antigravity-workflows
Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.
59
41%
Does it follow best practices?
Impact
91%
1.68xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-antigravity-workflows/SKILL.mdQuality
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 identifies a clear orchestration role across multiple workflow types, which gives it some identity, but it lacks concrete action details and has no explicit trigger guidance ('Use when...'). The language leans on internal terminology ('Antigravity skills') that users wouldn't naturally use, and the breadth of four distinct domains without specifics makes it hard 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 full SaaS product, 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 such as 'build an app', 'penetration test', 'end-to-end testing', 'create a chatbot'.
List specific concrete actions for each workflow type, e.g., 'Generates project scaffolding, runs OWASP security scans, configures AI agent pipelines, and executes browser automation tests.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a domain (orchestrating Antigravity skills) and lists several workflow types (SaaS MVP delivery, security audits, AI agent builds, browser QA), but the actions are described at a high level ('orchestrate', 'guided workflows') rather than listing concrete specific actions performed within those workflows. | 2 / 3 |
Completeness | It describes what the skill does (orchestrates workflows) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause should cap completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'SaaS MVP', 'security audits', 'AI agent builds', 'browser QA' that users might mention, but 'orchestrate multiple Antigravity skills' is internal jargon. Missing common natural variations users would say like 'build an app', 'test my site', 'pen test', 'create an agent'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Antigravity skills' and specific workflow types (SaaS MVP delivery, security audits, AI agent builds, browser QA) provides 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
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable orchestration framework with clear routing logic and a defined execution sequence, but it lacks the concrete, actionable detail needed to be truly effective. The workflow steps are abstract ('invoke recommended skills,' 'verify completion criteria') without specifying what those look like in practice. The copy-paste prompts add bulk without adding value, and the referenced external files cannot be verified.
Suggestions
Add concrete examples of what 'verify completion criteria' looks like for at least one workflow (e.g., for ship-saas-mvp: 'Verify deployment URL returns 200, run smoke test suite, confirm CI pipeline green').
Replace or reduce the 5 copy-paste prompts to 1-2 examples and use the saved space for a concrete walkthrough of one workflow execution showing actual skill invocations and expected artifacts.
Add explicit failure/retry guidance: what should happen when a step's completion criteria aren't met, with specific recovery actions.
Provide the referenced `docs/WORKFLOWS.md` and `data/workflows.json` bundle files, or inline the essential workflow metadata if those files don't exist.
| 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 Claude would already understand. The 'When to Use This Skill' section also restates what the description already conveys. | 2 / 3 |
Actionability | The workflow steps in 'How to Run This Skill' provide a reasonable sequence but remain abstract — there are no concrete commands, executable code, or specific examples of what 'invoke recommended skills' or 'verify completion criteria' actually look like. The routing table is helpful but the actual execution guidance is vague. | 2 / 3 |
Workflow Clarity | There is a clear 5-step sequence with some validation language ('verify completion criteria before moving to next step'), but the validation checkpoints are implicit rather than explicit. There's no concrete feedback loop for what happens when a step fails, and no specific criteria for what 'completion' means at each step. | 2 / 3 |
Progressive Disclosure | The skill references `docs/WORKFLOWS.md` and `data/workflows.json` as external sources, which is good progressive disclosure structure. However, no bundle files are provided, so we cannot verify these references exist. The skill itself is somewhat monolithic with sections that could be trimmed rather than split out. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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
e41e34a
- Reviewed
Table of Contents
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.