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-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 domain (multi-skill orchestration for specific project types) but suffers from lack of explicit trigger guidance and overly abstract action language. It uses internal jargon ('Antigravity skills') that users wouldn't naturally say, and the concrete capabilities within each workflow type are not enumerated.
Suggestions
Add an explicit 'Use when...' clause listing trigger scenarios, e.g., 'Use when the user wants to build a SaaS product from scratch, 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', 'MVP', 'penetration test', 'automated testing', 'web scraping QA'.
List specific concrete actions for each workflow type, e.g., 'Scaffolds project structure, generates boilerplate code, configures CI/CD pipelines, runs vulnerability scans, and automates browser test suites.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (SaaS MVP delivery, security audits, AI agent builds, browser QA) and the general action (orchestrate multiple skills through guided workflows), but doesn't list concrete actions like 'generate project scaffolding', 'run security scans', or 'execute browser tests'. | 2 / 3 |
Completeness | Describes what it does (orchestrate skills through guided workflows) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also somewhat vague, warranting a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'SaaS MVP', 'security audits', 'AI agent builds', and 'browser QA', but these are fairly specific product terms. Missing common natural user phrases like 'build an app', 'test my site', 'check security', or 'create a project'. 'Antigravity skills' is internal jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Antigravity skills' and specific workflow types (SaaS MVP, security audits, AI agent builds, browser QA) provides some distinctiveness, but 'orchestrate multiple skills through guided workflows' is broad enough to potentially overlap with other orchestration or project management skills. | 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 stays at a high level of abstraction without concrete examples of what execution actually looks like. The workflow steps lack explicit validation criteria and error recovery paths, and the referenced external files (WORKFLOWS.md, workflows.json) are not available to verify. Several sections (limitations, when-to-use, copy-paste prompts) add bulk without proportional value.
Suggestions
Add a concrete worked example showing one workflow (e.g., 'ship-saas-mvp') executed end-to-end with specific step names, artifacts produced, and validation checks at each stage.
Define explicit completion criteria for each workflow step (e.g., 'Step passes when: deployment URL returns 200, test suite passes with 0 failures') rather than the abstract 'verify completion criteria'.
Add an error recovery/feedback loop: what should happen when a step fails validation? Currently the workflow is linear with no branching for failures.
Trim or remove the 'When to Use This Skill' and 'Limitations' sections, which mostly state things Claude can infer, and consolidate the five nearly-identical copy-paste prompts into a single parameterized template.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary sections like 'When to Use This Skill' with bullet points that largely restate the description, and the 'Copy-Paste Prompts' section is repetitive. The 'Limitations' section states obvious things Claude would already know. | 2 / 3 |
Actionability | The workflow steps (identify outcome, propose workflows, execute step-by-step) provide a reasonable framework but remain abstract—there are no concrete examples of what 'invoke recommended skills' or 'verify completion criteria' actually look like in practice. The routing table is helpful but the actual execution guidance is vague. | 2 / 3 |
Workflow Clarity | The 5-step execution process is clearly sequenced and includes a verification checkpoint ('verify completion criteria before moving to next step'), but the validation is implicit rather than explicit—there's no concrete definition of what completion criteria look like, no error recovery/feedback loop if a step fails, and no examples of artifact validation. | 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 these references are unverifiable, and the skill itself contains content (like the full copy-paste prompts section) that could be trimmed or externalized. | 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
- sickn33/antigravity-awesome-skills
- Commit
76aea27
- 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.