streamlit-snowflake
Build and deploy Streamlit apps natively in Snowflake. Covers snowflake.yml scaffolding, Snowpark sessions, multi-page structure, Marketplace publishing as Native Apps, and caller's rights connections (v1.53.0+). Use when building data apps on Snowflake, deploying SiS, fixing package channel errors, authentication issues, cache key bugs, or path resolution errors.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill streamlit-snowflake91
Does it follow best practices?
Validation 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 technical capabilities, includes natural trigger terms for both feature requests and troubleshooting scenarios, explicitly states when to use it, and targets a clear niche (Streamlit-in-Snowflake) that distinguishes it from related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'snowflake.yml scaffolding, Snowpark sessions, multi-page structure, Marketplace publishing as Native Apps, and caller's rights connections'. Also mentions specific version (v1.53.0+) and concrete error types. | 3 / 3 |
Completeness | Clearly answers both what ('Build and deploy Streamlit apps natively in Snowflake' with specific capabilities) AND when (explicit 'Use when...' clause covering building, deploying, and fixing specific error types). | 3 / 3 |
Trigger Term Quality | Includes natural terms users would say: 'Streamlit apps', 'Snowflake', 'data apps', 'SiS', 'package channel errors', 'authentication issues', 'cache key bugs', 'path resolution errors'. Good coverage of both feature terms and common problem terms. | 3 / 3 |
Distinctiveness Conflict Risk | Very clear niche: Streamlit-in-Snowflake (SiS) is a specific technology combination. Terms like 'snowflake.yml', 'Snowpark sessions', 'Native Apps', and 'SiS' are highly distinctive and unlikely to conflict with general Streamlit or general Snowflake skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-organized skill with excellent actionability and clear workflow structure. The content provides executable code examples, comprehensive error prevention guidance, and appropriate progressive disclosure to external references. Minor verbosity in explanatory sections (security model, runtime environments) could be tightened without losing clarity.
Suggestions
Condense the Security Model section - Claude understands privilege models; focus on the code patterns and when to use each rather than explaining what owner's/caller's rights mean
Consider moving the detailed Runtime Environments comparison to a separate reference file, keeping only the key decision point (Warehouse vs Container) and configuration snippet in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally efficient but includes some unnecessary explanations (e.g., explaining what owner's rights vs caller's rights means in detail, verbose security implications sections). The error prevention table is comprehensive but could be more condensed. | 2 / 3 |
Actionability | Provides fully executable code examples throughout - Snowpark session connections, caching patterns, SQL queries, bash deployment commands, and YAML configurations are all copy-paste ready with specific version numbers and parameters. | 3 / 3 |
Workflow Clarity | Clear numbered sequences for initialization and deployment (1. Initialize, 2. Configure, 3. Deploy). The error prevention table serves as validation guidance, and the 'When to Use' section provides clear decision boundaries. | 3 / 3 |
Progressive Disclosure | Well-structured with Quick Start at top, detailed patterns in middle, and references to external files (references/authentication.md, references/ci-cd.md, templates-native-app/README.md) for advanced topics. One-level-deep references are clearly signaled. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | 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.