import

Imports memories from an exported Markdown file or MEMORY.md into the current project. Use when migrating from another project, restoring from backup, importing Claude Code native MEMORY.md content, or setting up a new project with existing knowledge.

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

80%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 lean, highly actionable skill body with concrete commands and clear step sequencing. The main weakness is the absence of an explicit validation/verification checkpoint for what is a batch import operation, and all distinct import modes being kept inline rather than split into reference files.

Suggestions

Add an explicit validation checkpoint in the main import flow, e.g. after Step 4 verify the success count matches the parsed record count and reconcile any mismatch before reporting in Step 5.

Split the three import modes (mem0 export, --tools competing tools, native MEMORY.md) into one-level-deep reference files (e.g. COMPETING_TOOLS.md, MEMORY_MD_IMPORT.md) with clearly signaled links from the main body.

Deduplicate the repeated `infer=False` and metadata instructions into a single shared "add_memory call conventions" note to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense and action-oriented—bash snippets, structured steps, and tables—without explaining concepts Claude already knows, matching the lean top anchor; minor restatements of `infer=False` are not enough to drop it to 2.	3 / 3
Actionability	It provides concrete, executable commands (e.g. `python3 "<PLUGIN_ROOT>/scripts/parse_export_file.py" "<path-to-export-file>"`), specific `add_memory` parameter lists, exact detection commands, and copy-paste output strings, matching the fully-executable top anchor.	3 / 3
Workflow Clarity	Steps 1–5 and the T1–T4 flow are clearly sequenced with per-step error fallbacks, but this batch import operation has no explicit validate/verify checkpoint (e.g. confirm imported count equals parsed count), so per the rubric notes workflow_clarity is capped at 2; not 1 because the sequence is explicit, not 3 because no validation feedback loop exists.	2 / 3
Progressive Disclosure	The body is organized into clear single-level sections, but everything is inline—three distinct import modes (mem0 export, competing tools, native MEMORY.md) that could be separate reference files are packed into one document, matching anchor 2's "content that should be separate is inline"; not 3 because no one-level-deep reference navigation is used.	2 / 3
	Total	10 / 12 Passed

Description

90%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 with an explicit "Use when" clause covering several natural triggers and a clear statement of what the skill does. Its only gap is moderate specificity, since it describes one import action rather than enumerating multiple distinct operations.

Dimension	Reasoning	Score
Specificity	It names the domain and a concrete action ("Imports memories from an exported Markdown file or MEMORY.md into the current project") but offers one action verb across several sources rather than a list of multiple distinct concrete actions, matching anchor 2; not a 3 because it lacks the multi-action breadth of the top anchor.	2 / 3
Completeness	It explicitly states what the skill does ("Imports memories ... into the current project") and when to use it via an explicit "Use when" clause with multiple triggers, satisfying the top anchor's what-and-when requirement.	3 / 3
Trigger Term Quality	The "Use when migrating from another project, restoring from backup, importing Claude Code native MEMORY.md content, or setting up a new project" clause gives natural scenario-based triggers a user would actually say, matching the top anchor's coverage.	3 / 3
Distinctiveness Conflict Risk	"Imports memories" plus migration/backup/MEMORY.md triggers carve a clear niche unlikely to fire for unrelated skills, matching the top anchor's distinct-trigger profile.	3 / 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: mem0ai/mem0
Path: integrations/mem0-plugin/skills/import/SKILL.md
Commit: b357a5a

Reviewed: 7 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.