CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-openai-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.

63

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/agent-openai-memory/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The content is well-structured, actionable, and reasonably concise, with concrete code and a clear testing workflow. The main gaps are a few undefined helper fragments and all content being inlined with no bundle references to split out detail.

Suggestions

Define or link the referenced helpers (init_lakebase_config, uuid7, get_session_id's full context) so code examples are fully self-contained.

Add an explicit validation checkpoint in the setup workflow (e.g., 'Confirm the session persists before deploying') to raise workflow clarity.

Move the troubleshooting table and/or extended testing recipes into a reference bundle file and link from the body to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient with tight tables, code blocks, and clear sections; minor over-explanation such as 'This eliminates the need to manually manage conversation state between runs' could be trimmed.

4 / 5

Actionability

It provides concrete, mostly copy-pasteable code (session creation, get_session_id, YAML config, curl tests) and a troubleshooting table, but a few fragments like init_lakebase_config() and uuid7() are referenced without full definition.

4 / 5

Workflow Clarity

Numbered prerequisites, ordered configuration steps, and a multi-turn test sequence (first message -> note session_id -> second message to verify recall) give a clear sequence with an implicit validation checkpoint, though no explicit validate-then-proceed gate.

4 / 5

Progressive Disclosure

The ~170-line body is well organized into clearly headed sections and signals external skills (lakebase-setup, run-locally, deploy), but all detail lives inline with no bundle files to offload it, leaving minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

73%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.

The description clearly answers both what and when with strong, natural trigger terms, but its generic main action verb and second-person voice ('your agent') weaken specificity. Distinctiveness is good with only minor overlap risk.

Suggestions

Rewrite the action clause in third person with concrete verbs, e.g. 'Persists conversation history and user preferences for OpenAI Agents SDK agents', to remove the second-person penalty and raise specificity.

Add a couple of common synonyms users say, such as 'save', 'recall', or 'chat history', to round out trigger-term coverage toward a 5.

Tie the triggers more tightly to the Databricks/Lakebase implementation to sharpen distinctiveness from generic memory skills.

DimensionReasoningScore

Specificity

The what-action 'Add memory capabilities to your agent' names the memory domain with a few concrete scenarios (persist conversations, checkpointing, long-term storage), but the primary verb is generic; second-person voice ('your agent') triggers the -1 specificity penalty per the judging guidelines, pulling a base of 3 down to 2.

2 / 5

Completeness

It explicitly states both what ('Add memory capabilities to your agent') and when ('Use when: (1)... (2)... (3)...') with concrete, enumerated trigger phrases.

5 / 5

Trigger Term Quality

Natural terms like 'memory', 'state', 'remember', 'conversation history', 'persist', 'user preferences', and 'checkpointing' give good keyword coverage, though common variations such as 'save', 'recall', or 'chat history' are missing.

4 / 5

Distinctiveness Conflict Risk

The memory/state niche is mostly distinct with specific triggers, but 'memory' and 'state' could overlap with other persistence- or session-related skills, leaving minor conflict risk.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
databricks/app-templates
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.