agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer
33
0%
Does it follow best practices?
Impact
92%
1.58xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-topology-optimizer/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 minimal description that provides virtually no useful information for skill selection. It only names the skill and provides an invocation command, but fails to describe any capabilities, actions, domain context, or usage triggers. It is essentially a label rather than a description.
Suggestions
Add concrete actions describing what the topology optimizer does (e.g., 'Performs structural topology optimization to minimize material usage while meeting stress and displacement constraints').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks about topology optimization, structural design, material distribution, FEA-based optimization, or minimizing weight in engineering components').
Remove the invocation instruction ('invoke with $agent-topology-optimizer') from the description and replace it with functional content that helps Claude decide when this skill is appropriate.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only says 'Agent skill for topology-optimizer' without describing what the skill actually does—no verbs, no capabilities, no domain details. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It provides neither functional information nor usage triggers—only an invocation command. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'topology-optimizer', which is a technical/internal name rather than a natural keyword a user would say. There are no natural language trigger terms like 'optimize topology', 'structural optimization', 'FEA', etc. | 1 / 3 |
Distinctiveness Conflict Risk | While 'topology-optimizer' is a specific name, the description is so vague that Claude cannot determine when to select it versus any other skill. The lack of any functional description makes it impossible to distinguish from other optimization or engineering skills. | 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 an aspirational design document rather than an actionable skill. It presents hundreds of lines of non-executable pseudocode with undefined dependencies, no clear workflow for Claude to follow, and no validation or error-handling guidance. The content explains general optimization concepts Claude already knows while failing to provide the project-specific, concrete instructions needed to actually perform topology optimization.
Suggestions
Replace pseudocode class stubs with a concrete, executable workflow: e.g., '1. Run `npx claude-flow topology-analyze --swarm-id <id>`, 2. Review output metrics, 3. If latency > threshold, run `npx claude-flow topology-optimize ...`, 4. Validate with `topology-monitor`'.
Remove explanations of well-known algorithms (genetic algorithms, simulated annealing) and instead document the specific API surface, configuration options, and expected inputs/outputs for this project's topology tools.
Add explicit validation checkpoints and error-handling steps, especially for topology migration operations that could disrupt a running swarm.
Extract detailed algorithm implementations and metrics definitions into separate reference files, keeping SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. The code is largely pseudocode-style class definitions with placeholder methods (e.g., `this.calculateAverageLatency()`) that explain nothing Claude doesn't already know. Concepts like genetic algorithms, simulated annealing, and graph partitioning are explained at a tutorial level with no novel, project-specific information. | 1 / 3 |
Actionability | None of the code is executable — classes reference undefined constructors (HierarchicalTopology, MeshTopology, etc.), methods call unimplemented helpers, and MCP calls reference APIs with no documentation of their actual signatures or availability. The CLI commands at the end are the most concrete elements but lack context on prerequisites or expected outputs. | 1 / 3 |
Workflow Clarity | There is no clear multi-step workflow with sequencing or validation checkpoints. The content describes what the system conceptually does but never provides a step-by-step process for actually performing topology optimization. No error handling, validation steps, or feedback loops are defined. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content — from basic topology types to genetic algorithms to neural network integration — is dumped inline with no organizational hierarchy or navigation aids. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (813 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/claude-flow
- Commit
9d4a9ea
- 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.