memory-continue

Resume prior work by rebuilding context from the Basic Memory knowledge graph — pick up where you left off using memory:// URLs, recent activity, and search. Use when starting a session or when the user says 'continue with...', 'back to...', or 'where were we?'

Quality

88%

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 well-structured, actionable skill with concrete tool calls and a clear sequenced workflow. Its main weaknesses are redundant re-demonstration of the same tools across sections and a monolithic structure with no progressive disclosure to separate reference files.

Suggestions

Collapse the Scenario Playbooks or refactor them to reference the tool signatures already shown in 'Building Context' rather than re-listing full build_context/recent_activity/search_notes calls, reducing redundancy.

Move the Memory URL Reference and Timeframe Reference tables into separate reference files (e.g. references/url-formats.md, references/timeframes.md) and link to them from the body to add one-level-deep progressive disclosure.

Tighten the Guidelines section by trimming explanatory phrasing (e.g. 'The graph's connections are the point —') so each guideline is a lean imperative.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the Scenario Playbooks re-demonstrate build_context/recent_activity/search_notes already shown in 'Building Context', adding redundant tokens that could be tightened.	2 / 3
Actionability	Provides concrete, executable MCP tool calls with real parameters throughout (build_context with url/depth/timeframe, recent_activity, search_notes, read_note, list_memory_projects), copy-paste ready and specific.	3 / 3
Workflow Clarity	A clearly sequenced 4-step process (Identify → Gather → Read → Present) with an explicit verification checkpoint ('Confirm understanding. Verify the reconstructed context is what the user actually needs before acting on it'); the read-only nature means the destructive-operation cap does not apply.	3 / 3
Progressive Disclosure	Well-organized into clear sections, but it is a monolithic single-file skill over 50 lines with no external reference files, and reference material (Memory URL Reference, Timeframe Reference, Scenario Playbooks) is inline that could be split out.	2 / 3
	Total	10 / 12 Passed

Description

100%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, third-person description that concretely states what the skill does and when to use it with natural trigger phrases. It is specific, complete, and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'rebuilding context from the Basic Memory knowledge graph' via 'memory:// URLs, recent activity, and search' — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what (rebuild context from the memory graph using URLs/recent activity/search) and when ('Use when starting a session or when the user says...'), with an explicit 'Use when' trigger clause.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say — "continue with...", "back to...", "where were we?" — plus 'starting a session', giving good coverage of real trigger terms.	3 / 3
Distinctiveness Conflict Risk	Tied to a clear niche — 'Basic Memory knowledge graph' and 'memory://' URLs — with distinctive trigger phrases, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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-continue/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.