memory-schema

Schema lifecycle management for Basic Memory: discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift. Use when working with structured note types (Task, Person, Meeting, etc.) to maintain consistency across the knowledge graph.

Quality

85%

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

Quality

Content

78%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.

The content is highly actionable — real tool calls with complete parameters for every operation — with a clear lifecycle workflow and built-in validation checkpoints. Its main weakness is structure: the skill is a single ~240-line file with the full Picoschema syntax reference inlined, rather than splitting that reference material into a separate file for progressive disclosure.

Suggestions

Move the 'Picoschema Syntax Reference' section (~90 lines: basic types, optional fields, enums, arrays, relations, validation settings, complete example) into a references/picoschema.md file, leaving a short inline summary plus a clearly signaled one-level-deep pointer.

Add explicit gating language to the workflow (e.g., 'only proceed to fixing outliers after schema_validate passes') to turn the existing validation steps into true feedback loops.

Explain or verify the edit_note(operation="append", content="") metadata-only update pattern, since appending empty content purely to replace metadata is non-obvious and error-prone.

Dimension	Reasoning	Score
Conciseness	The body is efficient and almost entirely tool-specific knowledge Claude cannot know (Picoschema syntax, tool parameters), with only minor over-explanation such as 'Relations create edges in the knowledge graph, linking notes together' and the 'Schema as documentation' guideline paragraph — efficient but not perfectly lean, so 4 rather than 5.	4 / 5
Actionability	Fully executable, copy-paste-ready tool invocations with complete parameters throughout: schema_infer(note_type="Meeting", threshold=0.5), a full write_note(...) call including the metadata map and content, edit_note(...) with the complete updated schema, schema_validate, and schema_diff — covering the common cases end to end.	5 / 5
Workflow Clarity	The evolution section has a numbered sequence with a re-validate checkpoint and a fix-outliers recovery step, and the Workflow Summary sequences all six operations. It falls short of 5 because the summary states validation without gating language ('only proceed when valid') and the odd edit_note(operation="append", content="") metadata-only pattern is not verified or explained.	4 / 5
Progressive Disclosure	No references/ or scripts/ files exist — the entire ~90-line Picoschema syntax reference (basic types, optional fields, enums, arrays, relations, validation settings, complete example) is inlined in SKILL.md as content that clearly belongs in a one-level-deep reference file. Section organization is good, placing it above anchor 2, but the inlined reference material matches anchor 3 rather than 4.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

A strong description: it enumerates the full schema lifecycle concretely, includes an explicit 'Use when...' trigger clause with realistic entity-type examples, and is tightly scoped to Basic Memory's Picoschema system. The only gap is minor — a handful of natural synonym phrasings a user might use instead of 'schema' or 'validate'.

Dimension	Reasoning	Score
Specificity	Names six concrete lifecycle actions — 'discover unschemaed notes, infer schemas, create and edit schema definitions, validate notes, and detect drift' — giving comprehensive coverage of the domain, matching the top anchor rather than the 'minor gaps' of 4.	5 / 5
Completeness	Explicitly answers both 'what' (the six lifecycle actions) and 'when' via the concrete trigger clause 'Use when working with structured note types (Task, Person, Meeting, etc.)'.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('schema', 'validate', 'drift', 'structured note types', plus concrete entity names 'Task, Person, Meeting'), but a few natural user phrasings like 'note templates' or 'check note conformance' are missing, so it falls short of the comprehensive-synonyms anchor at 5.	4 / 5
Distinctiveness Conflict Risk	Anchored to a specific tool and subsystem ('Schema lifecycle management for Basic Memory') with distinct triggers around structured note types and the knowledge graph, so it occupies a clear niche with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: basicmachines-co/basic-memory
Path: skills/memory-schema/SKILL.md
Commit: 194afe1

Reviewed: 7 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.