CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean overview: dense with system-specific facts, no filler, and clean handoff to sibling skills for the operational details. As an instruction-free reference skill its actionability is inherently descriptive, which is the only dimension where it falls short of full marks.

DimensionReasoningScore

Conciseness

Every line carries non-obvious information (e.g., 'REST is the anchor at 3111. Streams = N+1 (3112), viewer = N+2 (3113), engine = N+46023 (49134). `--instance N` shifts the whole block by N*100') with zero padding and no explanation of concepts Claude already knows.

5 / 5

Actionability

Guidance is concrete and usable — port arithmetic, the 'new capability is a new function plus a trigger' rule, the mem::/api:: namespace conventions, and the viewer URL — but it is descriptive architecture rather than executable steps, leaving minor gaps against the fully-executable anchor.

4 / 5

Workflow Clarity

This is a single-purpose architectural reference under 50 lines with an unambiguous purpose (explaining how agentmemory works end to end); the simple-skill exception applies, and the lifecycle sequence (capture, compress, consolidate, forget) is stated coherently.

5 / 5

Progressive Disclosure

Well-organized short sections with no need for external references, and the 'See also' list points one level deep to clearly-named sibling skills (agentmemory-mcp-tools, agentmemory-hooks, agentmemory-config) for the detailed surfaces.

5 / 5

Total

19

/

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.

A strong description that clearly separates architectural understanding from surface usage, with an explicit multi-scenario 'Use when' clause and natural trigger phrasing. Its only weakness is that the 'what' enumerates subsystems rather than a few more user-recognizable action keywords that would widen trigger coverage.

Suggestions

Add one or two natural trigger synonyms users would type, such as 'extend agentmemory' or 'debug why a memory was (or wasn't) retrieved', to broaden trigger coverage.

Name the concrete artifacts users interact with (e.g., 'the web viewer on port 3113', 'sessions and commits') in the 'what' portion so those keywords can also match user phrasing.

DimensionReasoningScore

Specificity

The description lists several specific coverage areas — 'the iii engine primitives it runs on, its storage model, ports, and the viewer' — rather than generic claims, but they are topics rather than concrete actions, leaving minor gaps versus the comprehensive anchor.

4 / 5

Completeness

Both parts are explicit: the 'what' enumerates the subsystems covered, and the 'when' opens with 'Use when reasoning about... when extending the system, or when answering how agentmemory works under the hood' — three concrete trigger scenarios matching the top anchor.

5 / 5

Trigger Term Quality

Natural phrases like 'how agentmemory is built', 'memory is stored or retrieved end to end', 'extending the system', and 'under the hood' match what a user would actually say; a few common variations (e.g., 'extend agentmemory', 'how memory works') are missing, so it falls just short of the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

'Under the hood' / 'how it is built' framing carves a clear niche apart from the sibling surface skills (mcp-tools, rest-api, hooks), but the memory-retrieval trigger could plausibly fire for those closely related siblings, so minor overlap risk remains.

4 / 5

Total

17

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rohitg00/agentmemory
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.