CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

memory-curate

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

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

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.

Highly actionable content with concrete, parameterized tool calls and thoughtful gotchas for each capability. The main weakness is workflow clarity: destructive/batch curation operations lack explicit post-change validation loops, capping that dimension at 3.

Suggestions

Add explicit validation checkpoints after destructive or batch operations — e.g., after merging or moving notes, re-run bm orphans or bm_search to verify no unresolved [[links]] remain, and fix before reporting done.

Frame the health check as a before/after feedback loop: record orphan/duplicate counts at the start, apply changes, then re-measure to confirm the curation pass actually improved the graph.

Move the Example Conversations section into a references/ file (e.g., examples.md) and keep a one-line pointer in SKILL.md to reduce token load.

DimensionReasoningScore

Conciseness

Mostly lean operational guidance with useful API gotchas ("insert_after_section needs the heading to exist", permalink behavior on move); the intro paragraph restates the description and the Example Conversations section runs slightly long.

4 / 5

Actionability

Copy-paste-ready bm_search/bm_read/bm_edit/bm_move/bm_write calls with parameters, a documented <project> placeholder convention, a relation-type vocabulary, and a one-call CLI alternative ("bm orphans") cover the common cases.

5 / 5

Workflow Clarity

Capability sequences and scaled workflows (health check / deep session / topic pass) are described, but destructive and batch operations (merge, move, delete) have only "Confirm before changing" with no validate-then-fix feedback loops, so the batch-operation cap applies.

3 / 5

Progressive Disclosure

Well-organized single-file structure with clear numbered capabilities, a sibling-skill boundary note, and no bundle files to reference; minor content (Example Conversations, relation vocabulary) could be split into a reference file.

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.

A strong description that names five concrete capabilities in third person and includes an explicit "Use to..." trigger clause. The main gaps are a generic when-clause and trigger phrases that live in the body rather than the description itself.

DimensionReasoningScore

Specificity

Lists five concrete, distinct actions — "link orphan notes, propose typed relations, merge duplicates, audit tags and folders, build hub notes" — matching the comprehensive multi-action anchor.

5 / 5

Completeness

Both what and when are explicitly present ("Use to organize and connect a knowledge base as notes accumulate"), but the when clause is general and lacks concrete trigger phrases like "when the user mentions orphans, duplicates, or tag cleanup".

4 / 5

Trigger Term Quality

Natural terms like "orphan notes", "merge duplicates", "organize", and "knowledge base" are present, but common user phrasings such as "clean up my notes" or "find related notes" appear only in the body's When to Use section, not the description.

4 / 5

Distinctiveness Conflict Risk

The Basic Memory graph-curation niche is mostly distinct with specific triggers, but "merge duplicates" and "organize" overlap with the sibling memory-defrag skill (which handles note content) without the description drawing that boundary.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

basicmachines-co/basic-memory

Path

skills/memory-curate/SKILL.md

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.