CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

63

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./planning/done/gemini-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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, actionable reference with concrete CLI/MCP examples, but it has moderate redundancy across sections and lacks explicit sequenced workflows with validation checkpoints — particularly around the demonstrated YOLO auto-approve mode. As a single self-contained file with no bundle references, progressive disclosure is good but not exemplary.

Suggestions

Add an explicit verify/confirm step before invoking Gemini in --yolo or yolo_mode:true, e.g. a checkpoint that lists planned actions and requires user confirmation for destructive operations, to lift workflow_clarity above the validation cap.

De-duplicate content: either trim the 'When to Use' bullets that restate the description, or replace the stylized [gemini_prompt] example-workflow blocks with the actual copy-paste CLI/MCP commands already shown in Usage Patterns.

Move the multi-method Authentication and full Example Workflows detail into a reference file (e.g. references/advanced.md) and link from the body, to improve progressive_disclosure toward a 5.

DimensionReasoningScore

Conciseness

Content is mostly efficient and free of concept over-explanation, but the 'When to Use' bullets restate the description and the 'Example Workflows' re-illustrate tools already shown in Usage Patterns, so it could be tightened rather than earning a 4.

3 / 5

Actionability

Provides copy-paste-ready CLI commands ('gemini -p "..." --output-format json', pipe examples), MCP tool names, and config snippets, but the Rust example targets an unverified crate and the example-workflow blocks use stylized [gemini_prompt] pseudo-syntax rather than literal executable calls, leaving minor gaps short of a 5.

4 / 5

Workflow Clarity

The skill is a usage-pattern reference rather than an explicitly sequenced multi-step workflow, and it demonstrates destructive-capable 'yolo'/'yolo_mode' options with only a one-line caution and no verify-then-proceed checkpoint, so validation gaps keep it at the 3 anchor.

3 / 5

Progressive Disclosure

No bundle files exist and the body is a single well-organized file with clear section headers, tables, and code blocks; it earns good-structure marks but not a 5 because everything is inline with no one-level-deep references and some sections (detailed auth methods, example workflows) could be split out.

4 / 5

Total

14

/

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.

The description is strong: it clearly states the skill's purpose and gives an explicit, multi-trigger 'Use when' clause, and it is tightly scoped to a Gemini-specific niche with low conflict risk. The only mild gap is specificity, where capabilities are named as use-cases rather than the concrete tool operations.

DimensionReasoningScore

Specificity

Lists several specific capabilities — 'delegating tasks to Gemini', 'Google Search grounding', 'parallel task execution', '1M token context window' — which is above the 1-2-action anchor, but stops short of enumerating the concrete tool operations (gemini_prompt, gemini_search), so it is not a comprehensive 5.

4 / 5

Completeness

Explicitly states both what it does ('Integrate with Google's Gemini CLI for delegating tasks to Gemini') and when to use it via an explicit 'Use when...' clause with multiple concrete triggers, matching the top anchor; the present Use-when clause means no completeness cap applies.

5 / 5

Trigger Term Quality

Includes fairly natural phrases a user might say ('alternative AI perspective', 'Google Search grounding', 'parallel task execution', 'Claude calling Gemini') with good Gemini/Google keyword coverage, but misses common synonyms like 'second opinion' or 'ask another model', fitting the 'good coverage, a few natural terms missing' anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear, narrow niche (a Gemini CLI bridge) with Gemini-specific triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Raudbjorn/TTTRPS
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.