agent-memory
Add memory capabilities to your agent. Use when: (1) User asks about 'memory', 'state', 'remember', 'conversation history', (2) Want to persist conversations or user preferences, (3) Adding checkpointing or long-term storage.
83
79%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/agent-langgraph-memory/SKILL.mdQuality
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description with explicit trigger guidance and good keyword coverage. Its main weakness is that the 'what' portion is somewhat high-level—'add memory capabilities' is broad and could benefit from listing more concrete actions like specific storage or retrieval operations. The description also uses second person ('your agent') which is not ideal but less penalizable than first person.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Store and retrieve conversation history, save user preferences, implement checkpointing for long-running agent workflows'.
Rephrase to third person voice: 'Adds memory capabilities to agents' instead of 'Add memory capabilities to your agent'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('memory capabilities') and some actions like 'persist conversations', 'user preferences', 'checkpointing', 'long-term storage', but doesn't list multiple concrete specific actions (e.g., no mention of specific APIs, storage mechanisms, or retrieval methods). | 2 / 3 |
Completeness | Clearly answers both 'what' (add memory capabilities to your agent) and 'when' with an explicit 'Use when:' clause listing three specific trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'memory', 'state', 'remember', 'conversation history', 'persist conversations', 'user preferences', 'checkpointing', 'long-term storage'. These cover a good range of terms a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | 'State' and 'remember' are somewhat generic terms that could overlap with other skills (e.g., state management in UI frameworks, general knowledge recall). However, the combination with 'memory', 'conversation history', and 'checkpointing' narrows the scope reasonably well. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill that provides clear step-by-step guidance for adding memory to a LangGraph agent on Databricks. Its main strengths are executable code examples, comprehensive troubleshooting, and a clear setup checklist. Its weakness is length — the document tries to be both a quick-start guide and a comprehensive reference, leading to some redundancy that could be addressed by splitting detailed patterns into a separate file.
Suggestions
Move the 'Key Principles' section (patterns 1-5) into a separate reference file like `MEMORY_PATTERNS.md` and link to it, keeping SKILL.md focused on the setup workflow.
Remove the 'First-Time Setup Checklist' section or consolidate it with the step-by-step instructions above it, as it largely duplicates information already presented.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., the setup checklist largely repeats information already covered in the step-by-step sections, and the 'Key Principles' section explains patterns that could be more concisely shown in the complete example). The troubleshooting table and testing sections add value but the overall document is quite long (~250 lines) with some content that could be consolidated. | 2 / 3 |
Actionability | The skill provides fully executable code examples throughout: complete Python snippets for memory tools, configuration YAML, curl commands for testing, and a table initialization script. Every step includes copy-paste ready commands and code with specific values and patterns. | 3 / 3 |
Workflow Clarity | The multi-step process is clearly sequenced with a 'Quick Setup Summary' table showing all 4 files to modify, numbered steps for configuration, a first-time setup checklist with checkboxes, and explicit validation via the testing section. The table initialization step is clearly marked as 'First Time Only' and the deploy step references another skill. | 3 / 3 |
Progressive Disclosure | The skill references other skills (lakebase-setup, deploy, run-locally) and external templates well, but the document itself is quite long and monolithic. The 'Key Principles' section with 5 detailed patterns could be split into a separate reference file. The skill references `examples/memory_tools.py` but no bundle files were provided, making it impossible to verify that reference exists. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- databricks/app-templates
- Commit
dfeb4ac
- 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.