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 known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-swarm-memory-manager/SKILL.md

Quality

Discovery

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 is an extremely weak description that provides essentially no useful information for skill selection. It only names the skill and provides an invocation command, but fails to describe any capabilities, actions, or usage triggers. It would be nearly impossible for Claude to correctly select this skill from a pool of available skills.

Suggestions

Add concrete actions describing what the skill does, e.g., 'Manages shared memory and state across multiple agents in a swarm, including reading, writing, and synchronizing shared data.'

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

Replace the invocation instruction with functional description — invocation syntax belongs in the skill body, not the description field used for skill selection.

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's impossible to distinguish it from other agent skills. Without knowing what it does, there's no way to determine when it should or shouldn't be selected.	1 / 3
	Total	4 / 12 Passed

Implementation

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

This skill is largely aspirational rather than actionable - it describes a distributed memory management system using impressive-sounding concepts (CRDTs, vector clocks, sharding) but provides no executable code or clear workflows. The JavaScript examples are syntactically invalid, mixing MCP tool invocation syntax with async/await patterns that cannot run. The content reads more like a design document or architecture overview than an operational skill that Claude can follow.

Suggestions

Replace pseudo-JavaScript with actual executable MCP tool calls showing the exact syntax Claude should use (e.g., proper tool_use format), removing the async/await wrapper functions that cannot execute.

Define a clear sequential workflow: e.g., 1) Initialize memory namespace → 2) Index existing keys → 3) Monitor for updates → 4) Sync and validate → 5) Report metrics, with explicit validation at each step.

Remove conceptual descriptions Claude already knows (CRDT, LRU, vector clocks, write-ahead logging) and replace with specific implementation details unique to this system's MCP tools and namespace conventions.

Replace hardcoded fake metric values with actual computed values or clearly mark them as templates with placeholders that should be dynamically populated.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with many concepts Claude already understands (caching levels, CRDT, vector clocks, LRU eviction). The code examples are pseudocode dressed as JavaScript that isn't actually executable. Much of the content describes distributed systems concepts rather than providing actionable instructions.	1 / 3
Actionability	The code examples are not executable - they mix MCP tool call syntax with JavaScript async/await in ways that cannot actually run. Functions like `resolveConflict` are referenced but never defined. The 'Cache Optimization' and 'Conflict Resolution' sections are bullet-point descriptions with no concrete implementation. The metrics example hardcodes fake values (operations_per_second: 1000).	1 / 3
Workflow Clarity	There is no clear sequential workflow. The skill describes many operations (read, write, sync, conflict resolution, recovery) but never sequences them into a coherent process. No validation checkpoints exist - the 'Recovery Procedures' section is just four bullet points with no actual steps. Missing feedback loops for sync failures and conflict resolution.	1 / 3
Progressive Disclosure	The content is organized into logical sections with headers, which provides some structure. However, it's a monolithic wall of content (~180 lines) that could benefit from splitting detailed operations into separate files. The 'Integration Points' section references other agents but doesn't link to any external documentation.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: f547cec

Reviewed: 4 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.