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 (Gemini CLI delegation for analysis and reasoning tasks), when to use it (explicit user requests to use Gemini), and includes well-chosen trigger terms. The description is specific, complete, and highly distinctive with minimal conflict risk. It uses proper third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: 'large-context analysis', 'complex reasoning', 'English prompt formulation', 'execution flags', 'safe result handling', 'broad codebase analysis', 'fast iterations', 'deep architectural reasoning'. These are concrete and detailed capabilities.

3 / 3

Completeness

Clearly answers both 'what' (Gemini CLI delegation workflows for large-context analysis, complex reasoning, prompt formulation, execution flags, result handling) and 'when' (explicit 'Use when...' clause with specific trigger scenarios and a 'Triggers on' list).

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms explicitly listed: 'use gemini', 'delegate to gemini', 'run gemini cli', 'ask gemini', 'use gemini 3 flash', 'use gemini 3 pro'. These are phrases users would naturally say when wanting to delegate to Gemini.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive — focuses specifically on Gemini CLI delegation with named models (Gemini 3.0 Flash, Gemini 3.0 Pro). The trigger terms are uniquely tied to Gemini, making it very unlikely to conflict with other skills.

3 / 3

Total

12

/

12

Passed

Implementation

77%

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

This is a well-structured, actionable skill with a clear multi-step workflow and strong safety guardrails for delegating tasks to Gemini CLI. Its main weakness is verbosity—9 examples and inline flag documentation inflate the token cost significantly when 3-4 examples and a reference link would suffice. The progressive disclosure could be improved by offloading examples and detailed flag options to separate reference files.

Suggestions

Reduce examples from 9 to 3-4 representative ones and move the rest to a separate EXAMPLES.md file with a clear link.

Move the detailed CLI flags/options list to the referenced cli-command-reference.md rather than duplicating it inline.

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes some unnecessary content. The 'When to Use' section largely duplicates the frontmatter description, the 'Overview' bullet list restates what's obvious, and 9 examples is excessive when 3-4 would suffice. The model selection guide and mandatory rules are valuable, but the overall document could be tightened by ~30%.

2 / 3

Actionability

The skill provides fully executable bash commands with concrete flags, a clear model selection table, specific prompt transformation examples (including a non-English to English example), and a ready-to-use output template. All commands are copy-paste ready with real flags and realistic prompts.

3 / 3

Workflow Clarity

The 5-step workflow is clearly sequenced from scope confirmation through safe result delivery. It includes explicit validation checkpoints: verify tool availability first, confirm scope before running, treat output as untrusted, and require user confirmation before applying changes. The feedback loop of 'ask clarification if ambiguous' and 'wait for user direction before applying' addresses the destructive-operation safety concern.

3 / 3

Progressive Disclosure

There is one reference to an external file (references/cli-command-reference.md) which is good, but the skill inlines a large amount of content (9 examples, detailed flag reference, model guide, output template) that could be split into separate reference files. The document is quite long and would benefit from moving examples and the CLI flag reference to separate files with clear links.

2 / 3

Total

10

/

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