CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini-cli

Integrate Gemini AI CLI into Claude Code for AI collaboration, code analysis, and tool execution. Use when working with Gemini AI, Google AI, multimodal tasks, or needing advanced AI capabilities.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gemini-cli/SKILL.md

The canonical home for this skill is gemini-cli in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

53%Weight 40%Scale 1-5

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

The body is highly actionable with abundant copy-paste-ready commands, but it is over-long and repetitive, monolithic with no progressive disclosure, and its headline 'auto-pilot' batch examples lack validation and contradict its own safety guidance — capping workflow clarity.

Suggestions

Split the monolith into referenced bundle files (e.g., references/configuration.md, references/troubleshooting.md, examples/) and keep SKILL.md a lean overview, eliminating repeated YOLO safety guidance.

Add explicit validation/review checkpoints to the batch and destructive Examples — or remove the 'Auto-Pilot' / 'Daily Development Automation' --yolo examples that contradict the 'NEVER Use YOLO For multi-step workflows' rule — to raise workflow clarity above 3.

Cut generic padding Claude already knows (intro restatement of the description, 'Never commit API keys', repeated safe/unsafe YOLO lists) to improve token efficiency.

DimensionReasoningScore

Conciseness

The ~660-line body is noticeably verbose: it restates the description in the intro, repeats YOLO safe/unsafe guidance across at least five sections, and pads with generic advice Claude already knows (e.g., 'Never commit API keys'), well beyond 'mostly efficient'.

2 / 5

Actionability

Commands are concrete and copy-paste ready throughout — install, auth, 'gemini --yolo -p', '--output-format json', checkpoint restore, settings.json, and env vars — and the examples cover the common cases comprehensively.

5 / 5

Workflow Clarity

Some workflows (Think-Act-Observe loop, sequential decomposition, error-handling pattern) include verification checkpoints, but the flagship batch Examples run large destructive/auto-pilot operations under --yolo with no validation and directly contradict the body's own 'NEVER Use YOLO For multi-step workflows' rule, triggering the destructive/batch missing-validation cap of 3.

3 / 5

Progressive Disclosure

No bundle files exist and the document is a single ~660-line monolith; config reference, MCP guide, troubleshooting, and examples that clearly belong in separate referenced files are all inlined with section headers but no external navigation.

2 / 5

Total

12

/

20

Passed

Description

75%Weight 40%Scale 1-5

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 is solid: it states a concrete domain, lists several specific actions, and includes an explicit 'Use when' trigger, all in third person. It is held back from the top band by abstract phrasing ('AI collaboration', 'advanced AI capabilities') and a lack of synonyms or file extensions in the triggers.

DimensionReasoningScore

Specificity

Names the domain ('Integrate Gemini AI CLI into Claude Code') and several concrete actions ('AI collaboration, code analysis, and tool execution'), though 'AI collaboration' is somewhat abstract, leaving minor coverage gaps short of a 5.

4 / 5

Completeness

It answers both 'what' (integrate Gemini CLI for collaboration/code analysis/tool execution) and an explicit 'Use when...' trigger, but the 'what' leans on abstract phrasing and the triggers could be more concretely tied to actions.

4 / 5

Trigger Term Quality

'Use when working with Gemini AI, Google AI, multimodal tasks' provides good natural keyword coverage, but the generic buzzword tail 'needing advanced AI capabilities' and missing synonyms/extensions keep it below 5.

4 / 5

Distinctiveness Conflict Risk

The Gemini/Google AI framing carves a distinct niche unlikely to conflict with most skills, but the generic tail ('AI collaboration', 'advanced AI capabilities') creates minor overlap risk with general coding/AI skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (668 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.