Agent skill
by iusztinpaul in iusztinpaul/designing-real-world-ai-agents-workshop
Connecting Streamlit apps to Snowflake. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflake --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .claude/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .claude/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflakeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflake --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .agents/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .agents/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflake --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .cursor/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .cursor/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git --path .agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflake --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .gemini/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .gemini/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflakeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .github/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .github/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install iusztinpaul/designing-real-world-ai-agents-workshop connecting-streamlit-to-snowflake --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake .opencode/skills/connecting-streamlit-to-snowflake && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "connecting-streamlit-to-snowflake" agent skill from https://github.com/iusztinpaul/designing-real-world-ai-agents-workshop/tree/main/.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake into .opencode/skills/connecting-streamlit-to-snowflake/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connecting-streamlit-to-snowflake", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
connecting-streamlit-to-snowflakeConnecting Streamlit apps to Snowflake. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
Connecting Streamlit To Snowflake is an agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. Connecting Streamlit apps to Snowflake. Use when setting up database connections, managing secrets, or querying Snowflake from a Streamlit app.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Databases, covering Data warehousing. It works with Streamlit, Snowflake and Python. The repository describes itself as: Hands-on workshop: Build a multi-agent AI system from scratch — Deep Research Agent + Writing Workflow served as MCP servers. Includes code, slides, and video. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit ea4f6e9. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
snowFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
docs.streamlit.ioFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Connecting Streamlit To Snowflake loads about 1.3k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 234 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from iusztinpaul/designing-real-world-ai-agents-workshop at commit ea4f6e9, republished under its Apache-2.0 licence (© iusztinpaul). 234 words, ~1,261 tokens.
.claude/skills/connecting-streamlit-to-snowflake/SKILL.md (or your agent's skills folder).Connect your Streamlit app to Snowflake the right way.
Always use st.connection("snowflake") instead of raw connectors.
import streamlit as st
conn = st.connection("snowflake")
# Query data
df = conn.query("SELECT * FROM my_table LIMIT 100")
st.dataframe(df)Why st.connection:
For apps running in Snowflake, use caller's rights to run queries with the viewer's permissions instead of the app owner's:
conn = st.connection("snowflake", type="snowflake-callers-rights")This is useful when:
Use the built-in ttl parameter to cache query results:
from datetime import timedelta
conn = st.connection("snowflake")
# Cache for 10 minutes
df = conn.query("SELECT * FROM metrics", ttl=timedelta(minutes=10))
# Cache for 1 hour
df = conn.query("SELECT * FROM reference_data", ttl=3600)Store credentials in .streamlit/secrets.toml (never commit this file).
CRITICAL: Derive the account and host values from the user's Snowflake CLI connection config. Run snow connection list and use the exact values. A wrong account will redirect to the wrong login page.
# .streamlit/secrets.toml
[connections.snowflake]
account = "ORGNAME-ACCTNAME" # from `snow connection list`
host = "myaccount.snowflakecomputing.com" # from `snow connection list` (include if present)
user = "your_user"
authenticator = "externalbrowser"
warehouse = "your_warehouse"
database = "your_database"
schema = "your_schema"Add to .gitignore:
.streamlit/secrets.tomlUse parameters to prevent SQL injection:
conn = st.connection("snowflake")
# Safe: parameterized
df = conn.query(
"SELECT * FROM users WHERE region = :region",
params={"region": selected_region}
)
# UNSAFE: string formatting - don't do this
# df = conn.query(f"SELECT * FROM users WHERE region = '{selected_region}'")Use the session for write operations:
conn = st.connection("snowflake")
session = conn.session()
# Write a dataframe
session.write_pandas(df, "MY_TABLE", auto_create_table=True)
# Execute statements
session.sql("INSERT INTO logs VALUES (:ts, :msg)", params={...}).collect()Define multiple connections in secrets:
# .streamlit/secrets.toml
[connections.snowflake]
account = "prod_account"
# ... prod credentials
[connections.snowflake_staging]
account = "staging_account"
# ... staging credentialsprod_conn = st.connection("snowflake")
staging_conn = st.connection("snowflake_staging")Build a chat interface using Snowflake Cortex LLMs:
import streamlit as st
from snowflake.cortex import complete
st.set_page_config(page_title="AI Assistant", page_icon=":sparkles:")
if "messages" not in st.session_state:
st.session_state.messages = []
for msg in st.session_state.messages:
with st.chat_message(msg["role"]):
st.write(msg["content"])
if prompt := st.chat_input("Ask anything"):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.write(prompt)
with st.chat_message("assistant"):
response = st.write_stream(
complete(
"claude-3-5-sonnet",
prompt,
session=st.connection("snowflake").session(),
stream=True,
)
)
st.session_state.messages.append({"role": "assistant", "content": response})See building-streamlit-chat-ui for more chat patterns (avatars, suggestions, history management).
streamlit[snowflake] gates snowflake-connector-python on python_version < "3.12". On Python 3.12+, the connector is silently skipped and you get No module named 'snowflake' at runtime. Always add snowflake-connector-python>=3.3.0 as an explicit dependency in pyproject.toml:
dependencies = [
"snowflake-connector-python>=3.3.0",
"streamlit[snowflake]>=1.54.0",
]© iusztinpaul, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake of iusztinpaul/designing-real-world-ai-agents-workshop.
Open the folder on GitHubat commit ea4f6e9
Connecting Streamlit To Snowflake next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Connecting Streamlit To Snowflake this skilliusztinpaul/designing-real-world-ai-agents-workshop | 512 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Snowflake Developmentsickn33/agentic-awesome-skills | 47k | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Snowflake Developmentalirezarezvani/claude-skills | 28k | — | ~3.2k | Automated safety check: Pass | MIT | |
| Data Warehouse Experimentationrampstackco/claude-skills | 945 | — | ~7.3k | Automated safety check: Pass | MIT | |
| Snowflake Snowpark DbtMindrally/skills | 271 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Chdb SQLvemetric/vemetric | 395 | 1 repos | ~1.2k | Automated safety check: Pass | Apache-2.0 |
sickn33/agentic-awesome-skills
Comprehensive Snowflake development assistant covering SQL best practices, data pipeline design (Dynamic Tables, Streams, Tasks, Snowpipe), Cortex AI functions, Cortex Agents, Snowpark Python, dbt…
alirezarezvani/claude-skills
A skill your agent uses when writing Snowflake SQL, building data pipelines with Dynamic Tables or Streams/Tasks, using Cortex AI functions, creating Cortex Agents, writing Snowpark Python…
rampstackco/claude-skills
Running experiments out of the data warehouse instead of via dedicated experiment platforms.
Mindrally/skills
Best practices for Snowpark Python (DataFrames, UDFs, UDTFs, stored procedures) and dbt with the dbt-snowflake adapter.
vemetric/vemetric
A skill your agent uses when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse…
dbt-labs/ade-bench
A skill your agent uses when authoring or debugging ade-bench tasks that must run on both DuckDB and Snowflake, including shared project migrations, setup patches, and solution patches
iusztinpaul/designing-real-world-ai-agents-workshop
Builds bidirectional Streamlit Custom Components v2 (CCv2) using st.components.v2.component.
iusztinpaul/designing-real-world-ai-agents-workshop
Building chat interfaces in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
iusztinpaul/designing-real-world-ai-agents-workshop
Building dashboards in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
iusztinpaul/designing-real-world-ai-agents-workshop
Building multi-page Streamlit apps. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
iusztinpaul/designing-real-world-ai-agents-workshop
Choosing the right Streamlit selection widget. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
iusztinpaul/designing-real-world-ai-agents-workshop
Creating and customizing Streamlit themes. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.
Categories
Connecting Streamlit apps to Snowflake. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. Connecting Streamlit To Snowflake is an agent skill from iusztinpaul/designing-real-world-ai-agents-workshop. Connecting Streamlit apps to Snowflake.
Connecting Streamlit To Snowflake fits situations like: setting up database connections; managing secrets; querying Snowflake from a Streamlit app.
Run `npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a claude-code`. Or copy the skill folder (.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake in iusztinpaul/designing-real-world-ai-agents-workshop) into .claude/skills/connecting-streamlit-to-snowflake in your project. Claude Code loads it when a task matches its description.
Run `npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a codex`. Or copy the skill folder (.agents/skills/developing-with-streamlit/skills/connecting-streamlit-to-snowflake in iusztinpaul/designing-real-world-ai-agents-workshop) into .agents/skills/connecting-streamlit-to-snowflake in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add iusztinpaul/designing-real-world-ai-agents-workshop --skill connecting-streamlit-to-snowflake -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/connecting-streamlit-to-snowflake, .gemini/skills/connecting-streamlit-to-snowflake, .github/skills/connecting-streamlit-to-snowflake and .opencode/skills/connecting-streamlit-to-snowflake in your project.
Going by SKILL.md and its folder, Connecting Streamlit To Snowflake needs the command-line tools its instructions call (snow). Our summary lists: Python 3.
SKILL.md names 1 domain. As links in the text: docs.streamlit.io. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Connecting Streamlit To Snowflake is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Connecting Streamlit To Snowflake: Snowflake Development (sickn33/agentic-awesome-skills, 47k stars), Snowflake Development (alirezarezvani/claude-skills, 28k stars), Data Warehouse Experimentation (rampstackco/claude-skills, 945 stars) and Snowflake Snowpark Dbt (Mindrally/skills, 271 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
iusztinpaul (a GitHub user) maintains it in iusztinpaul/designing-real-world-ai-agents-workshop, which has 512 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on June 3, 2026.
Source: iusztinpaul/designing-real-world-ai-agents-workshop on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
