gemini-tools

Execute and manage Gemini CLI built-in tools including file operations, web search, shell commands, and memory. Use for automated workflows, tool orchestration, and safe execution patterns.

Quality

69%

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-tools/SKILL.md

Quality

Content

71%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 copy-paste bash and clear safety/validation sections, but it is verbose due to repetitive example patterns and monolithic — all content is inlined with no progressive disclosure to bundle files. Consolidating duplicate examples and moving reference material into separate files would improve both conciseness and structure.

Suggestions

Collapse the repetitive `gemini --yolo -p` bash function variants (YOLO uses, Tool Workflows, Advanced Patterns) into a small set of canonical templates with a table of prompt variations, cutting significant length.

Move the elaborated reference material (tool-policy.json config, monitoring/audit-trail scripts, advanced chaining patterns) into files under references/ and link to them from SKILL.md to enable progressive disclosure.

Embed a brief validation/checklist step directly inside the batch and destructive workflow examples (e.g. 'review the diff, then proceed') so checkpoints are not only in the separate Safety Patterns section.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows, but at ~560 lines it repeats near-identical `gemini --yolo -p "..."` bash function patterns across YOLO uses, Tool Workflows, and Advanced Patterns, so substantial tightening is possible.	3 / 5
Actionability	Nearly every section gives copy-paste-ready, executable bash commands and full parameterized functions covering the common cases (file ops, web, shell, memory, setup, bulk processing), with a concrete JSON tool-policy example as well.	5 / 5
Workflow Clarity	Explicit validation and feedback loops exist in dedicated sections (Pre-Execution Validation, Rollback, retry/recovery in Error Handling), but the batch and destructive workflows themselves fire one large YOLO prompt without inline checkpoints, leaving minor validation gaps.	4 / 5
Progressive Disclosure	Section headers are clear and logically grouped, but the skill is a monolithic ~560-line file with no bundle references (references/scripts/assets absent) and sizable elaboration (elaborate bash functions, JSON policy, monitoring/audit scripts) that could be split into separate files.	3 / 5
	Total	15 / 20 Passed

Description

67%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 cleanly answers both what and when with a Gemini-scoped niche and several concrete action categories, but its trigger phrases lean on abstract jargon ('tool orchestration', 'safe execution patterns') rather than natural user language and lack synonyms or extensions. Strengthening the 'when' clause with concrete user-utterance triggers would lift completeness and trigger-term quality.

Suggestions

Replace jargon triggers ('tool orchestration', 'safe execution patterns') with natural phrases a user would say, e.g. 'Use when running Gemini CLI tools in scripts, automating repetitive file or shell tasks, or chaining tool calls together'.

Concretize 'file operations' into the actual actions (read, write, modify, list files) to raise specificity toward 5.

Add common synonyms or extensions (e.g. 'shell commands, running scripts, web search, Google search') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete action categories ('file operations, web search, shell commands, and memory') with comprehensive coverage of the tool surface, but 'file operations' stays abstract rather than enumerating read/write/modify, a minor gap that keeps it below 5.	4 / 5
Completeness	Explicitly states both what ('Execute and manage Gemini CLI built-in tools including...') and when ('Use for automated workflows, tool orchestration, and safe execution patterns'), but the 'when' triggers are generic rather than concrete user-utterance phrases, so it is not a 5.	4 / 5
Trigger Term Quality	'web search' and 'shell commands' are natural user phrases, but 'tool orchestration' and 'safe execution patterns' are jargon users would not say, and no synonyms or file extensions are offered, so common variations are missing.	3 / 5
Distinctiveness Conflict Risk	Clearly scoped to 'Gemini CLI built-in tools', giving it a distinct niche, but it overlaps with the sibling 'gemini-cli' (main integration) and 'gemini-mcp' skills referenced in the body, a minor conflict risk that caps it at 4.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (567 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/gemini-tools/SKILL.md
Commit: 93ed392

Reviewed: 2 days 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.