Index of every page on this site: llms.txt
All skills
amanktyr avatar

/review

@5711aad
by Aman Ktyramanktyr/tailor6 stars
Run it yourself

Guides comprehensive code and architecture reviews (/review or tailor review), evaluating duplication, security risks, performance bottlenecks, and convention adherence.

Use this Skill: https://skilld.dev/gh/amanktyr/tailor/review

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈44 tokens for metadata: the name and description. ≈517 when used: this file.

Description uses 2.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈178 characters, or 2.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Code & Architecture Review Skill

Activate this skill when reviewing code changes, evaluating pull requests, or conducting a project-wide health review (/review or tailor review).

Review Directive: Provide actionable, prioritized feedback focusing on architecture, security, code reuse, and long-term maintainability.


1. Multi-Dimensional Review Rubric

Evaluate code changes across 5 core dimensions:

  1. Architecture & Boundaries: Does the implementation violate established ADRs in .ai/DECISIONS.md or cross layer boundaries illegally?
  2. Reuse & Duplication: Could this code have reused existing components, utilities, or abstractions instead of introducing duplicates?
  3. Dependency Governance: Were unnecessary external packages added when standard library primitives or native APIs suffice?
  4. Security & Validation: Are user inputs sanitized? Are database queries parameterized? Are secrets kept out of source code?
  5. Testing & Quality: Are there targeted tests covering happy paths, error handling, and edge cases?

2. Standardized Actionable Finding Schema

Structure all review feedback using this concise format:

### [SEVERITY] REV-00X: [Clear Issue Summary]
- **Severity Level:** CRITICAL | HIGH | MEDIUM | LOW | INFO
- **File Location:** `src/features/auth/login.ts:28`
- **Problem Statement:** Concise explanation of the flaw or anti-pattern.
- **Impact & Risk:** Why this matters (security compromise, memory leak, code duplication).
- **Remediation Code:**
  ```ts
  // Replace the insecure/duplicate block with this implementation

---

## 3. Pull Request Review Checklist

- [ ] Zero unvalidated user inputs reaching database or shell execution.
- [ ] Zero hardcoded credentials, API keys, or JWT secrets.
- [ ] Existing UI components and helpers reused where applicable.
- [ ] No new micro-packages introduced without justification.
- [ ] All automated tests pass with exit code 0.
- [ ] Updated project memory documentation in `.ai/` if architecture or schemas changed.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts3mo3 checks · Risk SAFE
  • Gen Agent Trust Hub3mo

    The skill provides a framework for conducting code and architecture reviews. It focuses on architecture boundaries, duplication, dependencies, security, and testing. No security risks, obfuscation, or malicious patterns were detected.

  • Socket3mo

    No alerts

  • Snyk3mo

    Risk: LOW · No issues

Signed by skilld at 5711aad. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 3 months ago

README badge

README badge for amanktyr/tailor/review