Claude Code skills for bootstrapping, validating, and fixing Snowglobe agents. Bundles four skills that auto-trigger by user intent: bootstrap-snowglobe-agent, snowglobe-agent-description, validate-snowglobe-agent, and analyze-fix-snowglobe-agent.
Analyzes a target snowglobe_agent.py for validation errors and example inconsistencies, then fixes them. Trigger when the user says "fix my agent", "analyze my agent", "clean up my snowglobe agent", "fix the tool defs", or similar requests to audit and repair a Snowglobe agent file.
End-to-end onboarding for a user who has never used Snowglobe before. Installs the `snowglobe` pip package, authenticates the CLI (skipping if already authed), registers the agent (POST to the Snowglobe API for new agents, or `snowglobe-connect init` to wire up existing ones), then creates the starter wrapper file via `init`. Scans the project to draft a chatbot description, augments the wrapper with `@snowglobe_tool` decorated functions, a `tool_defs()` function, `TOOLS_MAP`, and a tool-call loop in `completion()`, verifies with `snowglobe-connect test`, starts the wrapper with `snowglobe-connect start`, and hands the user a dashboard deep link. Trigger when the user says "set up snowglobe for my project", "bootstrap my snowglobe agent", "get started with snowglobe", "create a snowglobe agent", "connect my chatbot to snowglobe", "scaffold my agent", "add tools to my agent", or any similar bootstrap / onboarding request.
Writes effective agent descriptions for Snowglobe, the simulation platform that stress-tests AI agents by generating synthetic user interactions. Use this skill whenever the user wants to write, improve, or generate a Snowglobe chatbot description — including when they say things like "write a description for Snowglobe", "help me set up simulation for my agent", "write a chatbot description for testing", or "I want to simulate [agent name] in Snowglobe". Also trigger when the user is configuring a chatbot_wrapper.py or agents.json for Snowglobe and needs a description field.
Validates a target snowglobe_agent.py by running a suite of code-based validation scripts. Trigger when the user says "validate my agent", "run validation on my agent", "check my snowglobe agent", or similar requests to verify a Snowglobe agent file is correct.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin that bundles four skills for working with Snowglobe, the simulation platform that stress-tests AI agents with synthetic users.
The skills auto-trigger by intent — you don't run them as slash commands. Just ask Claude what you want to do (e.g. "set up snowglobe for my project") and the right skill activates.
| Skill | What it does | Trigger phrases |
|---|---|---|
bootstrap-snowglobe-agent | End-to-end onboarding: pip-installs snowglobe, runs snowglobe-connect auth, scans your code, drafts a chatbot description, scaffolds the wrapper file with @snowglobe_tool and tool_defs(), builds .snowglobe/agents.json, runs snowglobe-connect test, prompts you to snowglobe-connect start, and deep-links you to the dashboard | "bootstrap my snowglobe agent", "set up snowglobe for this project", "connect my chatbot to snowglobe" |
snowglobe-agent-description | Writes an effective Snowglobe chatbot description from your code | "write a chatbot description for snowglobe", "describe my agent for simulation" |
validate-snowglobe-agent | Runs the validation suite against your snowglobe_agent.py and reports issues | "validate my snowglobe agent", "check my agent" |
analyze-fix-snowglobe-agent | Runs validation + auto-fixes errors in place | "fix my snowglobe agent", "clean up my agent" |
In Claude Code:
/plugin marketplace add guardrails-ai/snowglobe-skills
/plugin install snowglobe-skills@snowglobe-skills
(Replace guardrails-ai/snowglobe-skills with your fork if you're using a fork.)
To update later:
/plugin marketplace update snowglobe-skills
After install, just ask. Examples:
bootstrap-snowglobe-agent runs the full bootstrap.validate-snowglobe-agent runs the validators.analyze-fix-snowglobe-agent repairs the file.snowglobe-agent-description drafts it from your code.Each skill is documented in its SKILL.md under plugins/snowglobe-skills/skills/.
snowglobe-skills/
├── .claude-plugin/
│ └── marketplace.json ← marketplace catalog
├── plugins/
│ └── snowglobe-skills/
│ ├── .claude-plugin/
│ │ └── plugin.json ← plugin manifest
│ └── skills/
│ ├── bootstrap-snowglobe-agent/
│ ├── snowglobe-agent-description/
│ ├── validate-snowglobe-agent/
│ └── analyze-fix-snowglobe-agent/
└── README.md
Apache-2.0 — see LICENSE.
npx claudepluginhub guardrails-ai/snowglobe-skills --plugin snowglobe-skillsComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development