CtrlK
BlogDocsLog inGet started
Tessl Logo

gemini

Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini on Google Ads strategy, SEO best practices, or implementation questions). Use when the user says "gemini review", "ask gemini", "gemini challenge", "second opinion from gemini", "consult gemini", "stress test with gemini", "what would gemini say", "cross-model review", or "get another opinion". Voice aliases: "gem", "gemini check". Especially useful for Google Ads changes, SEO metadata updates, campaign structure decisions, keyword strategies, and bid/budget changes — Gemini has native Google ecosystem knowledge that complements Claude's analysis.

73

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 a well-structured, highly actionable orchestration playbook with concrete commands and ready-to-use Gemini prompts for three modes and three change types. Its main weakness is mild verbosity in the presentation templates and the lack of a retry feedback loop on Gemini invocation errors.

Suggestions

Add a brief retry/recovery step when the gemini CLI exits non-zero (e.g., re-authenticate or retry once) rather than only reporting the error, to add a validation feedback loop.

Tighten the Step 5 cross-model analysis and next-steps templates — they are somewhat verbose and could be condensed without losing clarity.

Consider extracting the three large mode prompt blocks into a references file (e.g., prompts.md) referenced one level deep, keeping SKILL.md as a leaner overview.

DimensionReasoningScore

Conciseness

Mostly efficient with executable prompt blocks and bash commands earning their place; minor padding in the Step 5 cross-model analysis and next-steps templates and some persona restatement across the three mode prompts that could be tightened.

4 / 5

Actionability

Fully executable guidance — concrete bash commands (CLI detection, git diff, gemini -p invocations) and complete copy-paste-ready prompt templates covering the review/challenge/consult modes across code/ads/seo change types.

5 / 5

Workflow Clarity

Clear linear sequence (Steps 0–5) with an explicit CLI-detection validation gate and non-zero exit handling, but no fix-and-retry feedback loop on Gemini errors, only 'report the error to the user'.

4 / 5

Progressive Disclosure

Well-organized into clearly headed steps and subsections with no nested references and all content in one self-contained file; the long inline prompt blocks are core executable content rather than material that belongs in separate reference files, so structure is good with minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

100%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 exemplary: it states what the skill does across three modes, when to use it with concrete trigger phrases, and why it is distinct (Gemini's native Google ecosystem knowledge). It avoids fluff and stays in the standard imperative/third-person skill-description voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across three explicit modes — 'pass/fail gate for Google Ads campaigns, SEO metadata, or code', 'adversarial stress-test that tries to break your changes', and 'open Q&A' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both 'what' (three modes with concrete behaviors) and 'when' via an explicit 'Use when the user says...' clause listing concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases including synonyms and aliases — 'gemini review', 'ask gemini', 'second opinion from gemini', 'what would gemini say', 'cross-model review', plus voice aliases 'gem' and 'gemini check'.

5 / 5

Distinctiveness Conflict Risk

Clear niche — a Gemini-based cross-model second opinion leveraging native Google ecosystem knowledge — with triggers tied to 'gemini', making conflict with other skills minimal.

5 / 5

Total

20

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nowork-studio/NotFair
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.