agent-memory-coordinator

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

1.53x

Quality

—

Does it follow best practices?

Impact

95%

1.53x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

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 catalog of memory-system features rather than actionable guidance: it lists capabilities, namespaces, and best practices in the abstract with no executable code, commands, or validation-gated workflows. It is also a monolithic ~187-line document with no progressive disclosure.

Suggestions

Replace abstract feature lists with concrete, executable guidance: actual tool calls or commands for store/retrieve/search/delete/sync with copy-paste-ready examples.

Add a validation/feedback loop for destructive or batch memory operations (e.g. verify key exists before delete, confirm sync conflicts resolved).

Trim generic concepts Claude already knows (compression, sharding, replication, encryption-at-rest) and split detailed references into separate files linked from a concise overview.

Dimension	Reasoning	Score
Conciseness	The ~187-line body is padded with abstract descriptions of generic memory-system concepts (compression, deduplication, sharding, replication, encryption) that Claude already knows, with little operational content earning its tokens.	1 / 3
Actionability	There is no executable code, commands, or concrete tool/API calls; the 'Usage Examples' are user sentences and the 'Best Practices' are abstract advice, so the body describes rather than instructs.	1 / 3
Workflow Clarity	No operational multi-step sequence for performing memory operations is present, and there are no validation checkpoints despite memory operations being destructive/batch-like in nature.	1 / 3
Progressive Disclosure	The content is organized into clear headed sections, but it is a single oversized monolithic file (~187 lines) with no external references or overview-pointing-to-details structure, so material that should be split stays inline.	2 / 3
	Total	5 / 12 Passed

Description

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 a generic, auto-generated-style label that restates the skill name and gives an invocation hint, with no concrete capabilities, no natural trigger terms, and no 'use when' guidance. It does little to help a user or Claude decide when this skill applies.

Suggestions

Replace the description with concrete actions, e.g. 'Store, retrieve, search, and sync persistent memory across sessions and namespaces. Use when the user asks to remember, recall, or share context across agents or sessions.'

Add natural trigger terms users would actually say (e.g. 'remember', 'recall', 'persist', 'what did we decide', 'continue from where we left off').

Add an explicit 'Use when...' clause so Claude knows the triggering conditions.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for memory-coordinator - invoke with $agent-memory-coordinator') names a domain but lists no concrete actions, restating what the skill is rather than what it does, matching the vague/abstract anchor.	1 / 3
Completeness	'what' is stated circularly via the skill name and 'when to use it' is entirely missing (the 'invoke with' clause describes how, not when), failing both halves.	1 / 3
Trigger Term Quality	The only trigger-like phrase is 'invoke with $agent-memory-coordinator', an invocation syntax rather than a natural keyword a user would say; no everyday terms are present.	1 / 3
Distinctiveness Conflict Risk	The named memory-coordination domain is more specific than generic catch-alls, but the description provides no distinct trigger language to disambiguate it from other memory/persistence skills.	2 / 3
	Total	5 / 12 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/claude-flow
Commit: 03d4f84

Reviewed: 2 days 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.