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. It provides only a name and invocation syntax with zero information about capabilities, use cases, or trigger conditions. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what this skill does, e.g., 'Designs and implements v3 API integration architectures, maps data flows between systems, generates integration configuration files.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs help with v3 API integrations, system interconnections, data mapping, or migration to v3 architecture.'
Remove the invocation instruction ('invoke with $agent-v3-integration-architect') from the description and replace it with functional content that helps Claude understand when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only states it is an 'agent skill' with a name and invocation command, providing no information about what it actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command 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/an internal identifier, not something a user would naturally mention when seeking help. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. 'Integration architect' could overlap with countless other skills, and without any specifics, there's no way to differentiate it. | 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 is a project planning document masquerading as an actionable skill. It is extremely verbose, repeating performance targets and overlap statistics multiple times, while providing zero executable code—every TypeScript snippet is pseudocode with fictional method calls. The content would benefit enormously from being condensed to a concise overview with concrete, runnable commands and split across multiple reference files.
Suggestions
Replace all pseudocode TypeScript with either real executable code/commands or remove it entirely and provide concise prose instructions—the current code creates an illusion of actionability without substance.
Consolidate repeated information (performance targets appear 2-3 times each) into a single reference section or separate file, reducing the body to under 100 lines.
Add explicit validation checkpoints to the migration workflow (e.g., 'Run `npm test` after each phase; verify feature parity with `npx agentic-flow@alpha validate`') to make the phased plan actually followable.
Split detailed content (feature integration details, performance benchmarks, coordination points) into separate referenced files and keep SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 300+ lines with massive amounts of illustrative TypeScript that is not executable (placeholder methods, no real implementations). Repeats the same performance targets (e.g., '2.49x-7.47x speedup', '150x-12,500x') multiple times across sections. Explains high-level concepts Claude already understands (what RL algorithms are, what backward compatibility means). The duplication analysis table is repeated in both the hooks and the body. | 1 / 3 |
Actionability | Despite the volume of TypeScript code, none of it is executable—every class and method is pseudocode with placeholder implementations (e.g., `this.adaptToNewAPI()`, `this.agenticFlow.sona.setMode(mode)`) that don't correspond to real APIs. There are no concrete commands to run, no real file paths to edit, and no actual steps Claude could execute. The code gives the appearance of specificity while being entirely abstract. | 1 / 3 |
Workflow Clarity | There is a phased migration plan (Weeks 7-10) with a logical sequence and a backward compatibility strategy with dual operation → gradual switchover → complete transition. However, there are no explicit validation checkpoints between phases, no error recovery steps, and no concrete verification commands. The checklist at the end is useful but disconnected from the workflow steps. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files and no bundle files to support it. All content—integration strategy, feature details, migration plan, performance targets, coordination points, risk mitigation—is crammed into a single file with no clear navigation or layering. Content that should be in separate reference files (e.g., detailed API integration, benchmarks, migration guides) is all 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
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.