CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

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

82%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.

A well-structured, highly actionable skill body: concrete search patterns, complete tool-call templates per entity type, and a workflow with genuine approval and duplicate-check checkpoints. The two weaker spots are a redundant closing Guidelines section that repeats the steps, and no error-handling guidance for the note-creation calls.

Suggestions

Trim or fold the closing Guidelines section into the steps it repeats — 'Always web search', 'Search Basic Memory first', and 'Get approval before creating' are already demonstrated in Steps 1, 2, and 4 — to tighten conciseness.

Add a brief failure path for Step 5/6 (e.g., what to do if write_note fails or the target section doesn't exist in edit_note) to complete the workflow's validation loop.

Consider moving the three full write_note templates (Organization/Person/Technology) into a references/ file with one-level-deep links, keeping only the common structure inline, to reduce SKILL.md bulk.

DimensionReasoningScore

Conciseness

The body is dense with actionable material — entity-type tables, search query patterns, hedging examples, and complete write_note templates — with almost no explanation of concepts Claude already knows. Minor trimmable redundancy: the closing Guidelines section restates rules already demonstrated in the steps (e.g., "Always web search" repeats Step 1; "Search Basic Memory first" repeats Step 2), and "This context is often the most valuable part..." is a light editorial aside. Efficient overall, so 4 rather than 3; not 5 because of that redundant recap section.

4 / 5

Actionability

Fully concrete and executable throughout: explicit search query patterns, search_notes(query="Acme Corp") examples, complete write_note(...) templates with all parameters (title, directory, note_type, tags, content) and fully structured note bodies, and an edit_note(...) call with a specific operation ("insert_after_section") and section. Placeholders like "[2-3 sentence description from research]" are appropriate for an instruction-shaped skill and keep the guidance copy-paste adaptable.

5 / 5

Workflow Clarity

Six clearly sequenced steps with a real validation checkpoint: Step 2 searches for existing entities before proposing anything (update rather than duplicate), and Step 4 asks explicit approval ("Create Basic Memory entity for [Subject]? ... [yes / no / modify]") before Step 5 creates the entity. Not 5 because there is no guidance for handling write_note/edit_note failures (e.g., a wrong directory or missing section), leaving a minor validation gap at the creation step.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), so everything is inline — which is coherent for a single-file skill. The body is well sectioned (Workflow steps 1-6, then Guidelines) with templates clearly separated by entity type. Not 5 because at ~220 lines the three full write_note templates (Organization/Person/Technology) are bulk content that could naturally live in a references/ file; not 3 because what is present is clearly signaled and easy to navigate.

4 / 5

Total

17

/

20

Passed

Description

78%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 explicitly states both what the skill does and when to use it, with natural trigger phrasing and a distinctive Basic Memory framing. The main gaps are modest: the action list could be more comprehensive and a few natural trigger synonyms ("look up", "background on") are absent.

Suggestions

Enumerate one or two more concrete sub-actions in the description (e.g., 'check Basic Memory for existing entities and update rather than duplicate') to lift specificity beyond two named actions.

Add natural trigger synonyms such as 'look up' or 'background on' alongside 'research' to broaden the natural-phrase coverage without adding vagueness.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions — "Research an external subject using web search, synthesize findings into a structured Basic Memory entity" — with a clear output artifact, but does not enumerate the fuller set of sub-actions (checking existing notes, approval, storing source context). Matches the anchor for 'domain and 1-2 concrete actions, but not comprehensive'; not 4 because coverage of actions is thinner than 'several specific actions'.

3 / 5

Completeness

Explicitly answers both: what — "Research an external subject using web search, synthesize findings 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 that implies a research request." Concrete trigger phrases for both, matching the top anchor.

5 / 5

Trigger Term Quality

Natural user phrasing is present: "asked to research a company, person, technology, or topic" plus the distinctive "when a bare name or URL is provided that implies a research request." Good coverage of natural terms, but common synonyms like "look up", "find out about", or "background on" are missing. Not 5 because the synonym coverage is incomplete; not 3 because the enumerated entity types and the bare-name trigger are genuinely natural phrases users say.

4 / 5

Distinctiveness Conflict Risk

The "structured Basic Memory entity" output gives it a clear niche distinct from a generic web-research or deep-research skill. Minor overlap remains: the "bare name or URL is provided" trigger is fairly broad and a general research skill could also claim it. Mostly distinct with minor overlap risk rather than a fully conflict-free niche.

4 / 5

Total

16

/

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
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.