memory-curate

Curate the Basic Memory knowledge graph: find orphan notes and suggest links, propose typed relations, merge duplicates, audit tags and folders, and build hub notes. Use to organize, connect, and improve a knowledge base as notes accumulate.

Quality

78%

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 ./skills/memory-curate/SKILL.md

Quality

Content

76%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 body is highly actionable with executable code throughout and clear section structure. Its main gap is the absence of validation/verification checkpoints in the destructive batch workflows, which caps workflow clarity.

Suggestions

Add an explicit validation/verification step to the Deep Organization Session (e.g. after moving notes, verify wiki-links still resolve via build_context before proceeding).

Tighten the opening paragraph and Best Practices to remove mildly padded framing prose.

Consider extracting the relation-type vocabulary or example hub-note template into a reference file to exercise genuine progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and code-driven without explaining concepts Claude already knows, though the intro paragraph and some Best Practices prose could be tightened.	4 / 5
Actionability	Provides abundant executable, copy-paste-ready calls (search_notes, read_note, edit_note, move_note, write_note, list_directory, build_context) with concrete parameters covering the common curation cases.	5 / 5
Workflow Clarity	Three workflows are clearly numbered, but the Deep Organization Session performs destructive/batch operations (merge, move, edit) with no explicit validation or verification checkpoints, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	Content is well-organized into clear sections (When to Use, Capabilities, Workflows, Best Practices, Examples), but no bundle files exist and all ~240 lines are inline, so there is no actual file-level disclosure to reward.	4 / 5
	Total	16 / 20 Passed

Description

80%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 is specific and actionable, clearly stating what the skill does and giving a usable trigger clause. Its main weakness is a generic 'when' that omits the natural phrases users would actually say.

Suggestions

Replace the generic 'Use to organize, connect, and improve a knowledge base' with explicit trigger phrasing such as 'Use when the user asks to organize notes, find related or unlinked notes, merge duplicates, or clean up folders and tags.'

Add a few natural user phrases (e.g. 'clean up my notes', 'find related notes', 'what's not linked') to strengthen trigger-term coverage.

Briefly signal the boundary with memory-defrag (e.g. 'for knowledge-graph curation, not file-level memory hygiene') to reduce conflict risk with the sibling skill.

Dimension	Reasoning	Score
Specificity	Lists six concrete curation actions — 'find orphan notes and suggest links, propose typed relations, merge duplicates, audit tags and folders, and build hub notes' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Both 'what' (the six curation actions) and 'when' ('Use to organize, connect, and improve a knowledge base as notes accumulate') are stated, but the 'when' clause is generic rather than tied to concrete user trigger phrases.	4 / 5
Trigger Term Quality	Natural terms like 'organize, connect, and improve a knowledge base' and 'as notes accumulate' are present, but common user phrasings such as 'clean up my notes' or 'find related notes' are not included as triggers.	4 / 5
Distinctiveness Conflict Risk	The 'Basic Memory knowledge graph' niche with terms like 'orphan notes' and 'hub notes' is fairly distinct, though 'organize, connect, and improve' is broad enough to risk minor overlap with general organization skills.	4 / 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-curate/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.