Skip to content
Agentmart
Submit a tool

til-review

SRS-based TIL review session (spaced repetition).

Skill by SongYunSeop

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying til-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/songyunseop-til-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

SRS-based TIL review session (spaced repetition). Use when the user says 'quiz me', 'review what I learned', 'flashcard session', 'test my knowledge', or wants to do spaced repetition review of their TIL notes.

Use cases: testing, productivity

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/til-review

What's inside

Skill name
til-review
Description
SRS-based TIL review session (spaced repetition). Use when the user says 'quiz me', 'review what I learned', 'flashcard session', 'test my knowledge', or wants to do spaced repetition review of their TIL notes.
License
MIT
Instructions
62 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • evals.json · evals/
  • trigger-eval.json · evals/

SKILL.md (first lines)

# Review Skill

SRS (spaced repetition) based TIL review session. Manages review schedule with the SM-2 algorithm.

## MCP Tools

- `til_review_list`: List of cards due for review today + stats (load note content with `include_content: true`)
- `til_review_update`: Record review result (grade 0-5) or remove from review

## Step 1: Load Review Cards

Call `til_review_list` (`include_content: true`, pass category argument if provided).

- 0 cards → Show "No reviews today" + suggest registering untracked TILs (go to Step 5)
- Cards found → Display list + proceed to Step 2

## Step 2: Select Evaluation Mode

Select via `AskUserQuestion`:
- "Simple mode (Again / Good)"
- "Detailed mode (Again / Hard / Good / Easy)"

## Step 3: Per-Card Review Loop

For each card:

1. Display title, category, review info (repetition count, EF, days overdue)
2. Use `content` already loaded in Step 1 (no additional MCP calls needed)
3. Present key content as questions (generate 1-2 questions based on content)
4. Wait for user answer
5. Provide feedback (correct answer / supplementary explanation)
6. Input evaluation via `AskUserQuestion`:
   - Simple mode: "Good (Remembered)" / "Again (Forgot)" / "Skip" / "Stop Review"
   - Detailed mode: "Again (Failed)" / "Hard (Struggled)" / "Good (Normal)" / "Easy (Perfect)"
   - Grade mapping: Again=1, Hard=3, Good=4, Easy=5
   - "Skip": do not evaluate this card, move to next
   - "Stop Review": move to Step 4
   - Skip/Stop in detailed mode: select "Other" then type "Skip" or "Stop Review"
7. If not skipped, call `til_review_update` (action: "review", grade)
8. Display result summary (next review date, interval)

## Step 4: Completion Stats

After all cards are done:
- Number of cards reviewed, average grade
- If remaining > 0, show "N more remaining, continue tomorrow"
- Re-call `til_review_list` to display latest stats

## Step 5: Register TILs (Optional)

When no cards exist or user requests:
- Display full TIL list via `til_list`
- User selects files to add to review
- Call `til_review_update` (action: "review", grade: 4) for each selected file

## Rules

- Max 20 cards per session (prevent overload)
- Prioritize overdue cards (most urgent first)
- Remove from review: if user says "remove this card", call `til_review_update` (action: "remove")

From SongYunSeop/oh-my-til, MIT.

More from SongYunSeop/oh-my-til

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Mar 6, 2026 (8 months ago)
Last release
May 15, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from SongYunSeop

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get til-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying til-review?

CallGet help
Cite this page

til-review skill. Agent Mart. https://agentmart.dev/skills/songyunseop-til-review (last updated 2026-10-24)