agentleFS
Howie126313Howie126313/obsidian-vault-kit/skills/review-scheduler/SKILL.md

review-scheduler

Skill3 starsChanged 7 months agoApache-2.0View on GitHub

(macOS only) Spaced repetition review scheduler for Obsidian. Based on the Ebbinghaus forgetting curve, auto-reminds you to review articles at optimal intervals via macOS launchd + screen unlock detection. Triggers: "/review-scheduler", "set up review reminders", "start review scheduler", "stop review scheduler"

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. X-RayLuan/Openclaw-Study-Coach★ 8same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Show its rules and text

We split this skill into the rules it gives an agent

13 rules. About 0 are common, 8 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No args or start → execute Start Flow

    line 26
  2. Very specific:

    If the output is not Darwin, inform the user that this skill is macOS-only (requires launchd, Swift compiler, and osascript) and stop.

    line 42
  3. Distinctive:

    Before any action, run these checks:

    line 46
  4. Distinctive:

    If any dependency is missing, stop immediately and report to user:

    line 54
  5. Distinctive:

    Use AskUserQuestion to ask:

    line 63
  6. Distinctive:

    If already running → inform user "Review scheduler is already active", ask if they want to update the scheduled time

    line 74
  7. Distinctive:

    If user doesn't want to update → end

    line 75
  8. Distinctive:

    If user wants to update → run Stop Flow first, then continue with deployment

    line 76
  9. Very specific:

    Detect vault path: follow ../../_shared/common-steps.md "Vault Detection" section, store as $VAULT_ROOT

    line 80
  10. Very specific:

    Read references/review_reminder.py

    line 86
  11. Very specific:

    Read references/unlock_watcher.swift

    line 92
  12. Distinctive:

    Check whether a review note was generated (if any articles are due for review today).

    line 121
  13. Distinctive:

    If not running → inform user "Review scheduler is not active" → end

    line 141

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review Scheduler

Manage spaced repetition review reminders for the Obsidian vault.

Argument Parsing

Parse user input arguments (args) to determine which subcommand to run:

  • No args or start → execute Start Flow
  • stop → execute Stop Flow
  • status → execute Status Check

Start Flow

Step 0: Platform Check

This skill requires macOS. Check the platform first:

uname -s

If the output is not Darwin, inform the user that this skill is macOS-only (requires launchd, Swift compiler, and osascript) and stop.

Step 0.5: Dependency Check

Before any action, run these checks:

which python3 && python3 --version
python3 -c "import yaml; print('PyYAML OK')"
which swiftc

If any dependency is missing, stop immediately and report to user:

  • Python 3 missing: suggest brew install python3
  • PyYAML missing: suggest pip3 install pyyaml
  • swiftc missing: suggest xcode-select --install

Proceed only after all checks pass.

Step 1: Ask User for Scheduled Time

Use AskUserQuestion to ask:

"What time would you like to receive daily review reminders? (default 9:00, format: 08:30, 21:00)"

Parse user input into Hour and Minute. If user presses enter or says "default", use 9:00.

Step 2: Check Existing Deployment

launchctl list 2>/dev/null | grep com.obsidian-vault-kit.review
  • If already running → inform user "Review scheduler is already active", ask if they want to update the scheduled time
  • If user doesn't want to update → end
  • If user wants to update → run Stop Flow first, then continue with deployment

Step 3: Deploy Files

  1. Detect vault path: follow ../../_shared/common-steps.md "Vault Detection" section, store as $VAULT_ROOT
  2. Detect vault name: take the directory name of $VAULT_ROOT
  3. Create .review/ directory: mkdir -p $VAULT_ROOT/.review
  4. Create reviews/ directory: mkdir -p $VAULT_ROOT/reviews
  5. Deploy review_reminder.py:
    • Read references/review_reminder.py
    • Replace {{VAULT_PATH}} with the actual $VAULT_ROOT absolute path
    • Replace {{VAULT_NAME}} with the actual vault name
    • Write to $VAULT_ROOT/.review/review_reminder.py
  6. Deploy unlock_watcher.swift:
    • Read references/unlock_watcher.swift
    • Replace {{PYTHON_PATH}} with the result of which python3
    • Replace {{SCRIPT_PATH}} with $VAULT_ROOT/.review/review_reminder.py
    • Write to $VAULT_ROOT/.review/unlock_watcher.swift
    • Compile: swiftc $VAULT_ROOT/.review/unlock_watcher.swift -o $VAULT_ROOT/.review/unlock_watcher -framework Cocoa
  7. Deploy launchd plist (scheduled task):
    • Read references/com.obsidian-vault-kit.review.plist
    • Replace {{PYTHON_PATH}}, {{SCRIPT_PATH}}, {{HOUR}}, {{MINUTE}}
    • Write to ~/Library/LaunchAgents/com.obsidian-vault-kit.review.plist
  8. Deploy launchd plist (unlock watcher):
    • Read references/com.obsidian-vault-kit.review-watcher.plist
    • Replace {{WATCHER_PATH}} with $VAULT_ROOT/.review/unlock_watcher
    • Write to ~/Library/LaunchAgents/com.obsidian-vault-kit.review-watcher.plist

Step 4: Start Scheduled Tasks

launchctl load ~/Library/LaunchAgents/com.obsidian-vault-kit.review.plist
launchctl load ~/Library/LaunchAgents/com.obsidian-vault-kit.review-watcher.plist

Step 5: Run Once for Verification

python3 $VAULT_ROOT/.review/review_reminder.py

Check whether a review note was generated (if any articles are due for review today).

Step 6: Report Results

Report to user:

  • Scheduled task is active, daily reminder at HH:MM
  • Screen unlock also triggers a check
  • Review notes are saved in the reviews/ directory
  • To stop, run /review-scheduler stop

Stop Flow

Step 1: Check If Running

launchctl list 2>/dev/null | grep com.obsidian-vault-kit.review

If not running → inform user "Review scheduler is not active" → end

Step 2: Unload Tasks

launchctl unload ~/Library/LaunchAgents/com.obsidian-vault-kit.review.plist 2>/dev/null
launchctl unload ~/Library/LaunchAgents/com.obsidian-vault-kit.review-watcher.plist 2>/dev/null
rm -f ~/Library/LaunchAgents/com.obsidian-vault-kit.review.plist
rm -f ~/Library/LaunchAgents/com.obsidian-vault-kit.review-watcher.plist

Note: keep .review/ directory and existing review notes in reviews/ — do not delete user data.

Step 3: Report

Inform user that the scheduled tasks have been stopped. Existing review notes are preserved.


Status Check

# Check scheduled tasks
launchctl list 2>/dev/null | grep com.obsidian-vault-kit.review
# Recent review notes (use native Glob, no Bash needed)
Glob("*.md", path="$VAULT_ROOT/reviews")

Report to user:

  • Whether the scheduled tasks are running
  • Most recent review note filenames
  • Whether today's review note exists

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.