Name: conversation-memory
Rating: 48 (1 reviews)
Author: administrakt0r

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

51%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/conversation-memory/SKILL.md

The canonical home for this skill is conversation-memory in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

32%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 skill body is well-sectioned but substantively thin: persona-flavored intro padding, no concrete or executable guidance, and no real workflow, with a truncated principles list. It reads as a concept outline rather than actionable instructions.

Suggestions

Cut the persona intro and truncated 'core principles' list; replace with concrete actions for each capability (e.g., how to store, retrieve, decay, and surface memories).

Turn Sharp Edges 'solutions' into concrete steps or short code/pseudocode rather than '// ...' comment stubs.

Add a minimal end-to-end workflow for the common case (capture a memory -> consolidate -> retrieve relevant memories -> inject into the prompt) with an explicit verification step.

Dimension	Reasoning	Score
Conciseness	The opening persona narrative ('You're a memory systems specialist who has built AI assistants that remember users across months of interactions...') is padded framing Claude does not need, and the truncated 'core principles: 1. Memory types differ—short-term, lo' adds noise without value.	2 / 5
Actionability	Guidance is high-level and descriptive ('Store and update facts about entities', 'Include relevant memories in prompts') with no concrete steps, code, or commands; the Sharp Edges 'solutions' are code-comment stubs ('// Implement memory lifecycle management') rather than executable instructions.	2 / 5
Workflow Clarity	There is no multi-step workflow or sequenced process; content is a set of categorized concept labels, and the only numbered list ('core principles') is truncated mid-sentence, leaving no coherent sequence or checkpoints.	2 / 5
Progressive Disclosure	The body is short and organized into clearly headed sections (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills, When to Use) with no external bundle files needed; minor gaps like empty Anti-Pattern stubs keep it just below a 5.	4 / 5
	Total	10 / 20 Passed

Description

70%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 is well-formed: third-person voice, an explicit 'Use when:' trigger list, and a clearly scoped memory niche. Its main weakness is that the 'what' lists memory categories rather than concrete actions, capping specificity and completeness just below the top.

Suggestions

Replace category enumeration with concrete actions, e.g. 'Store, retrieve, and surface relevant memories across short-term, long-term, and entity-based stores for LLM conversations.'

Add a few natural synonyms/variations to the triggers (e.g. 'user memory', 'recall past messages') for fuller keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Persistent memory systems for LLM conversations') and enumerates memory types ('short-term, long-term, and entity-based memory'), but these are categories rather than concrete actions, so it sits at the 'names domain + 1-2 concrete elements' level rather than comprehensive actions.	3 / 5
Completeness	It explicitly answers both 'what' (persistent memory systems with three named types) and 'when' (a 'Use when:' clause with concrete triggers); the 'what' could be more action-oriented, keeping it just below a 5.	4 / 5
Trigger Term Quality	The 'Use when:' clause supplies several natural terms a user would actually say ('conversation memory, remember, memory persistence, long-term memory, chat history'), giving good coverage with only minor synonyms missing.	4 / 5
Distinctiveness Conflict Risk	The memory-system niche with dedicated triggers is mostly distinct, with only minor overlap risk against closely related skills it itself names (rag-implementation, context-window-management, prompt-caching).	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/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.