skill-evaluation-and-iteration-with-gemini
Diagnose, score, and systematically refactor Gemini CLI skills for high-efficiency performance and reliability.
- Audit skills for context-window inefficiency and token bloat.
- Upgrade basic prompts into robust, marketplace-ready agent protocols.
- Fix hallucination issues by enforcing strict tool boundaries and guardrails.
Secure checkout via Stripe
Included in download
- Audit skills for context-window inefficiency and token bloat.
- Upgrade basic prompts into robust, marketplace-ready agent protocols.
- file_write, file_read automation included
- Includes example output and usage patterns
Sample Output
A real example of what this skill produces.
Tool Precision: 4/10. Notes: Skill uses 'run_shell_command' to read files instead of 'read_file' with line offsets, causing context bloat. Diagnosis: Protocol Weakness. Plan: Update instructions to mandate 'grep_search' for initial discovery. Recommended: Execute surgical rewrite? (Y/N)
skill-evaluation-and-iteration-with-gemini
Diagnose, score, and systematically refactor Gemini CLI skills for high-efficiency performance and reliability.
Secure checkout via Stripe
Included in download
- Audit skills for context-window inefficiency and token bloat.
- Upgrade basic prompts into robust, marketplace-ready agent protocols.
- file_write, file_read automation included
- Includes example output and usage patterns
- Instant install
Sample Output
A real example of what this skill produces.
Tool Precision: 4/10. Notes: Skill uses 'run_shell_command' to read files instead of 'read_file' with line offsets, causing context bloat. Diagnosis: Protocol Weakness. Plan: Update instructions to mandate 'grep_search' for initial discovery. Recommended: Execute surgical rewrite? (Y/N)
About This Skill
Optimize Your AI Agent Performance
Low-quality skills lead to context exhaustion, hallucinations, and agent drift. This skill provides a rigorous diagnostic framework designed specifically for developer-centric agent architectures like the Gemini CLI. It systematically audits your instruction sets to ensure they meet professional distribution standards.
What it does
The evaluator performs a multi-phase audit of any instruction file (SKILL.md). It uses a 9-dimension rubric—including Tool Precision, Orchestration, and Output Contracts—to assign objective scores. After diagnosis, it identifies "context leaks" and protocol weaknesses, providing a prioritized plan to refactor vague advice into hard agent protocols. Finally, it can surgically rewrite your skill to implement these improvements automatically.
Why use this skill
Prompting an AI yourself is often a trial-and-error process. This skill automates the "red-teaming" of your agent logic. It replaces general prompts with high-efficiency tool patterns (like replacing generic shell commands with targeted search tools), drastically reducing token usage and improving the reliability of your local workflows. It ensures your skills are marketplace-ready by enforcing strict guardrails and clear triggering conditions.
Supported Frameworks
Optimized for Gemini CLI and agents utilizing Plan Mode, sub-agent orchestration, and advanced file manipulation tools.
📖 Learn more: Best DevOps & Deployment Skills for Claude Code →
Use Cases
- Audit skills for context-window inefficiency and token bloat.
- Upgrade basic prompts into robust, marketplace-ready agent protocols.
- Fix hallucination issues by enforcing strict tool boundaries and guardrails.
- Refactor vague instructions into imperative, phased execution steps.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/skill-evaluation-and-iteration-with-gemini | tar xz -C ~/.claude/skills/Free skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Early access skill
Be the first to review this skill.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
Allowed Hosts
File Scopes
**Permission Profile**: Analysis & Refactoring (Read + Write)
This skill is optimized for evaluating skills meant to be run by the **Gemini CLI**. It is highly attuned to the specific context window and tool capabilities of this environment.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
diagnosing-rag-failure-modes
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
subagent-orchestrator (Develop based on the Claude Code sourcemap)
Turn your AI agent into a coordinator that manages parallel subagents for complex coding and research tasks.
software-architect
A structured framework for planning, reviewing, and evolving complex software systems with explicit trade-offs.
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.