secops-setup-antigravity
Helps the user configure the Google SecOps Remote MCP Server for Antigravity. Use this when the user asks to "set up" or "configure" the security tools for Antigravity.
75
62%
Does it follow best practices?
Impact
100%
1.53xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./extensions/google-secops/skills/setup-antigravity/SKILL.mdQuality
Discovery
75%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 adequately identifies a clear niche (Google SecOps MCP Server configuration for Antigravity) and provides explicit 'Use when' guidance, which is good. However, it lacks specificity about what concrete configuration actions are performed and could include more natural trigger term variations that users might use when seeking this skill.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Sets up API credentials, configures endpoints, validates connectivity for the Google SecOps Remote MCP Server'.
Expand trigger terms to include more natural variations users might say, such as 'install', 'connect', 'Google SecOps', 'MCP server setup', 'SIEM configuration', or 'security integration'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Google SecOps Remote MCP Server for Antigravity) and a general action (configure), but doesn't list specific concrete actions like 'set API keys, define endpoints, configure authentication' etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (configure the Google SecOps Remote MCP Server for Antigravity) and 'when' (when the user asks to 'set up' or 'configure' the security tools for Antigravity) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural trigger terms like 'set up', 'configure', 'security tools', and 'Antigravity', but misses common variations users might say such as 'install', 'connect', 'Google SecOps', 'MCP server', 'SOAR', or 'SIEM'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Google SecOps Remote MCP Server for Antigravity specifically, making it highly unlikely to conflict with other skills. The combination of product names creates a distinct trigger profile. | 3 / 3 |
Total | 10 / 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 structured walkthrough for configuring Google SecOps for Antigravity with clear prerequisite checks and a logical sequence. However, it lacks concrete examples of the JSON config structure, has no validation/rollback steps for the destructive config merge operation, and describes the core merge logic abstractly rather than with executable specifics.
Suggestions
Add an example of the expected mcp_config.json structure (before and after merge) so Claude knows exactly what the output should look like.
Add an explicit validation step after writing the merged config, such as reading back the file and confirming the JSON is valid and all expected servers are present.
Include a backup step before modifying the existing config file (e.g., 'cp ~/.gemini/antigravity/mcp_config.json ~/.gemini/antigravity/mcp_config.json.bak').
Remove the 'You are an expert in...' line — this is unnecessary framing that wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary framing ('You are an expert in...') and slightly verbose phrasing in places. The 'Ask:' prompts and option descriptions could be tighter, but overall it doesn't over-explain concepts Claude already knows. | 2 / 3 |
Actionability | Provides some concrete commands (gcloud auth) and specific file paths, but the core configuration workflow relies on reading external template files and .env files without showing their contents inline. The merge logic is described abstractly rather than with executable code or concrete examples of the JSON structure. | 2 / 3 |
Workflow Clarity | Steps are listed in a reasonable sequence, but the merge operation (step 4) involves a destructive write to an existing config file with no explicit validation checkpoint or rollback guidance. The instruction to 'not overwrite other servers' is mentioned but no verification step confirms the merge was correct before writing. Missing feedback loop for a potentially destructive file operation caps this at 2. | 2 / 3 |
Progressive Disclosure | References external files (mcp_config.template.json, .env.example) which is appropriate, but doesn't clearly signal what those files contain or provide navigation hints. The skill is a reasonable length but the structure could better separate the prerequisite checks from the main workflow. | 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
- google/mcp-security
- Commit
9774ce8
- 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.