agent-memory-coordinator
Agent skill for memory-coordinator - invoke with $agent-memory-coordinator
35
0%
Does it follow best practices?
Impact
95%
1.53xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-memory-coordinator/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 description is essentially a label with invocation syntax rather than a functional description. It provides zero information about what the skill does, when to use it, or what triggers should activate it. It fails on every dimension of the rubric.
Suggestions
Describe the concrete actions this skill performs (e.g., 'Stores, retrieves, and organizes conversation context and user preferences across sessions').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to remember something, recall previous context, or manage stored notes and preferences').
Remove the invocation syntax ('invoke with $agent-memory-coordinator') from the description and replace it with capability and trigger information that helps Claude select this skill appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for memory-coordinator' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of functionality. | 1 / 3 |
Trigger Term Quality | The only keyword is 'memory-coordinator', which is technical jargon unlikely to be used naturally by users. There are no natural trigger terms a user would say. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from other memory-related or coordination-related skills. 'Memory-coordinator' could overlap with many things. | 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 is a high-level conceptual document that describes what a memory coordination system could do, rather than instructing Claude on how to actually perform memory operations. It lacks any executable code, concrete commands, specific tool references, or actionable workflows. The content reads like a product specification or architecture overview rather than a skill that enables Claude to take action.
Suggestions
Replace abstract descriptions with concrete, executable examples showing actual tool calls or commands for storing, retrieving, and searching memory (e.g., specific MCP tool invocations or API calls).
Define a clear step-by-step workflow for common memory operations with validation checkpoints, such as: check namespace exists → store data → verify storage → confirm retrieval.
Remove generic software engineering content (caching strategies, scalability, compliance sections) that Claude already knows and that doesn't provide actionable guidance specific to this memory system.
Split advanced topics (security, performance, collaborative memory) into separate referenced files and keep the main skill focused on core operations with a quick-start section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive sections on concepts Claude already understands (caching strategies, security compliance, scalability patterns). Most content is abstract categorization and listing rather than actionable instruction. The skill is padded with generic software engineering concepts that don't teach Claude anything new. | 1 / 3 |
Actionability | No executable code, no concrete commands, no specific tool invocations. The 'Usage Examples' are natural language prompts, not actionable instructions. Memory patterns show abstract YAML-like structures but nothing Claude can actually execute. There are no real APIs, commands, or concrete steps to perform memory operations. | 1 / 3 |
Workflow Clarity | No clear multi-step workflows are defined. Operations like Store, Retrieve, Search, Delete, and Sync are listed as bullet points without any sequencing, validation, or error handling. The 'Best Practices' section lists tips but doesn't define a workflow. No validation checkpoints exist for any operation. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content—from basic operations to advanced features, security, and performance optimization—is dumped into a single document. No navigation structure or links to detailed documentation for advanced topics. | 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
f547cec
- 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.