gemini
Gemini CLI for one-shot Q&A, summaries, and generation.
75
Quality
66%
Does it follow best practices?
Impact
99%
1.32xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/gemini/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a specific tool (Gemini CLI) and lists high-level capabilities, but lacks the explicit 'Use when...' guidance critical for skill selection. The capabilities listed are too generic and could apply to many AI tools, reducing distinctiveness.
Suggestions
Add an explicit 'Use when...' clause with trigger terms like 'use Gemini', 'Gemini CLI', 'ask Gemini', or 'one-shot generation'
Make capabilities more specific - instead of 'Q&A, summaries, generation', specify concrete actions like 'query Gemini for quick answers, generate text summaries via CLI, run one-shot prompts without conversation context'
Clarify what distinguishes this from other LLM/AI skills - emphasize 'one-shot' nature and CLI-specific use cases
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Gemini CLI) and lists some actions (Q&A, summaries, generation), but these are fairly generic categories rather than concrete specific actions like 'extract tables' or 'fill forms'. | 2 / 3 |
Completeness | Describes what it does (Gemini CLI for Q&A, summaries, generation) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'Gemini CLI' which is a specific trigger, and 'Q&A, summaries, generation' are somewhat natural terms, but missing common variations users might say like 'ask Gemini', 'generate with Gemini', or 'one-shot prompt'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Gemini CLI' is distinctive, but 'Q&A, summaries, and generation' are extremely broad capabilities that could overlap with many other AI/LLM-related skills or general text processing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent, minimal skill that respects Claude's intelligence and token budget. It provides exactly what's needed for one-shot Gemini CLI usage without any fluff. The safety note about avoiding --yolo is appropriately brief and well-placed.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. No unnecessary explanations of what Gemini is or how CLI tools work. Every line provides actionable information. | 3 / 3 |
Actionability | Provides concrete, copy-paste ready commands for common use cases. The quick start examples are immediately executable with clear flag usage. | 3 / 3 |
Workflow Clarity | For this simple, single-purpose skill (one-shot CLI usage), the workflow is unambiguous. The auth note provides a clear recovery path if needed. | 3 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized with clear sections (Quick start, Extensions, Notes) that are easy to scan. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
50ef2f3
- 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.