x-gemini

Direct Google Gemini bridge via the Antigravity (agy) CLI — uses Google Ultra subscription (no API key), opt-in Google Search grounding (via `--grounded`), and gemini-3.x models without the OpenCode layer

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/x-gemini/SKILL.md

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.

A lean, highly actionable CLI-bridge skill with executable commands, a recovery table, and well-signaled external references; its only weaknesses are minor repetition across sections and a destructive --yolo mode that lacks an explicit validation checkpoint.

Suggestions

Consolidate the repeated 'plain-text only', '--grounded required', and exit-code-noise notes into a single canonical statement to tighten conciseness.

Add an explicit validation gate before --yolo (e.g. a confirmation check or a dry-run/--plan step) so the destructive variant has a real checkpoint.

Verify gotchas.md and ../x-shared/capability-loading.md resolve from the skill directory, and surface them as proper one-level links to firm up progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no 'what is a CLI' padding) with every section earning its place; it loses the 5 only because 'plain-text only', '--grounded required', and the exit-code noise caveat are each restated 2–3 times and could be tightened.	4 / 5
Actionability	Fully executable, copy-paste-ready commands cover the common cases — 'agy-agent --grounded "Latest stable version of X?"', '--resume', '--add-dir', a complete env-var table, and an exit-code/recovery table — matching the 'fully executable, copy-paste ready' anchor.	5 / 5
Workflow Clarity	A clear Bootstrap → Quick Dispatch → Error Handling sequence with recovery feedback loops (auth → run interactively; timeout → raise AGY_TIMEOUT; quota → wait/switch model) sits at 'clear sequence with most checkpoints'; the destructive --yolo variant carries a DANGER gate but no hard validation checkpoint, keeping it below 5.	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep, clearly signaled references (gotchas.md, ../x-shared/capability-loading.md) and most content appropriately inline; no bundle files exist under references/scripts/assets, so it cannot reach the ideal 5 split, fitting 'good structure, minor organization gaps'.	4 / 5
	Total	17 / 20 Passed

Description

66%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 specific, well-differentiated description that concretely names the bridge, grounding, and model tier, but it omits any explicit 'Use when…' trigger guidance, which caps completeness and keeps it just above the midpoint.

Suggestions

Append an explicit 'Use when…' clause naming concrete triggers (e.g. 'Use when you need fresh web facts with citations via --grounded, or Gemini 3.x without the OpenCode layer').

Add a few natural trigger synonyms users might say (e.g. 'gemini pro', 'grounded gemini search') to lift trigger-term coverage toward comprehensive.

State the single most distinctive 'when' (Google Search grounding that opencode-routed Gemini does not reliably trigger) to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete attributes — 'Direct Google Gemini bridge via the Antigravity (agy) CLI', 'no API key', 'opt-in Google Search grounding (via --grounded)', 'gemini-3.x models' — with only minor gaps, fitting the 'lists several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	The 'what' is clear (a direct Gemini CLI bridge with grounding and model selection) but there is no 'Use when…' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Triggers 'x-gemini', 'ask gemini directly', 'gemini-3.1-pro' plus body keywords 'Google Gemini' and 'agy' give good natural-term coverage, but a few common variations (e.g. 'gemini pro', 'grounded search') are missing, so it sits just below the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	'Direct Google Gemini bridge … without the OpenCode layer' carves a clear niche distinct from sibling x-omo/x-research skills, with only minor overlap risk against other model-bridge skills, matching 'mostly distinct' rather than the fully-distinct 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: quangtran88/x-skills
Path: skills/x-gemini/SKILL.md
Commit: f17a69e

Reviewed: 6 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.