memory-notes

How to write well-structured Basic Memory notes: frontmatter, observations with semantic categories, relations with wiki-links, and best practices for building a rich knowledge graph. Use when creating or improving notes.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/memory-notes/SKILL.md

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.

A well-structured, highly actionable skill with comprehensive executable examples for every Basic Memory tool and a clear pre-creation search workflow. Its main weakness is moderate verbosity from re-explaining the note philosophy in multiple places rather than stating it once.

Suggestions

Tighten the prose-vs-observations rationale so it is stated once (in the Body section) rather than re-explained in Best Practices #2, trimming repeated explanation.

Add an explicit validate→fix→retry feedback loop for destructive edit_note operations (replace_section, find_replace): e.g. 'read the note → apply edit → re-read to confirm → revert if wrong'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but includes unnecessary re-explanation (e.g. re-stating the prose-vs-observations philosophy in Best Practices #2 after the Body section already covered it, and 'Observations are categorized facts — the atomic units of knowledge' restating the anatomy example), fitting the anchor for mostly efficient with some tightening possible.	3 / 5
Actionability	Provides fully executable, copy-paste-ready code for write_note, edit_note (all four operations with real parameters), move_note, build_context, search_notes, and read_note, with examples covering the common cases, matching the anchor for fully executable copy-paste-ready guidance.	5 / 5
Workflow Clarity	The 'Before Creating a Note' decision tree and the destructive-edit guidance ('read the note first and confirm the change before applying it') give a clear sequence with most checkpoints present, but there is no explicit validate→fix→retry feedback loop for destructive operations like replace_section and find_replace, leaving a minor validation gap.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized sections and no bundle files, and per the scoring notes a clear, well-organized self-contained skill can score 5; the one cross-reference to the memory-schema skill is clearly signaled and one level deep.	5 / 5
	Total	17 / 20 Passed

Description

76%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, specific description that names concrete components and has an explicit 'Use when' trigger, with a clear niche that minimizes conflict risk. Its main weakness is the thin trigger-phrase coverage, which relies on a single natural phrase rather than enumerating the terms users would actually say.

Suggestions

Expand the 'Use when' clause with concrete trigger phrases users naturally say, e.g. 'Use when creating or improving notes, building a knowledge graph, linking notes in Basic Memory, or organizing observations and relations.'

Add common synonyms and the tool/product name to the trigger phrasing (e.g. 'Basic Memory', 'knowledge graph', 'memory notes') so the skill surfaces for the full range of natural requests.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete components — 'frontmatter, observations with semantic categories, relations with wiki-links, and best practices' — giving comprehensive coverage of what the skill does, matching the anchor for multiple specific concrete actions.	5 / 5
Completeness	Clearly answers both 'what' (write well-structured notes with frontmatter/observations/relations) and 'when' ('Use when creating or improving notes'), but the 'when' clause is somewhat thin and could be more specific, placing it between anchors 4 and 5.	4 / 5
Trigger Term Quality	The only trigger phrase is 'creating or improving notes', which is relevant but misses common natural variations users might say ('knowledge graph', 'Basic Memory', 'linking notes', 'memory notes'), fitting the anchor for some relevant keywords missing common synonyms.	3 / 5
Distinctiveness Conflict Risk	The 'Basic Memory notes' + 'knowledge graph' + 'wiki-links' framing carves out a clear niche with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	17 / 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-notes/SKILL.md
Commit: a5fb68e

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.