Use this skill to understand the RingCentral App Connect project structure, including the monorepo layout, core package APIs, handlers, models, and how components interact.
64
43%
Does it follow best practices?
Impact
100%
1.16xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agent-skills/project-architecture/SKILL.mdQuality
Discovery
50%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 identifies a specific project domain (RingCentral App Connect) and lists structural areas of concern, which provides some useful context. However, it lacks concrete actions (what Claude will actually do), explicit trigger conditions for when to select this skill, and natural user-facing keywords. The use of second-person 'Use this skill' is borderline but functions more as an instruction to Claude than addressing the user directly.
Suggestions
Add explicit trigger guidance, e.g., 'Use when the user asks about RingCentral App Connect architecture, file locations, package dependencies, or how handlers/models are organized.'
Replace vague 'understand the project structure' with concrete actions like 'Explains the monorepo layout, traces API call flows through handlers and models, identifies package dependencies, and locates specific components within the codebase.'
Include natural trigger terms users would say, such as 'architecture', 'where is', 'how does X connect to Y', 'codebase overview', 'package structure', or specific package/directory names.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (RingCentral App Connect project) and some areas (monorepo layout, core package APIs, handlers, models, component interactions), but these are more structural categories than concrete actions. It doesn't list specific actions like 'navigate files', 'explain dependencies', or 'trace data flow'. | 2 / 3 |
Completeness | The 'what' is partially addressed (understand project structure, monorepo layout, APIs, handlers, models, interactions). The 'when' is implied by the opening 'Use this skill to understand...' but lacks explicit trigger guidance like 'Use when the user asks about project architecture, file locations, or how packages relate to each other.' | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'monorepo', 'APIs', 'handlers', 'models', and 'project structure', which users might naturally mention. However, it's missing common variations like 'architecture', 'codebase', 'where is', 'how does X work', or specific package names that users would likely say. | 2 / 3 |
Distinctiveness Conflict Risk | It's scoped to a specific project (RingCentral App Connect), which helps distinctiveness. However, 'project structure' and 'how components interact' are broad enough to potentially overlap with other code navigation or documentation skills. The mention of specific elements like handlers and models helps somewhat. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill serves as a reasonable architectural reference with good use of tables and code snippets for the RingCentral App Connect project. However, it reads more like a passive reference document than an actionable skill—it describes what exists but doesn't guide Claude on how to perform common tasks within the codebase. The lack of workflows, validation steps, and progressive disclosure to deeper reference materials limits its effectiveness.
Suggestions
Add common workflow sequences with validation steps, e.g., 'How to add a new connector: 1. Copy template, 2. Implement required interface methods, 3. Register in index.js, 4. Verify with npm test'
Convert the architecture reference into a concise overview that links to separate detailed files (e.g., CONNECTORS.md, MODELS.md, API_ROUTES.md) for progressive disclosure
Remove self-evident descriptions from tables (e.g., 'Auth - auth.js - OAuth flow' where the handler name already implies the purpose) to improve conciseness
Add actionable guidance for common development tasks like debugging, adding routes, or modifying models rather than just listing what exists
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-organized with tables and code blocks, but includes some information Claude could infer (like what each handler does when the names are self-explanatory) and could be tightened. The environment variables section and some table descriptions are somewhat verbose for an architecture overview. | 2 / 3 |
Actionability | Provides concrete code examples for entry point usage and connector registry, plus CLI commands for development workflow. However, the skill is primarily descriptive/reference material rather than instructing Claude on specific tasks—it describes the architecture but doesn't provide guidance on how to work with it (e.g., how to create a new connector, how to add a route, how to debug issues). | 2 / 3 |
Workflow Clarity | There are no multi-step workflows with validation checkpoints. The development workflow section is just a list of commands without sequencing or context about when to use each. For an architecture skill, there's no guidance on common development flows like adding a connector, modifying a handler, or debugging—just a flat reference. | 1 / 3 |
Progressive Disclosure | The content is structured with clear sections and tables, which aids navigation. However, it's a monolithic document with no references to supporting files for deeper dives (e.g., detailed connector creation guide, model schema details, API reference). For a project of this complexity, the architecture overview would benefit from linking to more detailed documents. | 2 / 3 |
Total | 7 / 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.
f59d4a2
Table of Contents
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.