memory-research

Research an external subject using web search, synthesize findings into a structured Basic Memory entity. Use when asked to research a company, person, technology, or topic — or when a bare name or URL is provided that implies a research request.

Quality

85%

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

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.

A highly actionable, well-sequenced skill body with concrete executable code and a clear six-step workflow including an approval gate. Its weaknesses are conciseness (redundant templates and a restating Guidelines section) and progressive disclosure (a monolithic file with no references splitting out the templates).

Suggestions

Condense the three near-identical Organization/Person/Technology write_note templates into one parameterized template with a small per-type diff table, since they share most of their structure.

Trim or remove the closing 'Guidelines' section — its bullets (Always web search, Search Basic Memory first, Hedge, Get approval, Capture user context) restate steps already covered in the workflow.

Move the entity-type info table and the full write_note templates into a references/ file (e.g. TEMPLATES.md) linked from the workflow, so the SKILL.md becomes a leaner overview with one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (it does not explain concepts Claude knows), but the three near-identical Organization/Person/Technology templates and the closing Guidelines section largely restate the workflow, so it could be tightened rather than earning the lean level-3 anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready guidance — real `search_notes`, `write_note`, and `edit_note` calls with concrete parameters, plus specific search-query and markdown-summary templates — matching the level-3 anchor.	3 / 3
Workflow Clarity	A clearly sequenced six-step workflow with explicit validation checkpoints (Step 2 dedup check against Basic Memory, Step 4 yes/no/modify approval gate before creation), satisfying the level-3 anchor for a clear sequence with feedback loops; no destructive/batch cap applies since approval is present.	3 / 3
Progressive Disclosure	The ~230-line SKILL.md is well-sectioned internally but monolithic with no bundle files: content that could live in a reference (the entity-type table and full per-type templates) is inline, matching the level-2 anchor of structure present but content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

92%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, well-constructed description: it states concrete capabilities and gives explicit, natural trigger phrasings covering both direct requests and implicit cues. The only soft spot is that the broad implicit bare-name/URL triggers create some overlap risk with adjacent skills.

Dimension	Reasoning	Score
Specificity	"Research an external subject using web search, synthesize findings into a structured Basic Memory entity" names multiple concrete actions (research via web search, synthesize into a structured entity) with their methods, matching the level-3 anchor for listing specific concrete actions.	3 / 3
Completeness	It explicitly answers both what (research + synthesize into a Basic Memory entity) and when (a "Use when..." clause with explicit entity-type and implicit-name/URL triggers), satisfying the level-3 anchor and avoiding the missing-trigger cap of 2.	3 / 3
Trigger Term Quality	The "Use when..." clause surfaces natural terms users would actually say — "research", "company", "person", "technology", "topic", plus "bare name" and "URL" for implicit triggers — giving good coverage of natural phrasings.	3 / 3
Distinctiveness Conflict Risk	The Basic Memory entity output gives it a niche, but the implicit triggers "a bare name or URL is provided" are broad and could overlap with generic web-search or URL-fetching skills, matching the level-2 anchor of being somewhat specific but still able to overlap.	2 / 3
	Total	11 / 12 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-research/SKILL.md
Commit: cb95e59

Reviewed: 11 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.