargo/env
cargo build --release
# Install binary to cargo bin directory
mkdir -p ~/.cargo/bin
cp target/release/hashcards ~/.cargo/bin/
Verify: Check that hashcards is installed:
~/.cargo/bin/hashcards --version
Expected Result: You should see version information for hashcards (e.g., hashcards 0.1.0).
Note: Building from source takes 5-10 minutes on first run, but the compiled binary is cached for instant startup afterwards.
Set up the directory for storing your flashcard files:
mkdir -p /home/workspace/flashcards
Verify: Check the directory exists:
ls -la /home/workspace/flashcards
Create an example flashcard file to get started:
cat > /home/workspace/flashcards/sample.md << 'EOF'
# Sample Flashcards
<!-- Source: Getting started with hashcards -->
Q: What is spaced repetition?
A: A learning technique that involves reviewing information at increasing intervals to improve long-term retention.
Q: What does FSRS stand for?
A: Free Spaced Repetition Scheduler - an algorithm that optimizes review intervals.
C: The capital of France is [Paris].
C: [Hashcards] stores flashcards as plain text files.
EOF
Note: Cards with C: prefix and [text] are cloze deletions - the text in brackets will be hidden during review.
Verify: Check the sample file was created:
cat /home/workspace/flashcards/sample.md
Register hashcards as a persistent user service:
Using Zo tools:
Use register_user_service with:
- label: srs
- protocol: http
- local_port: 8000
- entrypoint: /root/.cargo/bin/hashcards drill --port 8000 --open-browser false
- workdir: /home/workspace/flashcards
- env_vars: {"PATH": "/root/.cargo/bin:/usr/local/bin:/usr/bin:/bin"}
Critical notes:
/root/.cargo/bin/hashcards (not ~/.cargo/bin/) - shell expansion doesn't work in service entrypoint--port 8000 flag (not --addr 0.0.0.0:8000)--open-browser false to prevent it trying to open a browserVerify: Use tool list_user_services to confirm the srs service is registered with an HTTPS URL.
Wait a few seconds for the service to start, then test it:
curl -I https://srs-<your-username>.zocomputer.io
Replace <your-username> with your Zo username.
Expected Result: You should get an HTTP 200 response.
Check Logs: If something goes wrong, check the logs:
cat /dev/shm/srs.log
cat /dev/shm/srs_err.log
Once the service is running, simply open your browser and navigate to:
https://srs-<your-username>.zocomputer.io
You should see the hashcards web interface with your flashcards ready to review.
After completing this setup, you have:
https://srs-<your-username>.zocomputer.io/home/workspace/flashcards/hashcards.db/home/workspace/flashcards/ - create file .md files hereProtocol Details:
IMPORTANT: By default, this setup has no authentication. Anyone with your URL can access your flashcards.
Why this might be okay:
srs-<username>.zocomputer.io)If you want to add password protection:
Hashcards itself doesn't have built-in authentication. To add protection, you can:
If your flashcards contain sensitive information (e.g., work credentials, personal data), consider adding one of these authentication layers.
Create file .md (markdown) files in /home/workspace/flashcards/. You can ask Zo to help create cards from any source material.
Q: What is the question?
A: This is the answer.
Use C: prefix and wrap text in [brackets]:
C: The capital of [France] is [Paris].
When reviewing, the text in brackets will be hidden one at a time.
Full markdown formatting and KaTeX math expressions are supported:
Q: What is the quadratic formula?
A: $x = \frac{-b \pm \sqrt{b^2-4ac}}{2a}$
Tip: Ask Zo to convert reading notes, articles, or documentation into flashcards. For example: "Convert these notes into hashcards format" or "Create flashcards from this article about X."
Open https://srs-<your-username>.zocomputer.io and review cards. Grade each with Forgot/Hard/Good/Easy - the FSRS algorithm uses your grades to optimize review intervals.
Note: Hashcards identifies cards by content hash. Editing a card resets its progress (this is intentional - you want to relearn improved cards).
If something goes wrong, check the logs at /dev/shm/srs.log and /dev/shm/srs_err.log. Ask Zo for help debugging issues.
Ask Zo to list, restart, or delete your service. Your progress is stored in /home/workspace/flashcards/hashcards.db.
Memory is valuable when it helps you do what matters to you. Use SRS for things that serve your goals, not trivia.
Key principles:
Creating good cards forces deep thinking about the material - often more valuable than the reviews themselves. Use the add-flashcards command to generate cards from source material.
Further reading:
You now have a hashcards instance at https://srs-<your-username>.zocomputer.io. Create cards in /home/workspace/flashcards/ and review daily. Use the add-flashcards command to generate cards from source material.
For more information, see the hashcards documentation.