← Back to Skills Marketplace
hushenglang

Vocabulary Anti Forgetting

by Joe Hu · GitHub ↗ · v3.0.0 · MIT-0
cross-platform ✓ Security Clean
215
Downloads
0
Stars
1
Active Installs
5
Versions
Install in OpenClaw
/install vocabulary-anti-forgetting
Description
Anti-forgetting vocabulary review using spaced repetition. Selects 10 words from asset/vocabulary_bank.md and presents each with English, Chinese translation...
Usage Guidance
This skill appears to do exactly what it says: it uses the included vocabulary bank and a local Python script to run spaced‑repetition sessions and stores progress in <workspace>/memory/review_log.md (or a directory you set with REVIEW_MEMORY_DIR). It does not access the network or request credentials. Before installing, consider: (1) the skill will create/modify review_log.md outside the skill folder so your progress survives upgrades — if you want to preserve or inspect existing data, back up your workspace/memory directory first; (2) the vocabulary bank contains everyday language and some adult/sensitive words (visible in the bank) — review content if that matters for your environment; (3) if you run the script locally ensure you use a trusted Python runtime; (4) if you want the log placed elsewhere, set REVIEW_MEMORY_DIR to a directory you control. Based on the provided files, there are no covert behaviors to block or network exfiltration risks.
Capability Analysis
Type: OpenClaw Skill Name: vocabulary-anti-forgetting Version: 3.0.0 The skill bundle is a legitimate implementation of a spaced-repetition vocabulary review tool based on the Ebbinghaus forgetting curve. The Python script (review.py) performs standard file I/O to manage a review log and read a vocabulary bank, with no network activity, external dependencies, or suspicious execution logic. The instructions in SKILL.md and the content in vocabulary_bank.md are consistent with the stated purpose and contain no evidence of prompt injection or malicious intent.
Capability Tags
cryptocan-make-purchases
Capability Assessment
Purpose & Capability
Name/description match the included files and behavior: review.py reads asset/vocabulary_bank.md, selects 10 words, and updates a local review_log. No extraneous binaries, credentials, or unrelated capabilities are requested.
Instruction Scope
SKILL.md directs the agent to run the provided review.py and to read/write the review_log.md in the workspace memory folder. The script only reads the local bank and the log, and updates local state; there are no instructions to read other system files, call external endpoints, or collect unrelated data.
Install Mechanism
No install spec is provided (instruction-only skill with an included Python script). review.py uses only standard library modules; nothing is downloaded or executed from external URLs.
Credentials
The skill declares no required environment variables or credentials. The script accepts an optional REVIEW_MEMORY_DIR env var to override where review_log.md is stored; otherwise it writes to the workspace memory directory (two levels above the skill folder). Writing outside the skill folder is explained as intentional for persistence across upgrades and is proportionate to the feature, but users should be aware it will create/modify files in their workspace memory directory.
Persistence & Privilege
The skill is not always-enabled and does not request elevated privileges. It persists only its own review_log.md in the workspace memory directory and does not modify other skills or global agent configuration.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install vocabulary-anti-forgetting
  3. After installation, invoke the skill by name or use /vocabulary-anti-forgetting
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.0
**Major update: Spaced repetition rework, CLI, and file handling changes** - Replaced previous session flow with a robust spaced repetition algorithm (levels 0–7, Ebbinghaus intervals) for scheduling reviews. - Introduced `review.py` CLI script to handle review sessions and stats—sessions now run as a single command, outputting and updating all results at once. - Changed review history tracking: now uses a unified `review_log.md` in the workspace `memory/` directory, with a new markdown table format including review level and dates. - Added support for reviewing any custom number of words; stats requests supported via CLI. - Improved file structure, separating vocabulary bank from user/session memory to ensure persistence and easier upgrading.
v2.0.0
**Major update: Quiz removed, now offers detailed review cards for each word.** - Replaces interactive quiz with a study-based session: presents 10 vocabulary cards (English, Chinese, example sentence, synonyms) per session. - Removes all question/answer mechanics and batching; user receives full review content in a single reply. - Each vocabulary card includes usage notes and 3–5 synonyms in addition to translation. - Session still tracks spaced repetition and updates review history files as before. - Session log simplified to record only words reviewed (no score or duration). - Skill description, session flow, and rules updated to reflect the new review-first, quiz-free workflow.
v1.2.0
- Only two question types are now used: 选择题 (MCQ) and 填空题 (Fill-in-blank); translation questions removed. - Each word gets three questions using only those two types; new fixed question distribution pattern detailed. - Quiz section, examples, and session log updated to reflect change (translation/翻译题 references removed). - Presentation and feedback instructions adjusted for revised question types. - Overall session flow and review logic remain unchanged.
v1.1.0
- Quiz delivery updated: each reply now presents a batch of 3 questions (each on a different word) instead of one question per reply. - Documentation and examples adjusted throughout to clarify "3 per reply" quiz flow. - Session instructions now specify automatic feedback and next-batch presentation after answering each set of 3. - No changes to review logic, triggers, or result summary.
v1.0.0
Initial release: Anti-forgetting vocabulary review skill using spaced repetition. - Selects 10 words per session based on review history and vocabulary bank. - Presents a summary table before quizzing. - Conducts a 30-question quiz (MCQ, fill-blank, translation) with shuffled groups. - Tracks review stats and schedules next review dates per spaced repetition logic. - Logs each session with words reviewed, score, and duration. - Responds to several user commands for starting a review session.
Metadata
Slug vocabulary-anti-forgetting
Version 3.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 5
Frequently Asked Questions

What is Vocabulary Anti Forgetting?

Anti-forgetting vocabulary review using spaced repetition. Selects 10 words from asset/vocabulary_bank.md and presents each with English, Chinese translation... It is an AI Agent Skill for Claude Code / OpenClaw, with 215 downloads so far.

How do I install Vocabulary Anti Forgetting?

Run "/install vocabulary-anti-forgetting" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Vocabulary Anti Forgetting free?

Yes, Vocabulary Anti Forgetting is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Vocabulary Anti Forgetting support?

Vocabulary Anti Forgetting is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Vocabulary Anti Forgetting?

It is built and maintained by Joe Hu (@hushenglang); the current version is v3.0.0.

💬 Comments