antigravity-cli

Operate the Antigravity CLI (agy): plugins, auth, sandbox.

Quality

64%

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 ./optional-skills/autonomous-ai-agents/antigravity-cli/SKILL.md

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete executable commands and a clean, well-sectioned structure backed by one well-signaled reference, but it carries some internal repetition and lacks explicit validation feedback loops for its riskier batch/destructive delegation patterns.

Suggestions

De-duplicate the 'agy -p' plain-text/no-JSON caveat and the worktree fan-out description so each point lives in one place (e.g. keep it only in 'Output + bounding caveat' and reference it from 'Pitfalls').

Add an explicit validate->fix->retry loop for the destructive/batch delegation patterns (e.g. after a background '--dangerously-skip-permissions' run, show how to inspect the session log and re-run on failure).

Tighten the Quick Reference flags list by grouping related flags (print/timeout, sandbox/permissions) to cut tokens without losing the lookup value.

Dimension	Reasoning	Score
Conciseness	The body is dense and operator-focused with no concept padding, but it repeats itself in places (the 'agy -p' plain-text/no-JSON caveat appears in both 'Output + bounding caveat' and 'Pitfalls', and the worktree fan-out is described twice), so it could be tightened rather than being fully lean.	2 / 3
Actionability	It gives fully executable, copy-paste-ready examples with exact commands, flags, and paths (e.g. 'terminal(command="agy -p '... ' --model '...'" ...)', '~/.gemini/antigravity-cli/settings.json'), matching the level-3 anchor for concrete, complete guidance.	3 / 3
Workflow Clarity	The install workflow has a clear numbered Verification checklist with explicit read/terminal steps, but the destructive/batch delegation patterns (background bounded runs and parallel worktree fan-out under '--dangerously-skip-permissions') lack explicit validate-fix-retry checkpoints, which the guidelines cap at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned and offloads detail to a single real one-level-deep reference ('references/cli-docs.md', confirmed present) clearly signaled under 'Support files' with a description of its contents, matching the level-3 anchor.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 clearly identifies a distinct, named target and its capability areas, but it lacks any explicit 'Use when...' trigger guidance, which caps both completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when installing or running the agy CLI, debugging Antigravity auth/sandbox, or managing agy plugins').

Replace the single generic verb 'Operate' with multiple distinct concrete actions (e.g. 'Install, update, run one-shot prompts, and manage plugins/auth/sandbox for the Antigravity CLI (agy)').

Include common natural variations of the trigger terms (e.g. 'Antigravity', 'agy', 'Gemini CLI') to broaden recall.

Dimension	Reasoning	Score
Specificity	It names the domain ('Antigravity CLI (agy)') and three concrete capability areas ('plugins, auth, sandbox'), but summarizes them under a single generic verb 'Operate' rather than listing multiple distinct concrete actions as a level-3 example would.	2 / 3
Completeness	The 'what' is stated ('Operate the Antigravity CLI (agy): plugins, auth, sandbox') but the 'when' is entirely absent with no explicit trigger guidance, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	It includes relevant keywords a user might say ('Antigravity CLI', 'agy', 'plugins', 'auth', 'sandbox'), but offers no 'Use when...' trigger phrasing and misses common natural variations, matching the level-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The named product target ('Antigravity CLI (agy)') gives it a clear niche with distinct triggers, making it unlikely to fire for the wrong skill despite the generic capability words.	3 / 3
	Total	9 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/autonomous-ai-agents/antigravity-cli/SKILL.md
Commit: c4f5a45

Reviewed: about 15 hours 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.