snowflake-platform
Build on Snowflake's AI Data Cloud with snow CLI, Cortex AI (COMPLETE, SUMMARIZE, AI_FILTER), Native Apps, and Snowpark. Covers JWT auth, account identifiers, Marketplace publishing. Prevents 11 documented errors. Use when: Snowflake apps, Cortex AI SQL, Native App publishing. Troubleshoot: JWT auth failures, account locator confusion, memory leaks, AI throttling.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill snowflake-platform87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides specific Snowflake capabilities, includes natural trigger terms users would actually search for, has an explicit 'Use when:' clause with both positive triggers and troubleshooting scenarios, and is highly distinctive to the Snowflake ecosystem.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'snow CLI, Cortex AI (COMPLETE, SUMMARIZE, AI_FILTER), Native Apps, Snowpark, JWT auth, account identifiers, Marketplace publishing' and mentions preventing '11 documented errors'. | 3 / 3 |
Completeness | Clearly answers both what (build with snow CLI, Cortex AI, Native Apps, Snowpark) AND when with explicit 'Use when:' clause covering apps, Cortex AI SQL, publishing, and troubleshooting scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Snowflake', 'Cortex AI', 'Native App', 'JWT auth', 'account locator', 'memory leaks', 'AI throttling', 'snow CLI', 'Snowpark', 'Marketplace publishing'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with Snowflake-specific terminology (Cortex AI, Native Apps, snow CLI, account locator) that creates a clear niche unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, actionable skill with excellent executable examples and clear workflows for complex operations like JWT authentication and Marketplace publishing. The Known Issues section is particularly valuable with 11 documented problems and fixes. The main weakness is length - the document tries to cover too much in one file, and some sections could be extracted to separate reference documents for better progressive disclosure.
Suggestions
Extract Cortex AI Functions, Native App Development, and REST API sections into separate reference files (e.g., CORTEX.md, NATIVE-APPS.md, REST-API.md) with brief summaries and links in the main skill
Remove explanatory prose like 'Snowflake Cortex provides LLM capabilities directly in SQL' - Claude knows what Cortex is; jump straight to the function table
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanations (e.g., 'Snowflake Cortex provides LLM capabilities directly in SQL') and could be tightened in places. The billing section and model tables add value but some prose could be trimmed. | 2 / 3 |
Actionability | Excellent executable code examples throughout - SQL queries, bash commands, Python code, and TypeScript snippets are all copy-paste ready. Configuration files show complete, working examples with proper syntax. | 3 / 3 |
Workflow Clarity | Multi-step processes like JWT setup, Native App publishing, and security review workflow have clear numbered sequences with explicit validation steps. The External Access Integration section explicitly warns about the reset-after-deploy issue and includes the critical re-run step. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and a 'When to Use' guide, but the document is quite long (~600 lines) with detailed content that could be split into separate reference files (e.g., Cortex AI functions, Native App development, REST API could each be their own files). | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (823 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.