agent-v3-memory-specialist
Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist
37
6%
Does it follow best practices?
Impact
85%
1.77xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-v3-memory-specialist/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 placeholder that provides no useful information about the skill's capabilities, use cases, or trigger conditions. It only contains an invocation command, which is useless for skill selection. It fails on every dimension of the rubric.
Suggestions
Add concrete actions describing what the skill does (e.g., 'Stores, retrieves, and manages persistent memory entries across conversations' or whatever the actual functionality is).
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to remember something, recall previous context, or manage stored notes').
Replace the internal agent invocation syntax with a user-facing description that clearly distinguishes this skill from other potentially similar skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for v3-memory-specialist' is entirely abstract and gives no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states how to invoke the agent, not what it does or when it should be selected. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'v3-memory-specialist' is internal jargon, and 'invoke with $agent-v3-memory-specialist' is a technical invocation command, not a user-facing trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. 'Memory specialist' is slightly suggestive of a domain but without any elaboration, it could conflict with any memory-related or general-purpose skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a project planning document or architectural design spec rather than an actionable skill for Claude. It is extremely verbose, repeating performance targets throughout, and contains no executable code or concrete commands—only illustrative class designs for systems that don't exist. The content would need to be fundamentally restructured to serve as a useful skill instruction.
Suggestions
Replace illustrative class designs with actual executable commands or code that Claude can run to perform memory migration tasks (e.g., real CLI commands, working scripts with actual library imports).
Reduce content by 70%+ by removing repeated performance claims, ASCII diagrams, project timeline details, and coordination points that don't help Claude execute tasks.
Add concrete validation steps with feedback loops (e.g., 'Run X command, check output for Y, if Z then fix and retry') instead of aspirational benchmark class sketches.
Split detailed migration plans, SONA integration, and benchmarking into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Contains extensive ASCII diagrams, repeated performance claims (150x-12,500x mentioned 6+ times), project management details (week-by-week plans, coordination points), and conceptual explanations that don't provide actionable guidance. Much of this is planning documentation rather than a skill instruction. | 1 / 3 |
Actionability | Despite containing TypeScript and SQL code blocks, none are executable—they are illustrative pseudocode/design sketches for classes that don't exist yet. There are no concrete commands Claude can run, no real library imports, no actual tool invocations. The bash 'phases' are just bullet-point plans, not commands. | 1 / 3 |
Workflow Clarity | There is a phased migration strategy (Phase 1-3) with some sequencing, and a validation section with success criteria checklist. However, the phases contain no concrete validation checkpoints or feedback loops—just high-level descriptions of what should happen in each week. The validation benchmarks are aspirational code, not actual verification steps. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content—architecture, migration plans, benchmarks, SONA integration, coordination points—is inlined in a single massive document. No navigation structure or links to separate detailed guides. | 1 / 3 |
Total | 5 / 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
322b2ae
- 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.