Name: gemini-chat
Rating: 52.8 (1 reviews)
Author: fernandezbaptiste

gemini-chat

Interactive chat workflows with Gemini CLI including context management, multimodal conversations, and session persistence. Use for extended AI conversations, brainstorming, or collaborative problem-solving.

Quality

58%

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 ./.claude/skills/gemini-chat/SKILL.md

The canonical home for this skill is gemini-chat in fernandezbaptiste/Skrillz

Quality

Content

50%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 content is rich with concrete, executable examples but is over-long, padded with concepts Claude already knows, and ships autonomous YOLO workflows without validation checkpoints. It is also a monolithic file with no progressive disclosure into bundle references.

Suggestions

Trim or move basic prompt-engineering and role-persona material that Claude already knows; keep only Gemini-CLI-specific flags and behaviors to improve conciseness.

Add explicit validation/verification steps (e.g. review diffs, run tests, confirm before applying) to the --yolo automated workflows so batch execution is gated, raising workflow clarity above the cap of 3.

Split integration patterns, automation scripts, and the command reference into separate reference files linked from SKILL.md so the body stays an overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	At ~530 lines the body is noticeably verbose, padding in basic prompt-engineering concepts Claude already knows (structured prompts, role personas, 'be specific/provide context' advice) and redundant automation examples, fitting the 'noticeably verbose; several unnecessary explanations or padded sections' anchor.	2 / 5
Actionability	Provides mostly executable, copy-paste-ready bash commands and code (gemini -i, --include-directories, --checkpointing, --yolo, slash commands, vim/tmux integration) covering common cases, with only minor gaps and a few possibly-speculative subcommands like 'gemini context size'.	4 / 5
Workflow Clarity	Sequences exist (e.g. brainstorm_session, code review) but the YOLO/--yolo automated workflows are batch operations that execute autonomously with no validation or verification checkpoints, so workflow clarity is capped at 3 per the destructive/batch guidance.	3 / 5
Progressive Disclosure	The body has clear section headers but is a single ~530-line monolith with no bundle files (references/scripts/assets absent) and content that belongs in separate files (integration patterns, automation scripts, prompt engineering) inlined, matching 'some structure but content that should be separate is inline'.	3 / 5
	Total	12 / 20 Passed

Description

67%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 in third person, covers both what the skill does and when to use it, and names several concrete capabilities. It is held back by slightly generic trigger terms and minor overlap with sibling Gemini skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Gemini CLI chat) and several concrete capabilities — 'context management, multimodal conversations, and session persistence' — with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the fully comprehensive level 5.	4 / 5
Completeness	Answers both 'what' (interactive chat workflows with context management, multimodal, session persistence) and 'when' ('Use for extended AI conversations, brainstorming, or collaborative problem-solving'); the trigger clause is explicit but could be more concrete, so it sits at level 4 rather than 5.	4 / 5
Trigger Term Quality	Includes some natural terms a user would say ('brainstorming', 'extended AI conversations', 'collaborative problem-solving') but misses common variations like 'chat with Gemini' or 'ask Gemini', fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Gemini CLI interactive-chat niche is mostly distinct, but the body's 'Related Skills' (gemini-cli, gemini-tools, gemini-mcp) signal minor overlap risk with closely related sibling skills, placing it at level 4 rather than the minimal-conflict level 5.	4 / 5
	Total	15 / 20 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
skill_md_line_count	SKILL.md is long (533 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: .claude/skills/gemini-chat/SKILL.md
Commit: 93ed392

Reviewed: 2 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.