Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add BENJAMINGLAI/anki-card-skill --skill anki-expertgit clone --depth 1 https://github.com/BENJAMINGLAI/anki-card-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/benjaminglai/anki-card-skill/anki-expert)<a href="https://agentmods.dev/skills/benjaminglai/anki-card-skill/anki-expert"><img src="https://agentmods.dev/badge/skills/benjaminglai/anki-card-skill/anki-expert/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/benjaminglai/anki-card-skill/anki-expert"><img src="https://agentmods.dev/badge/skills/benjaminglai/anki-card-skill/anki-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.04111 |
| Opus 5 | $0.00042 | $0.02056 |
| Sonnet 5 | $0.00017 | $0.00822 |
| Haiku 4.5 | $0.00008 | $0.00411 |
Grade A, and why
anki-expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to anki-expert — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anki Flashcard Expert Skill
Trigger Conditions
Activate when the user's request involves:
- Creating/generating Anki cards or flashcards
- Creating study cards from text, files, or URLs
- Exporting to .apkg or .tsv format, or pushing to Anki via AnkiConnect
- Mentions of Anki, flashcard, or spaced repetition
Workflow
Step 1: Get Input Text
- If the user provides text inline (wrapped in
{}), use it directly. - If the user specifies a local file path (.md, .txt, .pdf), use the Read tool.
- For PDFs, use the
pagesparameter to read in batches. - For large files, read and generate cards in batches.
- For PDFs, use the
- If the user provides a URL (starting with
http://orhttps://):- Use the WebFetch tool (or platform equivalent) to retrieve the page content.
- Strip navigation, ads, headers, footers, and other non-content elements. Focus on the main article/body text.
- If the page is very long, process it in sections.
- If neither text, file, nor URL is provided, ask the user.
Step 2: Check for nidd Identifier
- Check whether the user's text ends with
nidd+ digits (e.g.,nidd1742293016393). - If no nidd is provided, ask the user for one. Do not start making cards until a nidd is obtained, unless the user explicitly states there is none.
Step 3: Check Top-Level Tag
- Check whether the user specified a top-level tag.
- If so, use it as the highest-level tag prefix for all cards.
Step 4: Generate Flashcards
Follow the Card-Making Rules below. Output as a pipe-delimited table:
Question | Answer | Tags
------- | -------- | --------
Card 1 question | Card 1 answer | Card 1 tags
Card 2 question | Card 2 answer | Card 2 tags
...
Note: Place all cards in a single table for easy copying.
Step 5: Review
Before exporting, present the generated cards to the user for review:
- Ask the user to review the card table — they can request edits, deletions, or additions.
- If the user requests changes, revise the cards and present the updated table.
- Only proceed to export after the user confirms the cards are satisfactory.
- If the user says "skip review" or "直接导出", proceed to export immediately.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 324 lines · 84 tokens per session scan A a10be4997085
anki-expert is a skill published in the GitHub repository BENJAMINGLAI/anki-card-skill (1 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 4,111 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to anki-expert, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
anki-expert
Generate high-quality Anki flashcards from user-provided text (inline, local .md/.txt/.pdf files, or URLs) and auto-export to .tsv, .apkg, or push directly via AnkiConnect. Trigger when the user mentions Anki, flashcards, spaced repetition, study cards, memory cards, make cards, help me memorize, or .apkg files.
anki
Anki spaced repetition learning system reference. Covers the science of SRS and SM-2 algorithm, card design principles, optimal deck settings, FSRS scheduler, study workflow, essential add-ons, custom templates, filtered decks, and AnkiConnect API.
experiment-report
A skill for generating Chinese undergraduate laboratory reports, with choices for five subject areas, four levels of detail, and six user situations.
user-research-cookiy
End-to-end user research assistant — qualitative and quantitative. Use this skill whenever the user mentions user research, user interviews, discussion guides, interview guides, research plans, qualitative research, quantitative research, user surveys, survey design, usability studies, participant recruitment…
lov-hanzi-lens
A research and infographic workflow for explaining one Chinese character, including its pronunciation, written form, history, meanings, and use in classical texts.
explainer
A tool for making narrated explainer or tutorial videos with computer-generated visuals. It can help create the script, the video, or both.