--- title: "Study notebook reviewer" type: "skill" url: "https://useaiblocks.com/skills/study-notebook-review" updated: "2026-11-03" first_published: "2026-10-25" job: "Study and check your understanding" tested: true licence: "MIT" source: "https://github.com/Mohamed-El-Sharqawy/agent-tutor/tree/5651e2eec062785967d07bcb4752a59f1bcf0eee/skills/agent-tutor-review" instructions: "https://useaiblocks.com/skills/study-notebook-review/SKILL.md" --- # Study notebook reviewer > Run a study notebook review: recall each old topic first, get honest feedback, and see new review dates for every lesson note that is due. Give it the lesson notes and review dates from your study notebook. It asks what you recall before showing the notes, then checks the gaps. You get feedback, fresh review dates and a mixed quiz across the topics you revisited. Free skill for the job "Study and check your understanding" · Level: beginner · Thinking: medium · Tested · Updated 2026-11-03 ## Links - Page: https://useaiblocks.com/skills/study-notebook-review - Instructions (SKILL.md): https://useaiblocks.com/skills/study-notebook-review/SKILL.md - All files (zip): https://useaiblocks.com/skills/study-notebook-review.zip - JSON version: https://useaiblocks.com/skills/study-notebook-review.json - In your AI: connect https://useaiblocks.com/mcp and ask "Use AI Blocks to get study-notebook-review" ## What it does Give it the lesson notes and review dates from your study notebook. It asks what you recall before showing the notes, then checks the gaps. You get feedback, fresh review dates and a mixed quiz across the topics you revisited. ## What you give it - Lesson notes with a review block (interval, due date and key takeaways). - Your study notebook dashboard with its Up for review list. - Your recall answers, typed or spoken, for each topic. - An AI that can read and write files in your notes folder or Obsidian vault. ## What you get - Recall feedback for each reviewed topic. - Updated note review dates. - A mixed quiz and an updated session log. ## Example: what goes in and what comes out ### What goes in - Your lesson notes, each with a review block (interval, ease, due date) - Your dashboard with an Up for review list - Your spoken or typed recall of each topic, from memory - Your review settings (optional) ### Before you start - An AI that can read and write files in your notes folder (an Obsidian vault) - Lesson notes made with the agent-tutor skill ### What comes out - **Recall check**: One prompt per due topic asking you to explain it from memory before any notes are shown. - **Retention verdict**: A plain call for each topic: solid, shaky but recoverable, or gone, judged against the note's key takeaways. - **Updated review block**: New interval, ease and due date written into each note's review frontmatter. - **Mixed mini-quiz**: 5 to 8 questions across all topics reviewed today, scored against a 70% pass mark. - **Dashboard review queue**: The Up for review list, current and sorted by due date, with finished notes removed. - **Session log entry**: A review entry in the day's log file with a retention verdict for each topic. ## Skip it when - You have a brand-new topic and no lesson notes yet: build the lessons first with the Personal study planner, then come back here. - You want a quick one-off quiz on a topic: ask your AI for a short quiz and skip the notebook. - Your notes have no review dates and no dashboard: set those up first, or this skill has no queue to read. ## How to use it 1. Open your AI in a tool that can read and write files in your notes folder. Paste in this skill's instructions, or add the skill folder. 2. Point it to your study notes folder, or your Obsidian vault. 3. Say you want to review. It reads your Up for review list and picks the due notes. 4. Explain each topic from memory before it shows anything. Answer honestly. 5. Take the mixed quiz at the end. 6. Check that the new due dates and the session log look right. 7. Next, open the dashboard to see the updated review list. For topics marked gone, rebuild the lesson with the personal study notebook. To plan review dates for plain study cards, use the study review scheduler. ## What to do next - [Personal study planner](https://useaiblocks.com/skills/personal-study-notebook): Personal study planner - [Study review scheduler](https://useaiblocks.com/skills/study-review-scheduler): Study review scheduler ## Sources and credits - From Mohamed El-Sharqawy: https://github.com/Mohamed-El-Sharqawy/agent-tutor/tree/5651e2eec062785967d07bcb4752a59f1bcf0eee/skills/agent-tutor-review, shared under the MIT licence (original name: agent-tutor-review). - [agent-tutor-review skill](https://github.com/Mohamed-El-Sharqawy/agent-tutor/tree/5651e2eec062785967d07bcb4752a59f1bcf0eee/skills/agent-tutor-review), Mohamed El-Sharqawy: Copied under the MIT licence. We gave it a plain name. We added Before you start and After this sections that link to other AI Blocks steps. ## Instructions (SKILL.md) ## Agent Tutor — Review Understanding decays. This skill runs recall-first review sessions and keeps the retention schedule honest. **Vault root:** `OBSIDIAN_VAULT` env var, else `learning/` in the current workspace. All content under `/Learning/`. ### Before you start Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait. **What you need** (use your own material or the linked skill): - **A document** (yours): a finished document, such as a Word file, a PDF or a page of notes. How to start: 1. **Look first.** Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name. 2. **Check what's missing.** Look for a document. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps. 3. **Do the job.** Follow the skill below with the facts and tools you have. Mark each gap with `MISSING:` where it belongs and never invent a fact to fill it. ### The schedule Every lesson note carries a `review:` block in its frontmatter with the note's memory state: ```yaml review: interval: 6 # current interval in days ease: 2.5 # multiplier applied on a solid recall due: 2026-08-28 # next review date ``` Scheduling is **FSRS-inspired and adaptive** — no fixed ladder and no ceiling. After each review, compute the next state: | Verdict | Interval | Ease | |---|---|---| | **Solid** | `round(interval × ease)` | `+0.05`, up to `max_ease` | | **Shaky but recoverable** | `round(interval × 1.2)` | `−0.2`, down to `min_ease` | | **Gone** | reset to the initial interval | `−0.5`, down to `min_ease`; flag for re-study | Defaults — overridable per learner with an optional `review_policy:` block in the learner profile: ```yaml review_policy: scheduler: fsrs-inspired initial_interval: 1 # days after first learning / after a lapse ease: 2.5 # starting multiplier min_ease: 1.3 max_ease: 3.5 max_interval: null # null = unbounded; set e.g. 365 to cap growth fuzz: true # ±5% jitter on computed due dates so notes don't pile up on one day ``` Notes are never "done": a long interval just means the topic comes up rarely. Legacy notes whose `review:` field is a plain list (`[+1d, +3d, +7d]`) still work — take the last entry as the current interval with default ease, and migrate them to the block format at this review. ### Running a review session 1. Read the review queue from the dashboard: - **Markdown mode** (default): read `Learning/Dashboard.md` → **Up for review** section (notes whose next review date has passed). - **Html mode** (`output_format.dashboard: html` in the learner profile): read the `agent-tutor-state` JSON island at the top of `Learning/Dashboard.html`'s `` — its `due_notes[]` entries (note, due date, interval) are the queue. Map each entry back to its actual note file under `Learning//notes/` (island labels are display names); the thin `Dashboard.md` hub is a signpost — never parse it. No `Dashboard.html` yet → the fallback below applies. - If the dashboard looks stale in either mode, scan `Learning//notes/*/` frontmatter directly — note `review:` frontmatter is always the scheduling authority. 2. **Recall first, always.** For each note: ask the user to explain the topic from memory *before* showing anything. ("Explain closures to me as if I'd never heard of them.") 3. Judge the recall against the note's key takeaways, then apply the schedule table: - **Solid** → apply the solid row. - **Shaky but recoverable** → show the key takeaways, have them re-explain; apply the shaky row only if the second attempt is clean, otherwise treat as gone. - **Gone** → mark for re-study: re-open the lesson, re-teach the gaps, apply the gone row (reset to the initial interval). 4. **Interleave**: mix topics from different phases/subjects in one session — interleaving is the point, don't review one phase in isolation. 5. End with a **mixed mini-quiz** (5–8 questions spanning everything reviewed today). - If an interactive quiz tool is available (e.g. pi's `quiz`), use it. - Otherwise run a chat quiz: one question at a time, wait for the answer, explain why the right option is right, track the score, report pass/fail vs 70% at the end. 6. Update each note's `review:` frontmatter, the Dashboard review queue, and append a session log entry (type `review`) to `Learning//logs/YYYY-MM-DD.md` with per-topic retention verdicts. ### Honesty rules - Judge recall against the note's key takeaways, not against "close enough". - Tell the user their actual retention state — "you've forgotten X entirely" is useful information. - If more than half of a subject's notes fail review, say it plainly and propose a re-teach plan rather than patching holes. ### Dashboard maintenance Keep the **Up for review** section current: one bullet per due note, sorted by due date: ``` - [[notes/03-closures]] — +7d interval, due 2026-08-24 ``` Remove bullets after the review is logged. This list is what the tutor reads at session start, so it must be true. **Html mode** (`output_format.dashboard: html` in the learner profile): the queue lives in `Dashboard.html` — the **Up for review** section and the `due_notes[]` of the island read in step 1. Update it at the end of the session by regenerating the html dashboard whole — a fresh island, overview and subject focus pages together, plus the thin `Dashboard.md` hub's counters, exactly the update-the-Dashboard moment every session ends with; never hand-patch the html. ### After this When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own: - The [Personal study planner](https://useaiblocks.com/skills/personal-study-notebook). - The [Study review scheduler](https://useaiblocks.com/skills/study-review-scheduler). It takes the document. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.