← All skills
gcp-spark
79 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a data skill usually connects to databases or online services with your credentials.
By GoogleCloudPlatform/data-agent-kit-plugin (GitHub) · data · 249 stars · scanned at commit e70c87b
Authors, optimizes, and runs PySpark and Spark code on Google Cloud Managed Spark
(Dataproc Serverless, clusters, and Spark Connect).
Use when:
- Authoring or running Spark/PySpark notebooks in any kernel (Local Kernel with
spark-remote templates, Remote Spark / Remote Kernel, ManagedSparkSession, Spark Connect).
- Querying, transforming, or writing data with PySpark or Spark SQL, including
Apache / BigLake Iceberg, BigQuery, GCS, Spanner, Cloud SQL, AlloyDB,
Amazon S3, or Azure Blob Storage / …
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 5 places.
Show 2 more
Connects to the internet
This is disclosed by the author in the skill's SKILL.md or README. Expected for a data skill.
Found in 15 places.
Show 12 more
- skills/gcp-spark/references/aws_s3.md, line 92
with urllib.request.urlopen(req) as response: - skills/gcp-spark/references/azure_storage.md, line 59
using the pre-installed `google.auth` + `urllib.request` REST API (zero extra - skills/gcp-spark/references/azure_storage.md, line 68
import urllib.request - skills/gcp-spark/references/azure_storage.md, line 87
req = urllib.request.Request( - skills/gcp-spark/references/azure_storage.md, line 91
with urllib.request.urlopen(req) as response: - skills/gcp-spark/references/jdbc_cloudsql.md, line 99
Fetch the secret via the pre-installed `google.auth` and `urllib.request` - skills/gcp-spark/references/jdbc_cloudsql.md, line 108
import urllib.request - skills/gcp-spark/references/jdbc_cloudsql.md, line 121
req = urllib.request.Request( - skills/gcp-spark/references/jdbc_cloudsql.md, line 124
with urllib.request.urlopen(req) as resp: - skills/gcp-spark/references/jdbc_cloudsql.md, line 264
import urllib.request - skills/gcp-spark/references/jdbc_cloudsql.md, line 269
req = urllib.request.Request( - skills/gcp-spark/references/jdbc_cloudsql.md, line 273
with urllib.request.urlopen(req, timeout=5) as resp:
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed.
Found in 35 places.
Show 17 more
- .claude-plugin/mcp.json, line 11
"command": "node", - .claude-plugin/mcp.json, line 19
"command": "node", - .claude-plugin/mcp.json, line 30
"command": "node", - .claude-plugin/mcp.json, line 41
"command": "node", - .claude-plugin/mcp.json, line 52
"command": "node", - .claude-plugin/mcp.json, line 63
"command": "node", - .claude-plugin/mcp.json, line 74
"command": "node", - .claude-plugin/mcp.json, line 85
"command": "node", - .claude-plugin/mcp.json, line 96
"command": "node", - .claude-plugin/mcp.json, line 107
"command": "node", - .claude-plugin/mcp.json, line 118
"command": "node", - .claude-plugin/mcp.json, line 129
"command": "node", - .claude-plugin/mcp.json, line 140
"command": "node", - .claude-plugin/mcp.json, line 151
"command": "node", - .codex-plugin/hooks.json, line 9
"command": "node \"${PLUGIN_ROOT}/.agents/hooks/telemetry_hook.js\" --agent_name codex --install_source data-agent-kit-plugin ; exit 0", - hooks.json, line 6
"command": "node skills/dak-setup/scripts/dak-setup.js sync" - hooks.json, line 17
"command": "node .agents/hooks/telemetry_hook.js --agent_name antigravity --install_source data-agent-kit-plugin || exit 0",
and 15 more places
Safer alternatives
Low-risk skills in the same category (data) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'gcp-spark' ] || [ -L ~/.agents/skills/'gcp-spark' ]; then echo 'A skill folder named gcp-spark already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/GoogleCloudPlatform/data-agent-kit-plugin' "$d" && git -C "$d" checkout --quiet 'e70c87ba66c5731062af13103626b8703b8bf42d' -- 'skills/gcp-spark' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/gcp-spark' ~/.agents/skills/'gcp-spark' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'gcp-spark' ~/.claude/skills/'gcp-spark' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for GoogleCloudPlatform/data-agent-kit-plugin shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/GoogleCloudPlatform/data-agent-kit-plugin/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | e70c87b | 79 |
| 2026-11-08 | 6f4818a | 95 |
| 2026-11-06 | 6f4818a | 42 |