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

84%

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

86%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 and well-structured, with executable templates and clear sequencing including existing-entity and approval checkpoints. The main improvement is light redundancy between the in-workflow guidance and the closing Guidelines section.

Suggestions

Remove the overlap between the embedded workflow guidance and the final "Guidelines" section, or collapse the Guidelines into a short checklist that only adds net-new points, to push conciseness to 5.

Add an explicit validation/retry step (e.g., verify the created note resolved correctly and re-run edit_note if a section was missed) to strengthen workflow clarity for the graph-mutating operations.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no boilerplate about what companies or technologies are) and the templates are purposeful. It is not a 5 because the closing "Guidelines" section restates points already embedded in the workflow (always web search, hedge uncertain info, capture user context), creating mild redundancy; it is above the midpoint so 4 rather than 3.	4 / 5
Actionability	It provides fully executable, copy-paste-ready code (search_notes, write_note, edit_note) with complete parameter values and per-entity-type content templates, covering the common organization/person/technology cases.	5 / 5
Workflow Clarity	Six steps are clearly sequenced with real checkpoints (Step 2 checks for an existing entity and branches, Step 4 requires explicit user approval before creating). It is not a 5 because there is no explicit validate-fix-retry error-recovery loop, and the existing-entity/approval gates do not fully substitute for that on a graph-mutating skill.	4 / 5
Progressive Disclosure	It is a single, self-contained SKILL.md with no bundle files, well-organized under clear section headers (When to Use, Workflow, Guidelines). Per the simple-skill scoring note, a self-contained skill with well-organized sections and no need for external references scores 5.	5 / 5
	Total	18 / 20 Passed

Description

82%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 strong: it clearly states both the action and the trigger conditions, including implicit triggers, with natural phrasing a user would actually say. The only minor gap is that it lists two actions rather than a comprehensive set of specific capabilities.

Suggestions

Add one or two more concrete capability verbs (e.g., "check for an existing entry before creating" or "link the new entity to related knowledge") to lift specificity from 3 toward 4-5.

Consider listing a couple more natural synonyms or phrasings users might say (e.g., "look up", "find out about") to push trigger-term coverage toward exhaustive.

Dimension	Reasoning	Score
Specificity	Names the domain and two concrete actions ("research an external subject using web search", "synthesize findings into a structured Basic Memory entity"), but does not list several specific actions. It is not a 4 because only two verbs are given rather than a broader set of specific operations.	3 / 5
Completeness	It explicitly answers both what (research an external subject and synthesize into a structured Basic Memory entity) and when ("Use when asked to research a company, person, technology, or topic — or when a bare name or URL is provided") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user-facing terms are well covered ("research", company/person/technology/topic, "bare name or URL") with synonyms and implicit-trigger phrasing. It is not a 5 because coverage is not exhaustive in the sense of the anchor-5 example (e.g., no file-extension-style synonyms), though it is clearly above the midpoint.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (external research synthesized into a Basic Memory entity) with distinct triggers including implicit bare-name/URL cases, giving minimal conflict risk 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-research/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.