Name: agent-memory-coordinator
Rating: 47 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-memory-coordinator

Agent skill for memory-coordinator - invoke with $agent-memory-coordinator

1.53x

Quality

18%

Does it follow best practices?

Impact

95%

1.53x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-memory-coordinator/SKILL.md

The canonical home for this skill is agent-memory-coordinator in ruvnet/claude-flow

Quality

Content

21%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 reads as a conceptual system catalog for an agent persona rather than an actionable skill: it explains memory-system concepts Claude already knows, provides no executable code or commands, and lacks validation-gated workflows. It is reasonably sectioned but monolithic with no progressive disclosure.

Suggestions

Cut the conceptual cataloging (compression, dedup, sharding, replication, caching) that Claude already knows and keep only skill-specific guidance.

Add concrete executable guidance: actual tool calls or API examples for store/retrieve/search/delete rather than abstract operation descriptions.

For destructive memory operations (delete, TTL expiry, garbage collection), add an explicit validate-then-confirm workflow with checkpoints to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The ~157-line body catalogues concepts Claude already knows (compression, deduplication, indexing, garbage collection, hot/cold caching, sharding, replication), matching the score-2 anchor of noticeably verbose padded sections; it stops short of score 1 only because it is organized as a structured reference rather than rambling prose.	2 / 5
Actionability	There is no executable code, command, or tool-call guidance anywhere — operations are described abstractly ("Store: Save data with optional TTL and encryption") and "examples" are sample utterances, matching the score-1 anchor of describing rather than instructing.	1 / 5
Workflow Clarity	Only a rough tips list ("Effective Memory Usage" 1-5) is present with no sequenced workflow and no validation checkpoints for destructive operations like delete/TTL/GC, matching the score-2 anchor; it is not 1 because some numbered structure exists.	2 / 5
Progressive Disclosure	The body has clear section headers but is a single monolithic inline document over 50 lines with no references to separate files (and no bundle files exist), matching the score-3 anchor of some structure but content that should be split is inline.	3 / 5
	Total	8 / 20 Passed

Description

16%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 auto-generated boilerplate that names a domain but provides no concrete capabilities, no natural trigger terms, and no usage guidance. It would rarely surface for the right request and tells Claude almost nothing about when to invoke it.

Suggestions

Replace the boilerplate with concrete actions, e.g. "Stores, retrieves, searches, and syncs persistent memory across sessions and agents."

Add an explicit trigger clause: "Use when the user asks to remember, recall, or persist information across sessions, or to share context between agents."

Include natural synonyms users say ("remember", "recall", "persist", "session memory") rather than only the technical "$agent-memory-coordinator" token.

Dimension	Reasoning	Score
Specificity	The description is pure boilerplate ("Agent skill for memory-coordinator") with no concrete actions named, matching the score-1 anchor of vague abstract language; it is even less specific than the score-2 example which at least names an action verb.	1 / 5
Completeness	It gives a vague "what" (memory-coordinator) but no "when" — there is no "Use when..." clause, matching the score-2 anchor; it cannot reach 3 because trigger guidance is entirely missing, and not 1 because a domain is at least named.	2 / 5
Trigger Term Quality	It offers only the technical jargon "$agent-memory-coordinator" and the term "memory-coordinator", with none of the natural phrases a user would say (e.g. "remember", "recall", "session"), matching the score-1 anchor of only technical jargon.	1 / 5
Distinctiveness Conflict Risk	The term "memory-coordinator" carves out a somewhat specific niche, matching the score-3 anchor, but the surrounding boilerplate is too vague to push higher and "memory" broadly risks overlap with other memory-related skills.	3 / 5
	Total	7 / 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: ruvnet/ruflo
Path: .agents/skills/agent-memory-coordinator/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.