agent-v3-integration-architect

Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect

4.42x

Quality

13%

Does it follow best practices?

Impact

93%

4.42x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-v3-integration-architect/SKILL.md

Quality

Content

20%

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

The body reads as a project architecture/planning document rather than an executable skill: non-runnable pseudocode, heavily redundant benchmark figures, and no external reference files. It has a phased structure but lacks validation checkpoints and progressive disclosure.

Suggestions

Replace pseudocode class sketches with concrete, runnable commands or remove them in favor of concise migration steps Claude can actually execute.

Add explicit validation checkpoints between migration phases (e.g. run feature-parity tests before the Phase 3 file removal) to satisfy the destructive-operation feedback-loop requirement.

Trim repeated benchmark figures and time-stamped version metadata, and move detailed benchmark/API material into reference files linked one level deep from a lean overview.

Dimension	Reasoning	Score
Conciseness	The ~350-line body is padded with redundant benchmark claims (2.49x-7.47x and 150x-12,500x each repeated), ASCII tables, and time-stamped planning detail (version 3.0.0-alpha, updated 2026-01-04), fitting the verbose/padded anchor rather than the tighter score-2 example.	1 / 3
Actionability	The TypeScript blocks reference fictional APIs (this.executeWithSONA, this.agenticFlow.sona.setMode, 'agentic-flow@alpha') and contain method stubs, so they describe an aspirational architecture rather than providing executable, copy-paste guidance.	1 / 3
Workflow Clarity	Phased migration steps are sequenced (Phase 1 Week 7, Phase 2 Week 8-9, Phase 3 Week 10) but the destructive file-removal step has no validation/verification checkpoint, capping it at 2 per the destructive-operations guideline.	2 / 3
Progressive Disclosure	The body is section-organized with headers, but it is a monolithic single file with no bundle references (references/scripts/assets absent) and benchmark/code detail that should be split is kept inline, so it does not reach the clear one-level-deep reference structure of score 3.	2 / 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 frontmatter description is essentially a restatement of the skill name plus invocation syntax, with no concrete capabilities or usage triggers. It fails to answer either what the skill does or when Claude should invoke it.

Suggestions

Replace the placeholder with a concrete capability statement, e.g. "Eliminates duplicate orchestration code by adapting claude-flow onto agentic-flow@alpha via adapter layers and phased migration."

Add an explicit trigger clause such as "Use when integrating claude-flow with agentic-flow@alpha, deduplicating swarm/agent/task/session orchestration, or planning ADR-001 migrations."

Use third-person action verbs ("Migrates", "Adapts") and natural user terms instead of "$agent-v3-integration-architect" invocation syntax.

Dimension	Reasoning	Score
Specificity	The description only states it is an "Agent skill for v3-integration-architect" with no concrete actions named, matching the vague/abstract anchor rather than the score-2 example that names a domain and some actions.	1 / 3
Completeness	It neither says what the skill does (no actions) nor when to use it (no "Use when..." trigger), so both what and when are weak/missing per the score-1 anchor.	1 / 3
Trigger Term Quality	"invoke with $agent-v3-integration-architect" is invocation syntax/jargon, not natural keywords a user would say; it lacks the common-variation coverage expected at score 2.	1 / 3
Distinctiveness Conflict Risk	It is tied to a specific named skill so not fully generic, but provides no functional niche or triggers to distinguish it from other architect skills, capping it below 3.	2 / 3
	Total	5 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Path: .agents/skills/agent-v3-integration-architect/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.