dive-memory-v3

Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.

Quality

70%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./desktop-app/backend/dive_core/skills/internal/dive-memory-v3/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a solid skill document with excellent actionability - nearly every feature has executable Python code examples. The progressive disclosure is well-handled with clear references to external documentation. However, it lacks explicit multi-step workflows with validation checkpoints for setup and maintenance operations, and could be more concise by trimming the troubleshooting and performance sections.

Suggestions

Add a 'Quick Start' workflow at the top with numbered steps: install → configure → start server → verify connection → first memory operation

Remove or significantly condense the 'Performance' and 'Troubleshooting' sections - these are reference material better suited for a separate troubleshooting.md file

Add validation checkpoints to the MCP setup process (e.g., 'Verify server is running: curl localhost:PORT/health')

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary sections like 'Performance' metrics and 'Troubleshooting' that add bulk without critical value. The use cases section, while helpful, could be more condensed since Claude can infer applications from the API examples.	2 / 3
Actionability	Excellent executable code examples throughout - every feature has copy-paste ready Python code with realistic parameters. MCP configuration JSON is complete and specific. Commands for starting the server are concrete.	3 / 3
Workflow Clarity	Individual operations are clear, but there's no explicit workflow for common multi-step processes like initial setup (install dependencies → configure → start server → verify). The 'Best Practices' section lists tips but doesn't sequence them into a setup or maintenance workflow with validation checkpoints.	2 / 3
Progressive Disclosure	Well-structured with clear sections progressing from core capabilities to advanced features. References to external files (api_reference.md, config.json, schema.sql) are clearly signaled at the end. Content is appropriately split between overview and detailed references.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 excels at listing specific capabilities and carving out a distinct niche for AI agent memory management. However, it relies on technical terminology that users may not naturally use, and lacks explicit 'Use when...' trigger guidance with user-facing scenarios. The 'when' component describes what the skill is good for rather than when Claude should select it.

Suggestions

Add explicit 'Use when...' clause with natural user triggers like 'remember this', 'recall what we discussed', 'save this for later', 'what did I tell you about X'

Include more natural language variations users might say: 'remember', 'recall', 'don't forget', 'persistent notes', 'save context'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'storing long-term memories', 'semantic search of past knowledge', 'building knowledge graphs', 'auto-injecting context', 'deduplicating memories', 'syncing to cloud storage'.	3 / 3
Completeness	Clearly explains what it does with detailed capabilities, but the 'when' guidance is weak - 'Use for...' lists features rather than user scenarios, and 'Essential for agents...' describes use cases abstractly rather than providing explicit trigger conditions.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'memory', 'knowledge graphs', 'semantic search', but uses technical jargon ('Model Context Protocol', 'MCP') and misses common user phrases like 'remember this', 'recall', 'save for later', 'persistent storage'.	2 / 3
Distinctiveness Conflict Risk	Clear niche focused on persistent memory and knowledge management for AI agents; the combination of 'memory system', 'MCP', 'knowledge graphs', and 'cross-session' creates a distinct identity unlikely to conflict with other skills.	3 / 3
	Total	10 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: duclm1x1/Dive-Ai
Commit: 20ba150

Reviewed: 5 months 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.