gemini
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
Overall
score
80%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
75%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 description has good structure with an explicit 'Use when' clause and clear differentiation through the Gemini CLI and large context window focus. However, it could be more specific about concrete actions beyond 'comprehensive analysis' and include more natural trigger term variations that users might actually say.
Suggestions
Add more specific concrete actions beyond 'comprehensive analysis' - e.g., 'analyze large codebases', 'review lengthy documents', 'process files exceeding Claude's context limit'
Include additional natural trigger terms users might say: 'large file', 'too long', 'external model', 'Gemini', 'big document', 'context limit'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gemini CLI) and some actions (code review, plan review, big context processing), but lacks comprehensive concrete actions. 'Comprehensive analysis' is somewhat vague. | 2 / 3 |
Completeness | Clearly answers both what (run Gemini CLI for code review, plan review, big context processing) and when (explicit 'Use when' clause with specific triggers for user requests). | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'code review', 'plan review', and '>200k' context, but missing common variations users might say like 'large file', 'long document', 'Gemini', or 'external model'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche targeting Gemini CLI specifically with distinct triggers around large context windows (>200k) and specific review types. Unlikely to conflict with general code review or document processing skills. | 3 / 3 |
Total | 10 / 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, highly actionable skill with excellent workflow clarity and concrete executable examples. The main weakness is verbosity—the critical warning about background mode is repeated excessively, and the content could be more token-efficient by consolidating redundant sections and potentially splitting detailed reference material into separate files.
Suggestions
Consolidate the background/non-interactive mode warnings into a single prominent section rather than repeating throughout the document
Consider moving the detailed troubleshooting section and model comparison table to separate reference files (e.g., TROUBLESHOOTING.md, MODELS.md) to reduce SKILL.md length
Remove redundancy between the 'Quick Reference' table and 'Common Use Cases' section—one or the other would suffice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful information but is verbose in places, with repeated warnings about background mode (mentioned 5+ times) and some redundancy between the quick reference table and the common use cases section. The model selection guide is thorough but could be more condensed. | 2 / 3 |
Actionability | Provides fully executable bash commands throughout, with specific flags, model names, and copy-paste ready examples. The troubleshooting section includes concrete diagnostic commands and the quick reference table maps use cases to exact command patterns. | 3 / 3 |
Workflow Clarity | Clear numbered steps for running tasks (1-7), explicit validation checkpoints (ask user for model, check for hung processes), and feedback loops for error handling. The troubleshooting section provides detection → diagnosis → resolution workflow with explicit commands at each step. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and headers, but everything is in a single file. The skill is ~200 lines and could benefit from splitting detailed troubleshooting and model comparison into separate reference files, keeping SKILL.md as a concise overview. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
87%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 14 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
Total | 14 / 16 Passed | |
- 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.