add-memory-kind

Add a new business memory kind end-to-end. Pick the storage combination (Markdown / SQLite / LanceDB), pick the markdown strategy (daily-log / skill-named / single-file), then wire up the schema(s), repo(s), and writer(s).

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-memory-kind/SKILL.md

Quality

Content

81%Weight 40%Scale 1-5

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

A well-structured, actionable recipe with executable code, an explicit verification checklist, and error-recovery pitfalls; the main gap is that two of the three promised markdown strategies are sketched rather than fully specified.

Dimension	Reasoning	Score
Conciseness	The body is information-dense, assumes Claude's competence (no 'what is SQLite' padding), and uses tight tables and code blocks; a few explanatory prose stretches (the combo table rationale, the 'rule of thumb', the speculative 'Future' section) could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	The daily-log, SQLite, and LanceDB recipes give copy-paste-ready code with concrete file paths and a usage example, but only one of the three named markdown strategies (daily-log) has a full recipe while skill-named and single-file are only 'sketched at the bottom' as deferred, a minor coverage gap that keeps it below 5.	4 / 5
Workflow Clarity	A clearly numbered sequence (decide combo -> pick md strategy -> 4-step recipes per layer) with an explicit §7 verification checklist (make lint, make test, cross-layer join-key and rebuild checks) and a §8 pitfalls table serving as error-recovery feedback, matching the 'clear sequence with explicit validation and checklists' anchor.	5 / 5
Progressive Disclosure	Well-organized into clearly signaled sections with one-level-deep Background references to rules/*.md; the bulk recipe content is appropriately inline and no bundle files exist to split into, fitting the 'good structure; references mostly clear; minor gaps' anchor.	4 / 5
	Total	17 / 20 Passed

Description

58%Weight 40%Scale 1-5

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

The description gives a strong, concrete 'what' covering storage and strategy choices plus the wiring steps, but omits any explicit 'when to use' trigger guidance, which caps its completeness and limits trigger-term naturalness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when adding a new persisted business entity (Episode, Case, Skill, AtomicFact, Foresight, Profile) or wiring a new memory kind into EverOS.'

Soften the jargon with one or two natural user phrasings or synonyms (e.g. 'memory type', 'persistence layer') alongside the technical terms.

Name the concrete entity types a user would say (Episode, Case, Skill) as trigger keywords rather than only the abstract 'business memory kind'.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Pick the storage combination (Markdown / SQLite / LanceDB)', 'pick the markdown strategy (daily-log / skill-named / single-file)', 'wire up the schema(s), repo(s), and writer(s)') with enumerated options, though 'wire up' is slightly abstract, keeping it just below the comprehensive 5 anchor.	4 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Relevant domain terms are present (Markdown / SQLite / LanceDB, daily-log / skill-named / single-file) but the language is technical jargon with no natural user phrasings, synonyms, or file extensions, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	'Add a new business memory kind end-to-end' carves a clear niche with distinct triggers and only minor overlap risk with closely related general persistence skills, fitting the 'mostly distinct' anchor.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: EverMind-AI/EverOS
Path: .claude/skills/add-memory-kind/SKILL.md
Commit: 6ff07ef

Reviewed: 3 days 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.