memento-flashcards

Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded by the agent, generate quizzes from YouTube transcripts, review due cards with adaptive scheduling, and export/import decks as CSV.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/productivity/memento-flashcards/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced body with strong validation and feedback loops. The main weaknesses are mild redundancy in the feedback rules across sections and a monolithic structure that could offload some detail into reference files.

Suggestions

De-duplicate the free-text grading/feedback rules: define them once in 'Reviewing Due Cards' and have the YouTube section reference that definition instead of restating it.

Consider moving the long quiz-generation prompt and the spaced-repetition algorithm table into a reference file (e.g. reference/QUIZ_PROMPT.md) referenced one level deep from the body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and action-oriented, but the free-text feedback rule is restated in both 'Reviewing Due Cards' and YouTube 'Step 6', and 'When to Use' overlaps the 'Quick Reference' table; tightening these would reach a 3. It is not a 1 because it avoids explaining concepts Claude already knows and leads with executable commands.	2 / 3
Actionability	Provides fully executable bash commands for every operation, a concrete grading format with exact reply templates, and a complete quiz-generation prompt — copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Multi-step flows (card creation, review, YouTube quiz steps 1-6) are explicitly sequenced with validation checkpoints (JSON validation with one retry, atomic writes) and feedback loops, plus a dedicated Verification section.	3 / 3
Progressive Disclosure	Scripts are correctly bundled in scripts/ and referenced inline, and sections are well organized, but at ~300 lines all guidance lives in SKILL.md with no one-level-deep reference docs; content such as the quiz prompt or algorithm table that could be split out is inline. It is not a 1 because references are not deeply nested and the scripts are properly externalized.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description using third person and concrete actions with good natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness at 2.

Suggestions

Append a 'Use when...' clause to the description, e.g. 'Use when the user wants to memorize facts, review flashcards with spaced repetition, or generate a quiz from a YouTube video.'

Add common natural variations users might say, such as 'study cards', 'memorize', or 'Anki-style review', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Create cards from facts or text', 'chat with flashcards using free-text answers graded by the agent', 'generate quizzes from YouTube transcripts', 'export/import decks as CSV' — matching the score-3 anchor.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2; it is not a 1 because the 'what' is thorough.	2 / 3
Trigger Term Quality	Includes natural terms a user would say — 'flashcards', 'spaced-repetition', 'YouTube transcripts', 'quiz', 'CSV' — giving good coverage rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (spaced-repetition flashcards, YouTube quizzes) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/productivity/memento-flashcards/SKILL.md
Commit: 4c9628e

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.