agent-topology-optimizer

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

1.58x

Quality

13%

Does it follow best practices?

Impact

92%

1.58x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-topology-optimizer/SKILL.md

Quality

Content

27%

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

The body is an extremely verbose monolith of illustrative-but-non-executable JavaScript wrapped in narrating comments, with only the command section offering real actionability. It lacks validation checkpoints and any progressive-disclosure structure, scoring near the floor on conciseness and organization.

Suggestions

Cut the class scaffolding and narrating comments; keep only the executable `npx claude-flow` commands and concise guidance Claude cannot derive itself.

Add explicit validation/verification checkpoints for topology migration (e.g. "validate before applying", "revert if performance regresses").

Move detailed algorithms and metrics into separate reference files (e.g. ALGORITHMS.md, METRICS.md) and link to them from a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is ~800 lines of dense class scaffolding with narrating comments ("Intelligent topology selection and optimization", "Comprehensive latency optimization") that explain concepts Claude already knows, far exceeding a reasonable token budget.	1 / 3
Actionability	The Operational Commands section gives concrete executable `npx claude-flow` commands, but the bulk of the JavaScript references undefined classes (HierarchicalTopology, NetworkOptimizer, mcp.* calls) that make the code non-runnable rather than copy-paste ready.	2 / 3
Workflow Clarity	Sequences exist in places (analyze → generate candidates → evaluate → select → migrate), but topology migration is a risky operation with no explicit validate/verify checkpoint or feedback loop, capping this at 2 per the destructive-operation rule.	2 / 3
Progressive Disclosure	Everything is packed into a single monolithic SKILL.md with no references, no separate files (references/scripts/assets are absent), and no navigation; the candidate variations, algorithms, and metrics should be split out.	1 / 3
	Total	6 / 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 near-tautology that restates the skill name plus an invocation token, with no concrete capabilities, natural trigger terms, or explicit usage guidance. It scores at the floor on every dimension.

Suggestions

Rewrite in third person to state concrete actions, e.g. "Reconfigures swarm communication topologies, optimizes network latency, and places agents to minimize communication distance."

Add an explicit trigger clause: "Use when the user asks to optimize swarm topology, reduce agent communication latency, or plan agent placement."

Replace the "invoke with $..." token with natural keywords users would actually say (topology, latency, swarm, agent placement, routing).

Dimension	Reasoning	Score
Specificity	The description only states "Agent skill for topology-optimizer" with an invocation token; it names no concrete actions, only restating the skill name as a near-tautology.	1 / 3
Completeness	It answers neither "what does this do" (only restates the name) nor "when should Claude use it" (no "Use when..." clause); even the cap-at-2 rule does not apply because the trigger guidance is entirely absent.	1 / 3
Trigger Term Quality	"invoke with $agent-topology-optimizer" is invocation jargon, not a natural phrase a user would say; there are no everyday keywords like "optimize", "topology", "latency", or "swarm". It is also first/second-person-flavored ("invoke"), reducing specificity.	1 / 3
Distinctiveness Conflict Risk	The generic "Agent skill for X" template could describe many agents and provides no distinct trigger, so it would conflict with other similarly-described skills.	1 / 3
	Total	4 / 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
Path: .agents/skills/agent-topology-optimizer/SKILL.md
Commit: 26c35b5

Reviewed: about 5 hours 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.