CtrlK
BlogDocsLog inGet started
Tessl Logo

giuseppe-trisciuoglio/developer-kit

Comprehensive developer toolkit providing reusable skills for Java/Spring Boot, TypeScript/NestJS/React/Next.js, Python, PHP, AWS CloudFormation, AI/RAG, DevOps, and more.

89

Quality

89%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

SecuritybySnyk

Risky

Do not use without reviewing

Overview
Quality
Evals
Security
Files

Quality

Discovery

100%

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 is a strong skill description that clearly defines what the skill does (Codex CLI delegation workflows with specific sub-capabilities), when to use it (explicit 'Use when' clause with concrete scenarios), and includes well-chosen trigger terms. The description is specific, distinctive, and complete, using proper third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'English prompt formulation, execution flags, sandbox modes, and safe result handling' as well as downstream tasks like 'code generation, refactoring, or architectural analysis'. These are concrete, actionable capabilities.

3 / 3

Completeness

Clearly answers both 'what' (Codex CLI delegation workflows for complex code generation including prompt formulation, execution flags, sandbox modes, result handling) and 'when' (explicit 'Use when...' clause plus enumerated trigger phrases).

3 / 3

Trigger Term Quality

Includes explicit trigger phrases that users would naturally say: 'use codex', 'delegate to codex', 'run codex cli', 'ask codex', 'codex exec', 'codex review'. These cover multiple natural variations of how a user might invoke this skill.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — targets a specific tool (Codex CLI with OpenAI's GPT-5.3-codex models) and a specific workflow (delegation). The trigger terms are all Codex-specific, making it very unlikely to conflict with general coding or other AI-tool skills.

3 / 3

Total

12

/

12

Passed

Implementation

62%

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

The skill is highly actionable with clear, executable commands and a well-structured multi-step workflow with appropriate safety checkpoints. However, it is significantly over-engineered and verbose—much of the content repeats itself across sections (safety warnings appear in Mandatory Rules, Instructions, Best Practices, and Constraints), and the 6 detailed examples are largely variations of the same pattern. The content would benefit greatly from aggressive trimming and offloading detailed references to separate files.

Suggestions

Reduce the examples section from 6 to 2-3 that demonstrate meaningfully different patterns (e.g., one exec, one review, one multimodal), and move the rest to a separate EXAMPLES.md file.

Consolidate safety warnings into a single section instead of repeating them across Mandatory Rules, Step 3 Safety Guidance, Best Practices, and Constraints—this alone could cut 30+ lines.

Move the detailed flag reference (all -a, -s, -m options with descriptions) to the referenced `cli-command-reference.md` file and keep only the most common patterns inline.

Remove the 'When to Use' trigger phrases list since this duplicates the frontmatter description and is not actionable instruction content.

DimensionReasoningScore

Conciseness

The skill is extremely verbose at ~300+ lines. It over-explains concepts Claude already knows (what SOLID principles are, what sandbox modes do, what REST APIs are), repeats safety warnings multiple times across sections, and includes excessive examples that are largely variations of the same pattern. The trigger phrases list duplicates the frontmatter description. The model selection table, best practices, and constraints sections all contain redundant information.

1 / 3

Actionability

The skill provides fully executable bash commands with concrete flags, specific model names, and real CLI syntax. Examples are copy-paste ready with detailed prompts. The command reference, flag descriptions, and example transformations (e.g., Italian to English prompt) are all concrete and actionable.

3 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced: confirm scope → formulate prompt → select mode/flags → execute → return results safely. It includes explicit validation checkpoints (verify tool availability, ask for clarification if ambiguous, require user confirmation before applying changes). The output template provides a structured feedback mechanism, and safety gates are clearly marked throughout.

3 / 3

Progressive Disclosure

There is one reference to an external file (`references/cli-command-reference.md`), but the bulk of the content is monolithic. The detailed flag descriptions, 6 examples, model selection guide, best practices, and constraints are all inline when much of this could be split into reference files. The structure has clear headings but the sheer volume of inline content undermines progressive disclosure.

2 / 3

Total

9

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Reviewed

Table of Contents