CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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

Highly actionable with concrete, executable tool examples and a clear search-to-create/edit workflow including a destructive-edit validation checkpoint. Its main weakness is conciseness and the lack of progressive disclosure — substantial reference material lives inline in one large file rather than being offloaded to bundle files.

Suggestions

Tighten redundancy: the Note Anatomy fenced example and the write_note example repeat the same API Design Decisions note — keep one canonical example and reference it, and collapse the multiple edit_note blocks into a single table or compact example set.

Move the detailed reference material (Relations type table, Memory URL patterns, full tool-call API examples) into a references/ file (e.g. REFERENCE.md) linked from a concise overview, so SKILL.md stays a lean entry point.

Convert the soft "good practice to read the note first" guidance into an explicit validation checkpoint (e.g. a numbered 'read → confirm → apply' step) to harden the destructive-edit feedback loop.

DimensionReasoningScore

Conciseness

Mostly efficient and domain-specific rather than generic, but ~340 lines with notable redundancy — the Note Anatomy example overlaps the later write_note example, edit_note operations are illustrated multiple times, and the Best Practices section is verbose prose that could be trimmed.

2 / 3

Actionability

Provides fully executable, copy-paste-ready examples for write_note, edit_note (append/prepend/replace_section/find_replace), move_note, build_context, read_note, and search_notes with concrete parameters.

3 / 3

Workflow Clarity

The Before-Creating-A-Note section gives a clear search-then-decide decision tree (exists → edit_note, doesn't exist → write_note, unsure → read first) and an explicit validation step to read and confirm before destructive edits.

3 / 3

Progressive Disclosure

Well-organized into clear sections, but it is a single ~340-line monolith with no bundle files; the relation-types table, memory-URL patterns, and detailed tool API examples are all inline when they could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 that states concrete capabilities, includes natural trigger keywords, and supplies an explicit 'Use when' clause in third-person voice. It closely matches the rubric's good-overall examples with no over-claims or fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete components — "frontmatter, observations with semantic categories, relations with wiki-links, and best practices" — each a specific actionable part of the skill, matching the multi-action anchor.

3 / 3

Completeness

Clearly answers both what ("How to write well-structured Basic Memory notes: ...") and when ("Use when creating or improving notes.") with an explicit trigger clause.

3 / 3

Trigger Term Quality

Covers natural terms a Basic Memory user would say (notes, observations, relations, wiki-links, knowledge graph) plus an explicit "Use when creating or improving notes" trigger, giving good keyword coverage.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear niche ("Basic Memory notes") with distinctive triggers around frontmatter, observations, and wiki-link relations, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
basicmachines-co/basic-memory
Reviewed

Table of Contents

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.