agent-topology-optimizer

Agent skill for topology-optimizer - invoke with $agent-topology-optimizer

1.58x

Quality

—

Does it follow best practices?

Impact

92%

1.58x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a verbose, monolithic catalog of placeholder class architectures and imagined MCP integrations rather than lean, executable guidance. It has some structure and concrete command syntax but lacks real executability, validation checkpoints, and any progressive disclosure into bundle files.

Suggestions

Cut the placeholder class skeletons to a lean overview plus a few genuinely executable snippets or commands, removing architectural boilerplate Claude can infer.

Add a concrete, numbered workflow with explicit validation/verification steps (e.g. analyze -> validate metrics -> migrate -> verify no downtime -> rollback on failure) for the destructive topology-migration operation.

Move detailed algorithm implementations and reference tables into separate files under references/ and link to them from a concise SKILL.md overview, replacing the monolithic wall of code.

Dimension	Reasoning	Score
Conciseness	The body is an ~800-line wall of placeholder class skeletons (e.g. TopologyOptimizer, NetworkLatencyOptimizer, AgentPlacementOptimizer) that spell out elaborate architectures Claude already understands, matching the 'verbose; padded with unnecessary context' anchor rather than the mostly-efficient anchor 2.	1 / 3
Actionability	There is concrete-looking structure and CLI commands ('npx claude-flow topology-optimize'), but the code references undefined classes and APIs (HierarchicalTopology, mcp.topology_optimize, GeneticPlacementAlgorithm) and is not executable, fitting 'some concrete guidance but incomplete; pseudocode instead of executable code' rather than the fully-executable anchor 3.	2 / 3
Workflow Clarity	A discernible sequence exists (analyze topology, generate/evaluate candidates, select, plan migration, monitor) and the operational commands are loosely ordered, but there are no validation checkpoints or feedback loops for the risky topology-migration operation, fitting 'sequence present but checkpoints missing' rather than anchor 1's missing sequence or anchor 3's explicit validation.	2 / 3
Progressive Disclosure	Section headings provide structure, but the content is a single monolithic ~800-line file with large code references inlined that would be better split into separate files, and no bundle files exist; this matches 'some structure but content that should be separate is inline' rather than anchor 3's well-signaled one-level references.	2 / 3
	Total	7 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a boilerplate placeholder that names the domain and an invocation token but states no concrete capabilities and provides no 'when to use' guidance. It is too generic to reliably trigger or distinguish this skill.

Suggestions

Replace the boilerplate with concrete actions, e.g. 'Reconfigures swarm topology, optimizes communication patterns, and plans low-downtime topology migrations.'

Add an explicit trigger clause such as 'Use when optimizing swarm/multi-agent network topology, reducing inter-agent latency, or planning topology migrations.'

Use natural user-facing terms (e.g. 'swarm topology', 'agent communication', 'network latency') instead of the technical '$agent-topology-optimizer' invocation token.

Dimension	Reasoning	Score
Specificity	The description only names a domain ('topology-optimizer') and an invocation token; it lists no concrete actions, matching the 'vague or no actions; abstract language' anchor rather than anchor 2 which requires naming some actions.	1 / 3
Completeness	The 'what' is very weak (a domain label with no described actions) and the 'when' is entirely absent with no 'Use when...' clause, matching the 'missing what OR when, or both very weak' anchor instead of anchor 2 which assumes a solid 'what'.	1 / 3
Trigger Term Quality	The only triggers are the technical token '$agent-topology-optimizer' and the jargon 'topology-optimizer', which a user would not naturally say, fitting the 'no natural keywords; technical jargon' anchor and falling below anchor 2's 'some relevant keywords'.	1 / 3
Distinctiveness Conflict Risk	The 'topology-optimizer' niche is fairly specific, but the boilerplate 'Agent skill for X - invoke with $X' form is shared across many agent skills and could overlap with other optimization agents, fitting 'somewhat specific but could still overlap' rather than the clearly-distinct anchor 3.	2 / 3
	Total	5 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 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	15 / 16 Passed

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.