AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Code Review Report

skill-2ykwang-agent-skills-code-review-report · by 2ykwang

Turn code changes into a single-file HTML code review report that pairs the diff with context a diff can't show — design decisions, rejected alternatives, tradeoffs, unfinished work — plus prioritized review points. Use when preparing for review after finishing a sizable change, refactor, or feature, or whenever the user asks for a review report, change report, or an HTML summary of their changes.

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-2ykwang-agent-skills-code-review-report

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-2ykwang-agent-skills-code-review-report)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Code Review Report? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Code Review Report

Build a single-file HTML report a reviewer reads before digging through the raw diff. A diff shows what changed; it doesn't show why, what was rejected, or what's still missing. Filling that gap with the context accumulated in this conversation is what separates this from a diff viewer.

1. Collect the change

Check the change with git status and git diff. Default scope: current branch vs the default branch, plus the uncommitted working tree.

  • git diff ...HEAD (committed), git diff HEAD (uncommitted)
  • Untracked files don't appear in diffs — find them with git status and read them directly.

If the scope is mixed or contains unrelated changes, ask the user. Exclude unrelated changes or mark them separately.

2. Collect the working context

Gather from this conversation the things a diff never records:

  • What was changed and why
  • Design decisions and their reasons, rejected alternatives, tradeoffs
  • Unfinished work and next steps
  • Concerns raised and reversals made along the way

If the conversation lacks this (e.g., the skill was invoked fresh), reconstruct from git log, commit messages, PRs, and related docs. If still empty, ask the user.

3. Extract review points

Inject the changed code plus the working context into subagents and collect suspicious spots as P1–P3 findings. Read references/review-perspectives.md for the perspective list and the subagent prompt skeleton. The context injection is the point — without it you only get surface-level remarks, not findings like spec mismatches or contradictions between decisions. For large changes, run one subagent per perspective in parallel.

4. Write the HTML

Start from assets/template.html. Follow references/report-structure.md for sections and references/style-guide.md for visual rules. Two things are non-negotiable:

  • Syntax highlighting on code blocks (add language-* classes)
  • Bidirectional anchors between change details and the review checklist

Write the report in the language the user works in: translate the template's headings and set `. Keep code as-is. Before finalizing, run the self-check at the end of references/report-structure.md`.

5. Finalize

  1. Save to the project root as -review-report.html (kebab-case task name).
  2. Inline the vendored highlight.js — replaces the template's placeholder, keeps the report self-contained and offline-friendly:

python3 /scripts/inline_hljs.py

  1. Open it for the user: open (macOS), xdg-open (Linux), start (Windows).

Principles

  • State tradeoffs, limitations, and unfinished work plainly.
  • Every change gets a "why", not just a "what".
  • Quote code; show before→after where possible.
  • Hierarchy through typography and spacing, not color.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.