CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gemini-cli-bridge

Integrate with Google's Gemini CLI for delegating tasks to Gemini. Use when you need an alternative AI perspective, Google Search grounding, parallel task execution, or want to leverage Gemini's 1M token context window. Enables "Claude calling Gemini" patterns for diverse AI collaboration.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

A well-organized, actionable body with concrete commands for MCP, CLI, and library integration plus error-recovery guidance. Main weaknesses are minor: pseudo-syntax in example workflows, unshown optional parameters, and time-sensitive version/quota claims that will need maintenance.

DimensionReasoningScore

Conciseness

Largely efficient with concrete commands and no padding explaining concepts Claude already knows, but minor items could be trimmed: the Claude-vs-Gemini comparison table and time-sensitive claims ('Gemini 2.5 Pro has a 1M token context window', '1000 req/day free', '60 req/min') that will go stale. Matches anchor 4 (efficient with minor over-explanation) rather than 5 given these trims; not 3 because nothing is extensively explained or padded.

4 / 5

Actionability

Mostly executable: copy-paste CLI commands ('gemini -p "Explain this error message" --output-format json', 'cat error.log | gemini -p "Analyze these errors"'), a concrete MCP server config JSON, env vars, and install/auth commands. Minor gaps keep it from 5: the example workflows use invented pseudo-syntax ('[gemini_prompt] prompt: ...'), and parameters like working_dir, timeout_secs, and sandbox are referenced without showing how to pass them in a real call.

4 / 5

Workflow Clarity

For this single-purpose delegation skill the action is unambiguous: pick a mode (MCP path is explicitly marked '(Recommended)'), then the concrete commands per mode, with an Error Handling section covering failure recovery (Not Found → 'npm install -g @google/gemini-cli'; Auth Failed → run gemini interactively; Rate Limit; Timeout). It is not 5 because no explicit validation checkpoint (e.g. verify the response or check gemini is installed before use) is built into the workflows.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~160-line body is well organized with clear section headers (When to Use, Usage Patterns, Configuration, Best Practices, Error Handling, Authentication) making it easy to navigate. It is not 5 because content like the MCP server setup, Authentication details, and Example Workflows could arguably live in separate reference files rather than fully inline; not 3 because structure and placement are good with nothing buried.

4 / 5

Total

16

/

20

Passed

Description

82%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.

A strong description that explicitly covers both what the skill does and when to use it, with distinctive, natural trigger terms. Its only real flaw is the second-person 'Use when you need...' phrasing, which costs it specificity under the rubric's voice rule.

Suggestions

Rewrite the 'when' clause in third person to avoid the second-person penalty, e.g. 'Use when an alternative AI perspective, Google Search grounding, parallel task execution, or a 1M-token context window is needed.'

Add a few more natural trigger synonyms such as 'ask Gemini', 'get Gemini's take', or 'second opinion' to broaden trigger-term coverage.

Lead with the concrete action verbs (e.g. 'Delegates tasks to Google's Gemini CLI...') to sharpen specificity.

DimensionReasoningScore

Specificity

The description lists several concrete actions ('delegating tasks to Gemini', 'Google Search grounding', 'parallel task execution', 'leverage Gemini's 1M token context window'), which is anchor-4 coverage, but 'Use when you need...' uses second-person voice, which the rubric penalizes by reducing specificity by 1. Not anchor 2 because the domain and actions are named specifically, not generic.

3 / 5

Completeness

Clearly answers 'what' ('Integrate with Google's Gemini CLI for delegating tasks to Gemini') and explicitly answers 'when' with concrete trigger phrases ('Use when you need an alternative AI perspective, Google Search grounding, parallel task execution...'). Matches the anchor-5 example pattern exactly; not below because neither element is missing or vague.

5 / 5

Trigger Term Quality

Good keyword coverage with natural phrases users would say: 'Gemini', 'Gemini CLI', 'Google Search grounding', 'alternative AI perspective', 'parallel task execution', 'Claude calling Gemini'. Not 5 because common variations like 'ask Gemini', 'second opinion', or 'Gemini's take' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — delegating work to Google's Gemini CLI — with distinct triggers ('Gemini', 'Google Search grounding', 'Claude calling Gemini') that would not fire for other skills. Minimal overlap risk; matches anchor 5.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Raudbjorn/TTTRPS

Path

planning/done/gemini-cli/SKILL.md

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.