Name: gemini-cli-bridge
Rating: 65.60000000000001 (1 reviews)
Author: Raudbjorn

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

77%

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 ./planning/done/gemini-cli/SKILL.md

The canonical home for this skill is gemini-cli-bridge in Raudbjorn/TTTRPS

Quality

Content

67%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 well-structured and largely actionable with concrete CLI/code examples, but loses points on conciseness due to narrated workflow filler and redundancy. The Example Workflows also mix non-executable pseudo-syntax with otherwise runnable commands.

Suggestions

Strip the narrated filler from Example Workflows (e.g. 'I'll use Gemini for real-time search:', 'Let me get Gemini's perspective on this code:') and show only the tool invocation, to tighten conciseness.

State the 1M token context window once instead of repeating it in the description, the comparison table, and 'When to Use'.

Replace the non-executable '[gemini_search]' / '[gemini_prompt]' block syntax in Example Workflows with the actual CLI or MCP calls used elsewhere so all examples are copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but the Example Workflows carry narrated filler ('I'll use Gemini for real-time search:', 'Let me get Gemini's perspective on this code:') and the 1M-token-context point is repeated across the description, table, and 'When to Use', so it 'includes some unnecessary explanation' rather than the lean 4.	3 / 5
Actionability	Provides mostly executable guidance — real CLI invocations ('gemini -p "..." --output-format json', 'cat error.log \| gemini -p "..."'), MCP tool names, a Rust snippet, and config JSON — but the Example Workflows use a non-executable '[gemini_search]' / '[gemini_prompt]' block syntax that is a minor gap, fitting 'mostly executable; minor gaps'.	4 / 5
Workflow Clarity	The skill is a catalog of distinct single-action usage patterns (MCP, direct CLI, Rust) rather than one multi-step process, and each is clearly sequenced and unambiguous with no destructive/batch operation that would require a validation checkpoint or trigger the 3-cap; this matches 'clear sequence with most checkpoints present; minor gaps'.	4 / 5
Progressive Disclosure	No bundle files exist and the body is a single well-organized file with clear section headers covering overview-level material, fitting 'good structure; most content appropriately placed; minor organization gaps' rather than the separate-file reference pattern of a 5.	4 / 5
	Total	15 / 20 Passed

Description

87%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, well-formed description that explicitly covers both capability and trigger conditions with a clearly distinct niche. The only minor gap is trigger-term synonym coverage, which keeps specificity and trigger_term_quality at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Integrate with Google's Gemini CLI for delegating tasks to Gemini') and several concrete capabilities (Google Search grounding, parallel task execution, 1M token context), which matches 'lists several specific actions; minor gaps' rather than the 1-2 actions of a 3 or the comprehensive action list of a 5.	4 / 5
Completeness	It explicitly states both what it does ('Integrate with Google's Gemini CLI for delegating tasks to Gemini') and when to use it with concrete trigger phrases, matching the 'clearly and explicitly answers both what AND when' anchor.	5 / 5
Trigger Term Quality	The 'Use when...' clause surfaces natural triggers ('alternative AI perspective', 'Google Search grounding', 'parallel task execution', 'Gemini', '1M token context window') giving good keyword coverage, but it stops short of the synonym/extension comprehensiveness that defines a 5.	4 / 5
Distinctiveness Conflict Risk	The Gemini-CLI / 'Claude calling Gemini' niche is distinct from other skills and unlikely to trigger for the wrong skill, fitting the 'clear niche with distinct triggers; minimal conflict risk' anchor.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Raudbjorn/TTTTRPS
Path: planning/done/gemini-cli/SKILL.md
Commit: 387c8cf

Reviewed: 1 day 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.