agent-v3-integration-architect
Agent skill for v3-integration-architect - invoke with $agent-v3-integration-architect
38
6%
Does it follow best practices?
Impact
93%
4.42xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-v3-integration-architect/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 non-functional as a skill selector. It provides zero information about what the skill does, when it should be used, or what domain it operates in. The only content is an invocation command, which is useless for Claude's skill selection process.
Suggestions
Add a clear 'what' clause describing the specific actions this skill performs (e.g., 'Designs and implements v3 API integrations, maps data schemas between systems, and generates integration architecture diagrams').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks about API integration, system architecture, v3 migration, or connecting services').
Remove the invocation syntax from the description and replace it with domain-specific keywords and concrete capabilities that distinguish this skill from other architecture or integration skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only states it's an 'agent skill' and provides an invocation command, with 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 provides an invocation syntax with no functional or contextual information. | 1 / 3 |
Trigger Term Quality | There are no natural keywords a user would say. 'v3-integration-architect' is technical jargon that doesn't correspond to any user-facing language or task description. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. 'Integration architect' could overlap with countless integration, architecture, or API-related skills without any way to differentiate. | 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 proposal rather than an actionable skill for Claude. It is extremely verbose, repeating key metrics multiple times, and all code examples are non-executable pseudocode referencing fictional APIs. The content lacks concrete, copy-paste-ready instructions and would benefit enormously from being condensed to essential integration steps with real commands.
Suggestions
Replace fictional TypeScript pseudocode with actual executable commands or real code snippets that Claude can run (e.g., real CLI commands, real file operations, real npm scripts).
Eliminate repeated information—state duplication statistics, performance targets, and feature lists exactly once each, reducing the document to under 100 lines.
Add explicit validation checkpoints with feedback loops within each migration phase (e.g., 'Run X to verify, if it fails do Y, then retry').
Split detailed integration specs (SONA modes, RL algorithms, MCP tools, performance benchmarks) into separate reference files and link to them from a concise overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 300+ lines. Massive amounts of illustrative TypeScript that is not executable (pseudo-API calls to non-existent methods). Repeats the same duplication statistics multiple times (in hooks, in the ASCII table, and in success metrics). Performance targets are stated three separate times. Much of this is aspirational project planning, not actionable skill instruction. | 1 / 3 |
Actionability | None of the TypeScript code is executable—it references fictional APIs (agentic-flow@alpha's Swarm, SONA, AgentDB, Flash Attention) with made-up method signatures. There are no real commands to run, no actual file paths to edit, and no concrete steps Claude could follow. The code is pseudocode dressed up as TypeScript. | 1 / 3 |
Workflow Clarity | There is a phased migration plan (Weeks 7-10) with a logical sequence and a backward compatibility strategy with three phases. However, validation checkpoints are only checklists at the end rather than inline verification steps, and there are no feedback loops for error recovery during the migration phases. | 2 / 3 |
Progressive Disclosure | Monolithic wall of content with no references to external files and no bundle files. Everything is inlined in a single massive document with no navigation aids. Content that could be split (performance benchmarks, RL algorithms, MCP tools details) is all dumped inline. | 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
ca77f83
- 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.