gemini

Gemini CLI for one-shot Q&A, summaries, and generation.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/gemini/SKILL.md

The canonical home for this skill is gemini in openclaw/openclaw

Quality

Content

100%

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

The body is a tight, action-first reference: concrete executable commands, a clear single-action quick start, and well-organized sections with no padding. It is an exemplary short skill body.

Dimension	Reasoning	Score
Conciseness	The body is ~20 lean lines with no concept-padding (no explanation of what Gemini is); every line is actionable guidance, matching 'Lean and efficient; assumes Claude's competence'.	3 / 3
Actionability	It gives concrete, executable commands ('gemini "Answer this question..."', 'gemini --model <name> "Prompt..."', 'gemini --output-format json') that are copy-paste ready, fitting 'Fully executable code/commands; specific examples'.	3 / 3
Workflow Clarity	This is a simple single-task skill whose single action (one-shot positional prompt) is unambiguous; per the simple_skills note that qualifies for 3, and there are no destructive/batch operations requiring validation checkpoints.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no external references and no bundle files present, and its sections (Quick start, Extensions, Notes) are well organized; per the simple_skills note this qualifies for 3.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 clearly identifies the tool and its primary modes but stops short of explicit trigger guidance and specific, varied trigger terms. Adding a 'Use when...' clause with natural user phrasings would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks Gemini a question, wants a summary, or needs text generation in one shot.'

Broaden trigger terms to natural user phrasings like 'ask Gemini', 'summarize', 'generate text', or 'quick one-shot prompt'.

Replace the vague 'generation' with more concrete actions (e.g. 'generate text or code') to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Gemini CLI') and several actions ('one-shot Q&A, summaries, and generation'), but 'generation' is vague and the action list is not comprehensive, so it matches 'Names domain and some actions' rather than the multi-specific level 3.	2 / 3
Completeness	It states what the skill does but lacks any 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing trigger clause caps completeness at 2, and it is not level 1 because the 'what' is present.	2 / 3
Trigger Term Quality	It includes some relevant natural keywords ('Q&A', 'summaries', 'generation', 'Gemini CLI') but misses common phrasings a user would actually say ('ask Gemini', 'summarize this', 'generate text'), fitting 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	'Gemini CLI' gives it a clear tool niche, but the use-triggers (Q&A, summaries, generation) are generic LLM tasks that could overlap with other generation skills, matching 'Somewhat specific but could still overlap'.	2 / 3
	Total	8 / 12 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 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	13 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/gemini/SKILL.md
Commit: e73c717

Reviewed: about 16 hours ago

Table of Contents

Discovery Implementation Validation

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.