analyzing-release-readiness

An agent skill by aws, from aws/agent-toolkit-for-aws. Tags: code-review, github, gitlab, release-management, review.

What it does

Trigger a pre-merge release readiness review on a GitHub PR, GitLab MR, or local branch. Use when the user wants to analyze code changes for risk, correctness, and potential rollback issues before merging. Trigger words include release readiness, analyze PR, analyze MR, review PR, risk analysis, pre-merge, safe to ship, ready to merge, ready to commit, any risks, before merging, validate changes, release management.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add aws/agent-toolkit-for-aws --skill analyzing-release-readiness

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/aws/agent-toolkit-for-aws
cp -r agent-toolkit-for-aws/plugins/aws-agents-for-devsecops/skills/analyzing-release-readiness ~/.claude/skills/analyzing-release-readiness

Safety box score

Grade C, moderate risk: 39 of 100 risk points, rated 2026-10-20. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill triggers an AWS-hosted release-readiness review and, in the local-repo flow, can create branches, commit all staged changes, push to `origin`, and later delete the review branch. The main risks are remote exposure of repository data, accidental inclusion of secrets, and destructive cleanup of local/remote branch state as part of the workflow.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	1 (low)	It drives shell-oriented workflows (`git ...`, `aws ...`) but does not ship binaries, eval code, or a native script; the commands are bounded to review-related operations.
Network access	2 (moderate)	It sends repository identifiers and branch metadata to the AWS DevOps Agent (`create_release_readiness_review`) and can use AWS CLI fallback calls, so review data leaves the machine.
Filesystem reach	2 (moderate)	The local flow mutates the working tree with `git stash`, `git checkout -b`, `git add -A`, `git commit`, and cleanup commands that can delete the review branch and restore stashed changes.
Secrets & credentials	2 (moderate)	It warns on filename patterns like `\.(env\|pem\|key\|p12\|pfx\|credentials\|secret)` but still runs `git add -A`, so other sensitive files can be staged and pushed.
Privilege & persistence	0 (none)	No `sudo`, service registration, shell startup edits, or global OS/package changes are requested.
Instruction hijack surface	0 (none)	I found no hidden instructions, prompt overrides, or external instruction fetching beyond the skill's own workflow text.
Irreversible actions	3 (high)	The skill can push branches, delete branches (`git push origin --delete ...`, `git branch -D ...`), and has a mandatory auto-fix path that can create and push a fix branch after review.
Transparency	0 (none)	The file is plain markdown with readable commands; there are no binaries, encoded payloads, or unpinned downloads.

Before installing

Confirm you are okay with a disposable branch being pushed to and later deleted from `origin`.
Review the local-repo flow and make sure no secrets are present under nonstandard filenames before the broad `git add -A`.
Use a scratch clone first if you do not want repository context sent to the AWS DevOps Agent.
Check that your remote repository policy allows branch creation/deletion from the account this skill will use.

Rated 2026-10-20 by an automated review of 1 file from the skill's repository.

Source

Repository: aws/agent-toolkit-for-aws (all skills from this repository)
Path: plugins/aws-agents-for-devsecops/skills/analyzing-release-readiness/SKILL.md
Branch: main
Collection: aws-agents-for-devsecops
Updated: 2026-09-19

make-pr-easy-to-review — Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior.
pr-review-canvas — Generate an interactive PR review walkthrough as an HTML page.
code-review — Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes.
github-review-pr — Reviews or re-reviews one contributor pull request—including an explicitly named closed PR being reconsidered—or a bounded newest-to-oldest sweep of all open.
get-pr-comments — Fetch and summarize review comments from the active pull request
interrogate — Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".