agent-swarm-memory-manager

Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager

2.25x

Quality

Does it follow best practices?

Impact

90%

2.25x

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-swarm-memory-manager/SKILL.md

Quality

Content

0%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is a verbose, aspirational description of a distributed memory management system rather than actionable instructions. The code examples are syntactically invalid hybrids of JavaScript and MCP tool calls that cannot be executed. Core concepts like CRDT, vector clocks, and multi-level caching are name-dropped without concrete implementation, and the entire document reads more like a design document than an operational skill.

Suggestions

Replace all code examples with valid, executable MCP tool call syntax — either proper tool_use format or the exact invocation pattern Claude should use, not JavaScript-MCP hybrids.

Remove explanations of well-known CS concepts (CRDT, LRU, vector clocks, sharding) and instead provide the specific key naming conventions, namespaces, and JSON schemas Claude should actually use.

Add a clear sequential workflow: 1) Initialize memory state → 2) Monitor for updates → 3) Sync with validation → 4) Handle conflicts with specific resolution steps → 5) Verify sync success.

Remove placeholder metric values (1000 ops/sec, 0.85 cache hit rate) and either compute real metrics or explain how to derive them from actual operations.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with many concepts Claude already knows (CRDT, LRU, vector clocks, write-ahead logging, sharding). The code examples are pseudocode that mixes JavaScript syntax with MCP tool call syntax in a non-executable way. Hardcoded metric values (1000 ops/sec, 0.85 cache hit rate) are meaningless placeholders that waste tokens.	1 / 3
Actionability	The code examples are not executable — they mix JavaScript async/await syntax with MCP tool invocation syntax in an invalid way (e.g., `await mcp__claude-flow__memory_usage { action: ... }` is neither valid JS nor a proper MCP tool call). Concepts like 'L1/L2/L3 caching' and 'CRDT' are mentioned but never concretely implemented or instructed. The skill describes rather than instructs.	1 / 3
Workflow Clarity	There is no clear sequential workflow. Operations are listed as isolated code blocks without ordering, dependencies, or validation checkpoints. Recovery procedures are bullet points with no concrete steps. There's no feedback loop for sync failures or conflict resolution despite these being critical operations.	1 / 3
Progressive Disclosure	The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content is inline regardless of complexity, and sections like 'Memory Operations' and 'Performance Metrics' could be separated. The structure is flat with no clear navigation hierarchy.	1 / 3
	Total	4 / 12 Passed

Description

0%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is essentially a placeholder that provides no functional information about the skill's capabilities or when it should be used. It only names the skill and provides an invocation command, which is insufficient for Claude to make informed skill selection decisions. This is among the weakest possible descriptions.

Suggestions

Add concrete actions describing what swarm-memory-manager does (e.g., 'Manages shared memory across multiple agents, stores and retrieves coordination state, tracks task assignments').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when coordinating between agents, sharing state across swarm tasks, or managing multi-agent memory').

Remove the invocation instruction from the description (it belongs elsewhere) and replace with functional capability details that distinguish this from other agent or memory skills.

Dimension	Reasoning	Score
Specificity	The description contains no concrete actions whatsoever. It only states it is an 'agent skill for swarm-memory-manager' without describing what it actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command, not functional information or usage triggers.	1 / 3
Trigger Term Quality	The only keyword is 'swarm-memory-manager', which is a technical/internal name, not a natural term a user would say. There are no natural language trigger terms like 'memory', 'shared state', 'coordination', etc.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. Without knowing what the skill does, it cannot be reliably differentiated from other agent or memory-related skills.	1 / 3
	Total	4 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-swarm-memory-manager/SKILL.md
Commit: 913f9ea

Reviewed: 3 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.