cloud-logging — skill for Claude Code: GCP logs
Skill for analyzing Google Cloud Logging and Error Reporting. Processes large JSON logs from GCP and converts them to Apache format for efficient analysis.
Apache-2.0 ★ 151 updated 2026-10-12
/plugin marketplace add gemini-cli-extensions/sre
/plugin install sre-extension@sreWhat cloud-logging does
This skill provides utilities for examining logs, errors, and system health across Google Cloud deployments. The core feature is a bundled script that transforms Cloud Logging JSON exports into Apache Combined Log format, which uses far fewer tokens than ingesting raw files whole.
The skill includes a conversion script, test data, and guidance on filtering logs by severity (ERROR and above are less verbose) and time windows to avoid saturating your context. For long-running operations like gcloud logging read, it recommends using timeout or running in the background with periodic polling of results.
What it helps with
- convert large GCP Cloud Logging JSON without bloating context
- transform Cloud Logging output into Apache log format for analysis
- filter errors by severity and time range to identify root causes
- process Error Reporting data from Google Cloud efficiently
Example prompts for the agent
- Convert logs from
access_logs_raw.jsonto Apache format for inspection - Find all ERROR-level entries in logs from the past 6 hours
- Run
cloudlogging2apachelogs.pyon the export and summarize HTTP status codes
How to install cloud-logging
1Plugin marketplace
/plugin marketplace add gemini-cli-extensions/sre/plugin install sre-extension@sreThis installs the whole sre-extension plugin with all its skills
2Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-logging -a claude-code3Manually: put the files in place
~/.claude/skills/cloud-logging/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cloud-logging/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-logging -a codex2Manually: put the files in place
.agents/skills/cloud-logging/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-logging -a cursor2Manually: put the files in place
.cursor/skills/cloud-logging/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gemini-cli-extensions/sre skills/cloud-logging2Manually: put the files in place
.github/skills/cloud-logging/SKILL.md1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-logging -a gemini-cli2Platform CLI
gemini skills install https://github.com/gemini-cli-extensions/sre --path skills/cloud-loggingManually: put the files in place
.devin/skills/cloud-logging/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cloud-logging
How do I install cloud-logging in Claude Code?
Run /plugin marketplace add gemini-cli-extensions/sre, then /plugin install sre-extension@sre, then npx skills add gemini-cli-extensions/sre --skill cloud-logging -a claude-code. The skill will be ready at ~/.claude/skills/cloud-logging/SKILL.md.
What does cloud-logging do?
It helps you examine Google Cloud logs by converting JSON exports into Apache log format, saving context tokens. Includes a script for conversion, filtering advice by severity level, and time-window constraints to keep queries fast.
Why not just load the entire log file?
Large files quickly fill your context window. Use jq or the bundled script to filter relevant data before analysis.
Source text
SKILL.md · Apache-2.0
---
name: cloud-logging
description: 🐉 Skill for interacting with and analyzing Google Cloud Logging and Error Reporting. Use this when you need to process large JSON logs from GCP or convert them to Apache format for easier analysis.
metadata:
author: Riccardo Carlesso
version: 0.3.0
status: published
---
# Cloud Logging
This skill provides utilities for analyzing logs, errors, and system health across Google Cloud deployments.
* Prioritize Logs with `severity` >= "ERROR" as they tend to be less verbose.
* Constrain logs around the time of investigation (possibly going back a few hours/days to find smoking guns).
## Logs DOs and DONT's
Ingesting Logs into an LMM memory can easily saturate your context.
* [BAD] **DO NOT** ingest big files. Antipattern: `ReadFile path/to/access_logs_raw.json`.
* It's ok to get raw logs, but also use `jq` or scripts to read them without polluting your context window.
* [GOOD] Use simple maniuplation like: `jq -r '.[] | .httpRequest.status'` to get a list of statuses.
* [GOOD] Reduce size with scripts such as `scripts/cloudlogging2apachelogs.py <big_logfile.json>` (provided in the skill)
* [BAD] Do not call **long**-running calls without precautions, eg `gcloud logging read`
* [GOOD] Rather prepend some reasonable `timeout 60 gcloud logging read ...`, or
* [BEST] Use the `run_shell_command` tool with `is_background: true` and poll the results being dumped to file periodically.
## Bundled Scripts
### cloudlogging2apachelogs.py
Converts GCP Cloud Logging JSON exports into a format loosely resembling Apache Combined Log format. This is much more token-efficient for the LLM.
**Usage**:
```bash
python3 scripts/cloudlogging2apachelogs.py path/to/logs.json
```
**Testing**:
You can verify the script works by running its test:
```bash
python3 scripts/cloudlogging2apachelogs_test.py
```
## Bundled Assets
* `assets/sample_logs.json`: A small sample of GCP Cloud Logging JSON for testing conversion scripts.
© Riccardo Carlesso · Apache-2.0 · gemini-cli-extensions/sre