CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

project-architecture

Use this skill to understand the RingCentral App Connect project structure, including the monorepo layout, core package APIs, handlers, models, and how components interact.

85

1.16x
Quality

82%

Does it follow best practices?

Impact

100%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

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

A well-organized, token-efficient architecture reference with concrete code and commands throughout. Its main structural weakness is that detailed reference material (API routes, env vars, model/handler tables) lives entirely inline with no progressive disclosure into separate files.

Suggestions

Move the API Routes catalog and Environment Variables documentation into references/ files (e.g. references/api-routes.md, references/env-vars.md) and keep a one-line pointer in SKILL.md so the main file stays a lean overview.

Complete the entry-point snippet by showing how `manifest` is defined/imported, since the current example is not copy-paste runnable.

Add a short 'Adding a new connector' section with the concrete file path under src/connectors/ and the registration call, since connector onboarding is the most likely actionable use of this architecture knowledge.

DimensionReasoningScore

Conciseness

The body is a dense, project-specific reference — repo tree, handler/model/library tables, route listings, env vars — with no padding and no explanation of concepts Claude already knows (e.g., no 'what is a monorepo' prose). Every section carries information Claude could not infer.

5 / 5

Actionability

Concrete executable snippets ('const { createCoreApp, connectorRegistry } = require(...)', 'connectorRegistry.registerConnector(...)') and real commands ('npm run server', 'npm run ngrok', 'npm test') cover common cases. Minor gaps: the first snippet uses an undefined `manifest` variable and there is no example showing where/how a new connector module is wired into `src/connectors/`.

4 / 5

Workflow Clarity

This is a reference/understanding skill, and the body is cleanly sequenced for lookup (structure → core package → registry → routes → env → workflow → database), with a Development Workflow section of concrete commands. There are no destructive or batch operations that would demand validation checkpoints, so nothing is missing — but there is also no explicit multi-step workflow with checkpoints, keeping it below 5.

4 / 5

Progressive Disclosure

Sections are well-labeled and navigation within the file is easy, but no bundle files exist and the full ~170-line reference — including the API route catalog and environment-variable documentation — is inlined in SKILL.md rather than split into clearly signaled one-level-deep reference files. This matches the 'content that should be separate is inline' anchor rather than the 'appropriately split' anchor above.

3 / 5

Total

16

/

20

Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states what the skill covers with concrete, natural trigger terms anchored to a specific project. Its only weakness is that the when-to-use guidance is implicit in the what rather than stated as an explicit separate trigger clause.

DimensionReasoningScore

Specificity

The description names the domain ('RingCentral App Connect project structure') and enumerates several concrete coverage areas — 'monorepo layout, core package APIs, handlers, models, and how components interact'. It stops short of a 5 because it uses a single action verb ('understand') with a topic list rather than multiple distinct concrete capabilities.

4 / 5

Completeness

Both what and when are present: the what is concrete ('understand the RingCentral App Connect project structure, including...') and 'Use this skill to understand...' provides explicit trigger guidance. It is not a 5 because the when-clause is fused into the what rather than stated as a distinct, specific trigger phrase ('Use when asked about...' / 'when the user mentions...').

4 / 5

Trigger Term Quality

Good natural keyword coverage: 'project structure', 'monorepo layout', 'handlers', 'models', 'core package APIs' are phrases a developer on this codebase would naturally say. A few natural synonyms are missing ('codebase', 'architecture', 'repo layout'), which keeps it below the comprehensive-synonyms anchor at 5.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a named proprietary project ('RingCentral App Connect'), giving it a clear niche with distinct triggers and virtually no risk of firing for an unrelated skill. It matches the clear-niche/minimal-conflict anchor exactly.

5 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ringcentral/rc-unified-crm-extension

Path

.agent-skills/project-architecture/SKILL.md

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.