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 description that clearly articulates a specific, niche capability with concrete actions and explicit trigger guidance. It names specific models, lists distinct features, and provides a clear 'Use when' clause with natural trigger phrases. The description is concise yet comprehensive, making it easy for Claude to select this skill appropriately.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions: task delegation in non-interactive mode, multi-model support with named models (Claude, GPT, Gemini), permission controls, output sharing, and session resume.

3 / 3

Completeness

Clearly answers both what (GitHub Copilot CLI task delegation with multi-model support, permission controls, output sharing, session resume) and when ('Use when users ask to hand work to Copilot, compare models, or run Copilot programmatically from Claude Code').

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would say: 'Copilot', 'hand work to Copilot', 'compare models', 'run Copilot programmatically', 'Claude Code', 'GPT', 'Gemini'. These cover likely user phrasings well.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche: GitHub Copilot CLI delegation from within Claude Code is a very specific use case unlikely to conflict with other skills. The combination of Copilot, non-interactive mode, and multi-model comparison creates clear differentiation.

3 / 3

Total

12

/

12

Passed

Implementation

72%

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

This is a solid, well-structured skill with strong actionability through concrete examples and executable commands. Its main weaknesses are moderate verbosity (trigger phrases, overview redundancy, model selection rationale Claude doesn't need) and the lack of explicit validation/verification steps integrated into the workflow after Copilot output is received. The progressive disclosure and overall organization are excellent.

Suggestions

Integrate an explicit validation step (e.g., run tests, lint, type-check) into the workflow between step 5 (run command) and step 6 (return results) rather than only mentioning validation in the Constraints section.

Trim the 'When to Use' trigger phrases list and 'Overview' bullet list — these repeat information Claude can infer from the instructions themselves, saving ~20 lines of context.

DimensionReasoningScore

Conciseness

The skill is reasonably well-structured but includes some unnecessary verbosity. The 'When to Use' section with trigger phrases, the 'Overview' bullet list that repeats CLI flags, and some explanatory text (e.g., 'This skill standardizes delegation...') could be trimmed. The model selection guidance in step 3 explains reasoning Claude already understands.

2 / 3

Actionability

The skill provides fully executable bash commands with concrete flag combinations, a clear prompt template, and three worked examples showing real input-to-command-to-output flows. Commands are copy-paste ready with specific model names and flag patterns.

3 / 3

Workflow Clarity

The 7-step workflow is clearly sequenced from prerequisites through execution to results. However, there are no explicit validation checkpoints after running Copilot commands — the 'Constraints and Warnings' section mentions validating output but doesn't integrate verification steps (tests/lint/type checks) into the workflow itself. For a skill that delegates to external models and may apply code changes, this is a meaningful gap.

2 / 3

Progressive Disclosure

The content is well-organized with clear sections (Overview, When to Use, Instructions, Examples, Best Practices, Constraints) and appropriately references `references/cli-command-reference.md` for additional details — a single-level-deep reference. The skill is self-contained for common use while pointing elsewhere for exhaustive CLI options.

3 / 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