agent-memory-systems

Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them.

Quality

52%

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/agent-memory-systems/SKILL.md

Quality

Content

43%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 body is a well-structured thin pointer that practices progressive disclosure cleanly, offloading detail to a confirmed one-level-deep reference. However, the body itself provides almost no actionable or workflow guidance, and repeats the description verbatim.

Suggestions

Surface a brief concrete procedure or key decision checklist in the body so Claude can act without always loading the full guide.

Drop or condense the verbatim repeat of the description and the "Key insight" rhetoric to save tokens.

Add a short sequenced overview (e.g. assess needs → pick memory type → choose retrieval strategy) with an explicit validation checkpoint, even if detail lives in the guide.

Dimension	Reasoning	Score
Conciseness	The 54-line body is mostly efficient, but the opening paragraph repeats the frontmatter description verbatim and "Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing…" is rhetorical padding, so it could be tightened.	3 / 5
Actionability	The body offers no concrete code, commands, or procedure — only "Read [the detailed guide]… before executing this skill" — which is a high-level hint missing the specific steps to execute (anchor 2).	2 / 5
Workflow Clarity	No sequenced steps or validation checkpoints appear in the body itself; everything is delegated to the guide, leaving only a rough "read guide then execute, treat validation as mandatory" directive with many gaps.	2 / 5
Progressive Disclosure	A clear overview with a single, well-signaled one-level-deep reference (references/detailed-guide.md, confirmed present) plus guidance on loading sections vs. reading fully gives easy navigation, matching anchor 5.	5 / 5
	Total	12 / 20 Passed

Description

61%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 scopes a coherent niche (agent memory architecture) with good natural keyword coverage, but lacks an explicit "Use when…" trigger clause and relies on the generic verb "covers" instead of concrete actions. This caps completeness and specificity at middling levels.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions agent memory, long-term memory, vector stores, RAG, or remembering across sessions".

Replace the generic "covers the architecture of" with concrete actions such as "designs, evaluates, and compares agent memory architectures".

Include a common synonym like "remembering across sessions" or "conversation history" to round out trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("agent memory") and enumerates concrete sub-areas — "short-term (context window)", "long-term (vector stores)", "cognitive architectures" — but the only action verb is the generic "covers", so it sits at anchor 3 rather than 4.	3 / 5
Completeness	The description gives a clear "what" ("covers the architecture of agent memory") but has no "Use when…" clause or explicit trigger guidance, so per the rubric completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes several natural terms a user would say ("agent memory", "context window", "vector stores", "long-term") giving good coverage, but misses common synonyms like "remember across sessions" or "recall" that keep it below 5.	4 / 5
Distinctiveness Conflict Risk	The agent-memory architecture niche is mostly distinct with only minor overlap risk against general RAG/vector-store skills, fitting anchor 4 rather than the fully-distinct 5.	4 / 5
	Total	14 / 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: sickn33/agentic-awesome-skills
Path: skills/agent-memory-systems/SKILL.md
Commit: b1aebac

Reviewed: ~18 hours 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.