ask-gemini

Consult Gemini as an independent expert with deep web research. Sends a question or task to Gemini CLI and returns a research-backed response.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

100%Weight 40%Scale 1-3

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, executable instruction set: it gives the exact shell command, a flagged variant, output-interpretation guidance, and an exit-code error-handling table, all well sectioned for a single-purpose skill. The only nit is a lightly repeated statement that Gemini performs Google Search.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, giving executable commands, a compact exit-code table, and brief notes without explaining concepts Claude already knows; the only minor slack is a repeated Google-Search fact that could be tightened.	3 / 3
Actionability	Provides fully executable, copy-paste-ready commands ('"${CLAUDE_PLUGIN_ROOT}/scripts/ask-gemini.sh" "$ARGUMENTS"' and a flagged example) plus a concrete exit-code table and default model/timeout, leaving no ambiguity about what to run.	3 / 3
Workflow Clarity	For this simple single-action skill the sequence is unambiguous (run the quoted command, read stdout, relay sources, handle non-zero exits), and the exit-code table provides explicit validation/checkpoint guidance for error recovery.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no external bundle files needed, and content is organized into clearly signaled sections (How to Use, Interpreting Output, Error Handling, Notes), satisfying the simple-skill allowance for a top score.	3 / 3
	Total	12 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 a distinct Gemini-consultation niche and uses proper third-person voice, but it lacks an explicit 'Use when...' trigger clause and its action list and natural trigger terms are only moderately specific. Adding a usage-trigger sentence would raise completeness and trigger-term coverage.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user wants a second opinion, deep web research, or an independent expert take on a question.'

Broaden natural trigger terms to include phrasings users actually say, such as 'ask Gemini', 'get Gemini's opinion', or 'research with Gemini'.

List more concrete capabilities (e.g. 'performs Google Search, cites web sources, returns a research-backed answer') to move specificity from domain-naming to multiple specific actions.

Dimension	Reasoning	Score
Specificity	Names the domain (Gemini CLI, web research) and concrete actions ('Sends a question or task', 'returns a research-backed response'), but the verbs are generic around a single tool rather than a comprehensive list of specific actions.	2 / 3
Completeness	Clearly states what the skill does, but there is no explicit 'Use when...' trigger clause, so the 'when to use it' guidance is only implied and completeness is capped at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms like 'Gemini', 'web research', and 'research-backed response', but misses common variations a user might say such as 'ask Gemini' or 'research with Gemini'.	2 / 3
Distinctiveness Conflict Risk	The Gemini-specific consultation niche ('Consult Gemini as an independent expert with deep web research') is clearly distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: PolyArch/humanize
Path: skills/ask-gemini/SKILL.md
Commit: 0ec921a

Reviewed: 8 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.