antigravity-workflows

Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.

1.68x

Quality

—

Does it follow best practices?

Impact

91%

1.68x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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, lean, and gives a concrete sequenced procedure with an explicit verification checkpoint. Its main weaknesses are dead references to unbundled source-of-truth files, a missing failure-recovery loop, and redundant copy-paste prompt blocks.

Suggestions

Bundle the referenced source-of-truth files (docs/WORKFLOWS.md and data/workflows.json) or remove the dead references so the signaled navigation actually resolves.

Add an explicit failure-recovery feedback loop (e.g., "If completion criteria are not met, diagnose, re-invoke the relevant skill, then re-verify before proceeding") and a per-workflow completion checklist.

Condense the five near-identical copy-paste prompt blocks to one or two representative examples to recover token budget.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not over-explain concepts Claude already knows, but the five near-identical "Copy-Paste Prompts" blocks add redundant tokens that could be condensed to one or two examples.	2 / 3
Actionability	It provides concrete routing mappings and a numbered run procedure, but the actual per-step completion criteria are deferred to external workflow files rather than specified in the skill itself.	2 / 3
Workflow Clarity	The 5-step sequence includes an explicit checkpoint ("Verify completion criteria before moving to next step"), but there is no error-recovery feedback loop or per-workflow checklist, which anchor 3 and the scoring notes expect for complex multi-phase processes.	2 / 3
Progressive Disclosure	Sections are well-organized and references are clearly signaled ("Read workflows in this order: 1. docs/WORKFLOWS.md 2. data/workflows.json"), but those referenced source-of-truth files are not present in the bundle, leaving the one-level-deep navigation dead.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 concrete and clearly scoped to workflow orchestration across four named scenarios, but it omits an explicit "Use when..." trigger clause and leans on a single action verb with some jargon. It is distinguishable but overlaps with the underlying specialized skills it routes to.

Suggestions

Add an explicit "Use when..." trigger clause naming the scenarios (e.g., "Use when the user wants to ship a SaaS MVP, run a web security audit, build an AI agent system, or set up browser QA") to raise completeness and trigger-term quality.

Lead with multiple concrete action verbs (e.g., "Routes, sequences, and verifies multi-skill workflows") instead of the single verb "orchestrate" to surface distinct capabilities for specificity.

Disambiguate the orchestrator from the specialized skills it routes to (e.g., "Use when a request spans multiple skills; for a standalone task, invoke the dedicated skill") to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description names the domain and a concrete action ("Orchestrate multiple Antigravity skills through guided workflows") plus four scenarios, but relies on a single action verb rather than listing multiple distinct concrete actions as anchor 3 requires.	2 / 3
Completeness	The "what" is explicit, but the "when" is only implied through the listed scenarios; there is no "Use when..." clause, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Scenario terms like "SaaS MVP", "security audits", "AI agent", and "browser QA" are natural, but they are fronted by jargon ("orchestrate...guided workflows") and lack common trigger variations or a "Use when" phrasing.	2 / 3
Distinctiveness Conflict Risk	The orchestrator framing is a distinct niche, but the four scenario triggers (security audit, AI agent build, browser QA) overlap with the specialized skills it routes to, creating conflict risk.	2 / 3
	Total	8 / 12 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: boisenoise/skills-collections
Commit: f36337d

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.