Automated summary
Reviews CloudWatch Logs retention and deletion-candidate findings and records each decision with its rationale in result/claude_review.json, without recomputing any figures.
Strengths
- Explicit checklist covering audit, security, legal hold, incident response, and replay requirements
- Clean separation of duties: LangGraph detects and calculates, Claude only reviews
- Requires rejecting deletion language whenever ownership or recent-event evidence is missing
- Structured, predictable output file (result/claude_review.json) that plugs easily into a pipeline
Limitations
- Read-only by design: makes no AWS calls and independently verifies none of the facts
- Does not recompute machine savings or remediation candidates, so output quality depends entirely on the supplied data
- Says nothing about multi-account or organization-level retention policy
Use it when a batch of FinOps CloudWatch retention findings needs a documented review before log deletions are approved.
Avoid it when you need to detect waste or quantify savings yourself, since that belongs to the detection engine.
Security analysis
SafeThe skill is review-only and does not instruct destructive actions, credential handling, network calls, or execution of shell commands. It explicitly limits Claude to reviewing findings and writing a decision file, and warns not to rerun calculations or change remediation candidates.
No concerns found
How this analysis is madeExamples
Review the CloudWatch retention findings in findings.json and write your decision and rationale for each one to result/claude_review.json.Check whether the deletion candidate for the log group /aws/lambda/checkout has enough ownership and recent-event evidence before we approve it.For each candidate in this batch, explain whether it actually changes retention or only requests more evidence.name: finops-cloudwatch description: Review CloudWatch Logs retention and deletion-candidate findings. user_invocable: false
CloudWatch Logs Review
Review-only authority: LangGraph owns detection and calculations. Claude must not rerun rule arithmetic.
Review Checklist
- Confirm environment, ingestion history, retention, and stored-bytes facts.
- Check audit, security, legal-hold, incident-response, and replay requirements.
- Reject deletion language when ownership or recent-event evidence is missing.
- Explain whether the candidate changes retention or only requests more evidence.
Output Contract
Write each finding decision and rationale to result/claude_review.json. Do not change machine savings or remediation candidates.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/cloudwatch-logs-review-mrx3xwnx' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/cloudwatch-logs-review-mrx3xwnx/download' --output '.skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md.part' && mv '.skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md.part' '.skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md' && test -s '.skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/finops-cloudwatch' && cp -R '.skill-downloads/cloudwatch-logs-review-mrx3xwnx' '.claude/skills/finops-cloudwatch'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/cloudwatch-logs-review-mrx3xwnx'openskills read 'cloudwatch-logs-review-mrx3xwnx'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/cloudwatch-logs-review-mrx3xwnx/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.