agentleFS
c-ibarrac-ibarra/ObsidianKnowledgeCurator/.agents/skills/okc-study/SKILL.md

okc-study

Skill0 starsChanged 43 days agoMITView on GitHub

Creates, manages, and syncs curated study decks and flashcards between Obsidian and Anki.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user wants to generate active-recall flashcard decks from curated notes, books, or entire categories, format them …

    line 8
  2. Distinctive:

    When generating or refining flashcards with the agent:

    line 56
  3. Distinctive:

    Minimum Information Principle: Every card must test a single, atomic concept or step.

    line 57
  4. Distinctive:

    Evidence Grounding: Every card must be backed by verifiable source facts and reference its Knowledge Unit.

    line 62
  5. Very specific:

    Zero Terminal Spam for Inspections: NEVER run exploratory python3 -c "..." or curl commands via run_command to inspect cards, files, or …

    line 70
  6. Very specific:

    Preferred Synchronization (Zero Popups): Call FastMCP okc tool sync_basic_deck(file_path="...") directly.

    line 71
  7. Very specific:

    CLI Fallback (Strict 1-Command Execution): If running via CLI, execute in exactly one atomic terminal command (uv run python …

    line 72

≈ “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

OKC Study Decks & Flashcards Skill

Use this skill when the user wants to generate active-recall flashcard decks from curated notes, books, or entire categories, format them cleanly in Obsidian, and synchronize them directly to Anki.

Triggers include:

  • /okc-study
  • "crear mazo de estudio"
  • "generar flashcards"
  • "sincronizar mazo con anki"
  • "study deck"
  • "create study cards"

Workflow

1. Create a Study Deck (/okc-study create)

To create a new managed study deck from a source folder or note and sync it directly to Anki:

uv run python scripts/study_deck.py create --source "<folder_or_note_path>" --deck "<DeckName>" [--anki-deck "<AnkiDeckName>"]

Example:

uv run python scripts/study_deck.py create --source "dataScienceKnowledgeBase/AI Engineer/raw/Claude Code" --deck "Claude Code Mastery"

2. Check Study Deck Status (/okc-study status)

To view card counts and Anki synchronization status:

uv run python scripts/study_deck.py status --deck "<DeckName>"

3. Synchronize to Anki (/okc-study sync-anki)

To push or re-sync pending flashcards and visual media to Anki:

uv run python scripts/study_deck.py sync-anki --deck "<DeckName>"

4. Recover Dangling Transactions (/okc-study recover)

To scan the 2PC journal and cleanly recover or abort interrupted transactions after a crash:

uv run python scripts/study_deck.py recover [--clean-only]

Formulation Principles (SuperMemo 20 Rules)

When generating or refining flashcards with the agent:

  1. Minimum Information Principle: Every card must test a single, atomic concept or step.
  2. Context First: Explicitly name the domain or technology in the question (avoid "What is this?").
  3. Dual Model Standard:
    • Basic: Question (Q:) / Answer (A:).
    • Cloze: Text with deletions ({{c1::key concept}}).
  4. Evidence Grounding: Every card must be backed by verifiable source facts and reference its Knowledge Unit.
  5. No Visual Answers: Questions must not reveal the answer in image file names or alt texts.

🛡️ STRICT ZERO-PERMISSION PROTOCOL FOR AGENTS

To prevent disruptive user confirmation popups during study operations:

  1. Zero Terminal Spam for Inspections: NEVER run exploratory python3 -c "..." or curl commands via run_command to inspect cards, files, or Anki status. Use native silent tools (view_file, grep_search) or FastMCP okc tools (inspect_flashcards_deck, status_flashcards_deck).
  2. Preferred Synchronization (Zero Popups): Call FastMCP okc tool sync_basic_deck(file_path="...") directly.
  3. CLI Fallback (Strict 1-Command Execution): If running via CLI, execute in exactly one atomic terminal command (uv run python scripts/study_deck.py sync-file --file "...").

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.