agent-swarm-memory-manager
Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager
34
0%
Does it follow best practices?
Impact
90%
2.25xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-swarm-memory-manager/SKILL.mdQuality
Discovery
0%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 fails on all dimensions. It provides only the skill's internal name and invocation command without any explanation of capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a list of available skills.
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 multiple agents, sharing state across swarm tasks, or managing distributed memory').
Replace the invocation instruction with functional description — invocation syntax belongs in the skill body, not the description field.
| 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's impossible to differentiate it from any other agent skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a design document or aspirational architecture description than an actionable skill for Claude. The code examples use invalid hybrid syntax that is neither executable JavaScript nor proper MCP tool invocations, making them unusable. The content is bloated with distributed systems concepts Claude already knows while lacking the concrete, step-by-step guidance needed to actually perform memory management tasks.
Suggestions
Replace all pseudo-JavaScript/MCP hybrid code with actual valid MCP tool call examples showing the exact syntax Claude should use (e.g., proper tool_use format for mcp__claude-flow__memory_usage)
Remove conceptual explanations of well-known distributed systems patterns (CRDT, vector clocks, LRU, sharding) and replace with specific, concrete instructions for what this agent should do step-by-step when invoked
Add a clear sequential workflow: what happens on initialization, what the main loop looks like, how to handle specific scenarios (conflict detected, sync failure, etc.) with explicit validation checkpoints
Cut content by at least 60% - remove the 'Integration Points', 'Memory Patterns', and 'Quality Standards' sections which are vague lists, and focus on the 2-3 core operations the agent actually needs to perform
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive conceptual explanations Claude already knows (CRDT, vector clocks, LRU eviction, write-ahead logging, sharding, replication). The code examples are pseudocode that mixes JavaScript syntax with MCP tool call syntax in a non-executable way, adding bulk without clarity. Many sections describe distributed systems concepts rather than providing actionable instructions. | 1 / 3 |
Actionability | The code examples are not executable - they mix JavaScript async/await syntax with what appears to be MCP tool call objects in an invalid hybrid syntax (e.g., `await mcp__claude-flow__memory_usage { action: ... }` is neither valid JS nor a proper tool invocation). Concepts like 'multi-level caching L1/L2/L3' and 'CRDT for conflict-free replication' are listed without any concrete implementation guidance. | 1 / 3 |
Workflow Clarity | There is no clear sequenced workflow. The skill lists responsibilities and code snippets but never defines a step-by-step process for what the agent should actually do when invoked. There are no validation checkpoints, no error recovery feedback loops, and no clear ordering of operations despite this being a complex multi-step coordination task. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no clear hierarchy. All content is inline regardless of importance, mixing initialization, optimization, metrics, integration points, and recovery procedures at the same level with no navigation structure. | 1 / 3 |
Total | 4 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
0d9f9b1
- 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.