conversation-memory

Persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.

Quality

38%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/conversation-memory/SKILL.md

Quality

Content

11%Scale 1-5

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

This skill is essentially a skeleton or outline with no substantive content. It names memory concepts and patterns but provides zero executable code, no implementation details, and no concrete guidance. The persona framing wastes tokens, and the anti-patterns and patterns sections are empty headers without explanations or examples.

Suggestions

Add concrete, executable code examples for each memory pattern (e.g., a tiered memory implementation with vector store for long-term and a list/deque for short-term memory)

Flesh out the anti-patterns with specific examples of what bad implementations look like and how to fix them

Define a clear workflow with numbered steps for implementing a memory system, including validation steps (e.g., testing retrieval relevance, checking memory isolation)

Remove the persona framing paragraph and replace it with actionable quick-start content showing a minimal working memory system

Dimension	Reasoning	Score
Conciseness	The skill wastes tokens on persona framing ('You're a memory systems specialist who has built AI assistants...') and explains concepts Claude already understands. The capabilities list is just keywords with no added value. However, it's not extremely padded—it's more sparse than verbose, but what's there is largely filler rather than useful content.	2 / 5
Actionability	There is no concrete code, no executable examples, no specific commands, and no actual implementation guidance. The patterns section names concepts ('Tiered Memory System', 'Entity Memory') without providing any implementation details, code snippets, or specific steps. Anti-patterns are listed as headers with no content beneath them.	1 / 5
Workflow Clarity	There is no workflow, no sequenced steps, and no validation checkpoints. The skill describes memory concepts at a high level but never explains how to actually implement any memory system. The sharp edges table offers solutions as comments ('// Implement memory lifecycle management') rather than actual steps.	1 / 5
Progressive Disclosure	The content has some section structure (Patterns, Anti-Patterns, Sharp Edges) but no references to supporting files, no bundle files exist, and the sections themselves are mostly empty shells. Content that should be detailed (pattern implementations, anti-pattern explanations) is either missing or stub-like.	2 / 5
	Total	6 / 20 Passed

Description

65%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 establishes a clear domain (LLM conversation memory) and includes a useful 'Use when' clause with relevant trigger terms. However, it lacks concrete action verbs describing what the skill actually does (e.g., store, retrieve, summarize, update memories), making it read more like a category label than a capability description. The trigger terms are decent but could include more natural user phrasings.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Stores, retrieves, and manages persistent memory across LLM conversations, including short-term context, long-term knowledge, and entity tracking.'

Expand trigger terms with additional natural phrases like 'recall', 'save context', 'session memory', 'context persistence', or 'remember previous conversations'.

Dimension	Reasoning	Score
Specificity	Names the domain ('persistent memory systems') and lists memory types (short-term, long-term, entity-based) but does not describe concrete actions like 'store', 'retrieve', 'summarize', or 'update' memories. The description is more of a category label than a list of capabilities.	2 / 5
Completeness	Has both a 'what' (persistent memory systems for LLM conversations including short-term, long-term, and entity-based memory) and a 'when' clause with explicit trigger terms. However, the 'what' is vague about specific actions, and the 'when' is a keyword list rather than descriptive trigger scenarios.	4 / 5
Trigger Term Quality	Includes several natural trigger terms: 'conversation memory', 'remember', 'memory persistence', 'long-term memory', 'chat history'. These are terms users would naturally use. Missing some variations like 'recall', 'context window', 'forget', 'save context', or 'session memory'.	4 / 5
Distinctiveness Conflict Risk	The focus on memory systems for LLM conversations is a fairly distinct niche. There could be minor overlap with general chatbot/conversation skills, but the specific mention of memory types (short-term, long-term, entity-based) and persistence helps distinguish it.	4 / 5
	Total	14 / 20 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/conversation-memory/SKILL.md
Commit: 57c135b

Reviewed: 3 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.