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

Decant Review

skill-minwoo19930301-decant-decant-review · by minwoo19930301

Review a fixed change set for specification compliance, correctness, security, regression risk, and evidence quality. Use for code or release review; remain read-only unless the user separately requests fixes.

↗ Repository
— No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-minwoo19930301-decant-decant-review

✓ 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-minwoo19930301-decant-decant-review)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo 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 Decant Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Decant Review

Review the requested baseline, not a moving or assumed diff.

Establish the baseline

  1. Identify the exact commit, branch diff, patch, or working-tree changes in scope.
  2. Read the specification and acceptance criteria.
  3. Inspect relevant tests, runtime paths, configuration, and failure handling.

Two passes

First check specification compliance: missing behavior, scope drift, unsupported claims, and unmet acceptance criteria.

Then check code quality: correctness, security, data loss, concurrency, compatibility, dependency risk, observability, and test adequacy. Increase depth with risk; do not manufacture low-value comments to fill a quota.

Finding contract

Each actionable finding includes:

  • severity and concise title;
  • exact file and line or reproducible location;
  • evidence and failure scenario;
  • impact;
  • smallest safe remediation.

Separate findings from optional improvements. If no actionable findings exist, say so and name any residual testing gaps.

Boundaries

  • Do not edit during a review-only request.
  • Do not call tests passing if they were not executed.
  • Do not treat the maker's self-review as independent evidence.
  • Do not conflate clarity review with correctness or security review.

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.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills