agent-swarm-memory-manager
Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-swarm-memory-manager35
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It functions only as a label and invocation command, providing zero information about what the skill does, what capabilities it offers, or when Claude should select it. Without any concrete actions or trigger guidance, this skill would be essentially unusable in a multi-skill environment.
Suggestions
Add concrete actions describing what swarm-memory-manager does (e.g., 'Manages shared memory across multiple agents, stores context, retrieves conversation history')
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when coordinating memory between agents, sharing context across swarms, or managing multi-agent state')
Remove the invocation syntax from the description and replace with capability-focused content that helps Claude understand the skill's purpose
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm-memory-manager' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | Missing both 'what' and 'when'. The description only states it's an agent skill and how to invoke it, but provides no information about capabilities or usage triggers. | 1 / 3 |
Trigger Term Quality | The only terms present are technical jargon ('swarm-memory-manager', '$agent-swarm-memory-manager'). No natural keywords a user would say when needing this functionality. | 1 / 3 |
Distinctiveness Conflict Risk | While the name 'swarm-memory-manager' is unique, the description is so vague that Claude cannot determine when to select this skill. It could conflict with any memory or agent-related skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a conceptual framework for distributed memory management but lacks executable, actionable guidance. The pseudo-code examples mix syntax styles and aren't directly usable, and critical workflows like conflict resolution and recovery lack explicit step-by-step procedures with validation checkpoints. The content would benefit from clearer tool invocation syntax and explicit error handling flows.
Suggestions
Convert pseudo-JavaScript MCP calls to actual tool invocation format that Claude can execute directly
Add explicit step-by-step workflows with validation checkpoints for critical operations like conflict resolution and recovery procedures
Include error handling flows showing what to do when sync fails, conflicts can't be resolved, or memory operations timeout
Remove role-play framing ('distributed consciousness keeper') and focus on concrete operational instructions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity like the role-play framing ('distributed consciousness keeper of the hive mind') and explanatory comments that Claude doesn't need. However, the code examples are reasonably focused on the actual operations. | 2 / 3 |
Actionability | Code examples use a pseudo-JavaScript syntax mixing MCP tool calls with async/await patterns that isn't actually executable. The mcp__claude-flow__memory_usage calls are shown as object literals rather than proper tool invocations, making them not copy-paste ready. | 2 / 3 |
Workflow Clarity | Multi-step processes like conflict resolution and synchronization lack clear sequencing and validation checkpoints. The 'atomicWrite' function mentions conflict detection but doesn't show what to do when resolution fails. No feedback loops for error recovery are defined. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but it's a monolithic document with no references to external files for detailed topics like CRDT implementation, recovery procedures, or the mentioned integration patterns. Some sections could be split out. | 2 / 3 |
Total | 7 / 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.
- 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.