bedrock-agentcore-memory

Amazon Bedrock AgentCore Memory for persistent agent knowledge across sessions. Episodic memory for learning from interactions, short-term for session context. Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions.

Quality

72%

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/bedrock-agentcore-memory/SKILL.md

Quality

Content

57%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.

A thorough, code-rich guide with concrete executable examples across all operations, but it is long and repetitive, lacks validation checkpoints around batch/destructive actions, and cites reference files that are missing from the bundle.

Suggestions

Remove duplicated code between the Operations and Integration sections, and move time-sensitive items (model ids, the 'validated by AWS December 2025' note) into a clearly marked deprecated/versioning section to tighten conciseness.

Add validation checkpoints to batch and destructive operations — e.g., confirm record count before batch_delete, and verify deletion succeeded after the GDPR right-to-be-forgotten flow.

Either create the three referenced files under references/ or remove the broken reference links, and consider splitting the bulk of the operation/integration code into those reference files so SKILL.md stays an overview.

Dimension	Reasoning	Score
Conciseness	Mostly code-forward, but the ~700-line body repeats patterns across sections (create_event and get_relevant_memories are re-implemented in the Integration section) and carries time-sensitive strings ('validated by AWS December 2025', model id 'anthropic.claude-3-sonnet-20240229-v1:0') that are not isolated in a deprecated/old-patterns section.	3 / 5
Actionability	Provides mostly executable boto3 code across all five operations and an integration pattern, with minor gaps such as undefined helpers (extract_topics, deduplicate) and a vague 'Batch API may be available - check latest docs' note.	4 / 5
Workflow Clarity	Operations are sequenced, but batch and destructive operations (batch_delete_memory_records, the GDPR 'right to be forgotten' deletion) lack validation or verify checkpoints, which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	A clearly signaled one-level References section exists, but the three cited files (references/memory-patterns.md, privacy-compliance.md, extraction-tuning.md) do not exist in the bundle, and most operational content is inlined into SKILL.md rather than split out.	3 / 5
	Total	13 / 20 Passed

Description

87%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.

A strong, third-person description that clearly states both the capability and concrete use-when triggers, with a distinct niche and minimal conflict risk. Minor specificity gains would come from enumerating the full set of memory operations rather than implying them.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities — 'Episodic memory for learning from interactions, short-term for session context' and 'persistent agent knowledge across sessions' — rather than vague language, though coverage of the full action set is slightly implied rather than enumerated.	4 / 5
Completeness	Explicitly answers both what ('Amazon Bedrock AgentCore Memory for persistent agent knowledge...') and when ('Use when building agents that remember user preferences, learn from conversations, or maintain context across sessions') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('agents that remember user preferences', 'learn from conversations', 'maintain context across sessions'), with good but not exhaustive keyword coverage.	4 / 5
Distinctiveness Conflict Risk	'Amazon Bedrock AgentCore Memory' is a clear, specific niche with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (704 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/bedrock-agentcore-memory/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.