CtrlK
BlogDocsLog inGet started
Tessl Logo

memory-systems

This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization.

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/memory-systems/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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

A well-structured, comprehensive design skill with good progressive disclosure and a real reference file. It is held back by conceptual verbosity, a pseudocode temporal example, and a sparse benchmark table that reduce conciseness and actionability.

Suggestions

Trim the conceptual intro and 'Core Concepts' prose to assumption-of-competence density; move detailed framework/benchmark comparison tables into the existing reference file.

Replace the temporal-query pseudocode (graph.create_temporal_relationship/query_at_time) with a runnable example against a named library (e.g. Graphiti) or clearly label it as illustrative.

Fill or remove the '—' cells in the benchmark table so it conveys actionable signals rather than sparse placeholders.

DimensionReasoningScore

Conciseness

Mostly efficient with dense tables and code, but includes conceptual padding Claude already knows ('Memory provides the persistence layer...', 'Think of memory as a spectrum...') and a benchmark table padded with '—'/'Variable' cells that could be tightened.

2 / 3

Actionability

Provides executable Mem0 and Cognee examples plus concrete decision tables, but the temporal-query example uses non-real pseudocode APIs (graph.create_temporal_relationship / graph.query_at_time) and the benchmark table has many incomplete '—' entries.

2 / 3

Workflow Clarity

Presents a clear escalation sequence (Prototype → Scale → Complex reasoning → Full control) and ordered error-recovery strategies, but lacks explicit validation checkpoints; the measure-then-escalate feedback loop is only implicit.

2 / 3

Progressive Disclosure

Well-organized into clear sections with a single one-level-deep, well-signaled reference ('See [Implementation Reference](./references/implementation.md) ... Read when:') that resolves to a real bundle file, giving easy navigation.

3 / 3

Total

9

/

12

Passed

Description

85%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description with explicit activation guidance and excellent conflict-routing. Its main weakness is trigger-term naturalness — several terms are domain jargon rather than phrases a user would naturally say.

Suggestions

Add user-natural phrasings alongside the jargon, e.g. 'when the agent needs to remember things across sessions' or 'long-term memory for agents', so the description triggers on how users actually ask.

Consider leading with the natural trigger ('Use when an agent needs to persist knowledge or remember entities across sessions') before the technical capability list.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection' — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Answers both what (the enumerated capabilities) and when via the explicit 'This skill should be used for...' trigger clause, so it is not capped at 2.

3 / 3

Trigger Term Quality

Contains relevant terms ('persistent semantic memory', 'entity tracking') but leans on technical jargon ('temporal validity', 'memory consolidation', 'graph or vector retrieval') that a user may not naturally say, missing common phrasings like 'remember across sessions'.

2 / 3

Distinctiveness Conflict Risk

Establishes a clear niche and explicitly routes adjacent work away ('Route file-backed scratchpads to filesystem-context, handoff summaries to context-compression, and token-efficiency tactics to context-optimization'), making wrong-skill triggering unlikely.

3 / 3

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
muratcankoylan/Agent-Skills-for-Context-Engineering
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.