antigravity-workflows

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

1.68x

Quality

45%

Does it follow best practices?

Impact

91%

1.68x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/antigravity-antigravity-workflows/SKILL.md

Quality

Discovery

32%

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 names a clear orchestration role and lists four workflow domains, giving it moderate specificity and distinctiveness. However, it lacks an explicit 'Use when...' clause, relies on internal jargon ('Antigravity skills'), and doesn't describe concrete actions within each workflow type. The breadth of coverage across four domains without deeper detail makes it harder for Claude to confidently select this skill over more targeted alternatives.

Suggestions

Add an explicit 'Use when...' clause listing trigger scenarios, e.g., 'Use when the user wants to build a SaaS MVP end-to-end, run a security audit, create an AI agent, or perform browser-based QA testing.'

Replace internal jargon like 'Antigravity skills' with user-facing language, and add natural trigger terms users would say (e.g., 'build an app', 'penetration test', 'automated testing', 'launch a product').

List 2-3 concrete actions per workflow type to increase specificity, e.g., 'Coordinates project scaffolding, deployment pipelines, and iterative feature builds for SaaS MVPs.'

Dimension	Reasoning	Score
Specificity	Names the domain (orchestrating Antigravity skills) and lists several workflow types (SaaS MVP delivery, security audits, AI agent builds, browser QA), but doesn't describe concrete actions beyond 'orchestrate' and 'guided workflows' — it's more of a category listing than specific capabilities.	2 / 3
Completeness	Describes what it does (orchestrates skills through guided workflows) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' itself is also somewhat vague, placing this at 1.	1 / 3
Trigger Term Quality	Includes some relevant keywords like 'SaaS MVP', 'security audits', 'AI agent builds', and 'browser QA' that users might mention, but 'orchestrate multiple Antigravity skills' is internal jargon unlikely to appear in user requests. Missing natural variations like 'build an app', 'test my site', 'pen test', etc.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Antigravity skills' and the specific workflow types (SaaS MVP, security audits, AI agent builds, browser QA) provide some distinctiveness, but the broad scope covering four different domains could overlap with individual skills handling each of those areas separately.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

This is a well-structured orchestration skill with good progressive disclosure and clear routing logic, but it lacks concrete, actionable detail about what actually happens during workflow execution. The copy-paste prompts section is verbose and repetitive, and the workflow steps would benefit from explicit validation criteria and error handling guidance rather than abstract instructions.

Suggestions

Replace or reduce the 5 copy-paste prompts to 1-2 examples, as they are nearly identical in structure and consume tokens without adding value.

Add concrete examples of what 'completion criteria' look like for at least one workflow step (e.g., 'Step 3 is complete when all tests pass and the deployment URL returns 200').

Include a brief error recovery instruction, e.g., 'If a step fails: diagnose using the invoked skill's output, fix, and re-run the step before proceeding.'

Dimension	Reasoning	Score
Conciseness	The skill is reasonably concise but includes some unnecessary sections like 'Copy-Paste Prompts' (5 examples that are largely redundant) and 'Limitations' that explain obvious things. The 'When to Use This Skill' section partially restates what the description already conveys.	2 / 3
Actionability	The workflow steps in 'How to Run This Skill' provide a clear sequence but remain abstract—there are no concrete commands, code, or executable examples. The routing table is helpful but the actual execution details are deferred entirely to external files (docs/WORKFLOWS.md, data/workflows.json) without showing what those contain.	2 / 3
Workflow Clarity	The 5-step process is clearly sequenced and includes verification ('Verify completion criteria before moving to next step'), but the validation checkpoints are vague rather than explicit. There's no concrete definition of what 'completion criteria' means for each step, and no error recovery/feedback loop if a step fails.	2 / 3
Progressive Disclosure	The skill appropriately serves as an overview/orchestration layer, pointing to docs/WORKFLOWS.md and data/workflows.json as one-level-deep references. Related skills are clearly listed. The structure is well-organized with clear section headers for easy navigation.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: boisenoise/skills-collections
Commit: 636b862

Reviewed: 4 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.