agentmemory-architecture

How agentmemory is built, the iii engine primitives it runs on, its storage model, ports, and the viewer. Use when reasoning about how memory is stored or retrieved end to end, when extending the system, or when answering how agentmemory works under the hood.

Quality

76%

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 ./plugin/skills/agentmemory-architecture/SKILL.md

Quality

Content

68%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 exceptionally concise and well-structured, surfacing only non-obvious architectural facts and pointing outward to related skills. As a reference/overview skill it lacks executable guidance and sequenced workflows, which limits actionability and workflow clarity.

Suggestions

Add a short, concrete example of registering a new function plus trigger (e.g., a mem::* function and api::* trigger snippet) to lift actionability.

Include a minimal retrieval example (e.g., a curl against port 3111 or an MCP call) so the storage/retrieval model is actionable, not just descriptive.

If extending the system is a primary trigger, add a brief ordered checklist for adding a new capability to improve workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: each section states only the non-obvious facts (iii primitives, hybrid retrieval model, lifecycle stages, port arithmetic) with no padding or explanation of concepts Claude already knows.	5 / 5
Actionability	It gives concrete facts (specific ports, the capture/compress/consolidate/forget lifecycle, 'new capability is a new function plus a trigger') but no executable code, commands, or concrete steps; guidance is descriptive rather than instructive for an architecture/reference skill.	3 / 5
Workflow Clarity	There is no multi-step process to sequence and no validation checkpoints; the content is a reference overview. The simple-skill exception is inapplicable because this is not a single action, and there are no batch/destructive operations requiring feedback loops.	3 / 5
Progressive Disclosure	Well-organized into clear sections with a 'See also' list pointing to sibling skills (agentmemory-mcp-tools, agentmemory-rest-api, agentmemory-hooks, agentmemory-config) one level deep; minor gap is that no bundle files exist to verify referenced paths and the cross-links are to sibling skills rather than to deeper detail files.	4 / 5
	Total	15 / 20 Passed

Description

83%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 strong, third-person, and clearly answers both what the skill covers and when to use it, with concrete trigger phrases tied to architecture and under-the-hood reasoning. It could be slightly sharpened by adding a few more natural synonyms users might say.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete capabilities ('captures observations, indexes them for hybrid retrieval, and serves them back over REST and MCP', 'iii engine primitives', 'storage model, ports, and the viewer'), with minor gaps in coverage of the underlying mechanisms.	4 / 5
Completeness	Explicitly answers both 'what' (memory server capturing/indexing/serving observations over REST and MCP) and 'when' ('Use when reasoning about how memory is stored or retrieved...', 'when extending the system', 'when answering how agentmemory works under the hood') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('reasoning about how memory is stored or retrieved end to end', 'extending the system', 'answering how agentmemory works under the hood') with good coverage, though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	It targets a clear niche (agentmemory architecture internals) with distinct triggers, with only minor overlap risk against sibling skills like agentmemory-config or agentmemory-mcp-tools.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/agentmemory
Path: plugin/skills/agentmemory-architecture/SKILL.md
Commit: 2d38daf

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.