Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Dim Review

ASecurity

Review an order's whole diff against its Build artifact, one agent per area, and return findings or the Review artifact. Use as the reviewer, when a brief names dim-review.

5 stars
0 votes
0 copies
0 views
Added 10/5/2026
code-qualitygo

Security Analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned 10/5/2026

$npx -y skills add cniska/dim-factory --skill dim-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dim Review?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Dim Review
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/cniska-dim-review/badge)](https://www.skillsdirectory.com/skills/cniska-dim-review)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: dim-review
description: Review an order's whole diff against its Build artifact, one agent per area, and return findings or the Review artifact. Use as the reviewer, when a brief names dim-review.
---

# Review

The brief carries the `order`, the `workspace`, the `build` (the Build artifact), the `diff` (the order's whole diff against the default branch), the `answers` the builder gave the last round's findings and `returned` (why the order is back at review, when it is).
## Returns

- Findings. Write a JSON array to a file under `$TMPDIR`, each `{"area", "file", "line", "failure", "fix", "severity"}` with severity `critical`, `high` or `medium`, and run `dim review return --findings <file>`. Every finding blocks; a point that would not block is left out. The order goes back to build, and the builder answers each finding once.
- The Review artifact. Write `{"body", "covered", "setAside", "unverified"}` to a file under `$TMPDIR` and run `dim review return --artifact <file>`. `body` follows [artifact](references/artifact.md), with no title, the outcome first and drawn from the record, and says whether the diff does what the Build artifact says; `covered` names each area that ran; `setAside` what was left out as outside the order; `unverified` each claim that could not be checked and what would settle it.
- `dim order return --reason "<the problem>"` when the Build artifact claims what the diff does not do and the fix is the builder's rather than a finding's.

A reply naming what is missing records nothing: fix the return and send it again. A second miss fails the station. `dim order show` prints the order, and `dim message send <text>` leaves the operator a note it reads after the turn.

## What the gates proved

Each commit passed the project's check on its own code when the gates kept it, with the check's declaration unchanged. After a rebase only the branch's head was checked again. Read for what reading alone can show.

## The passes

Read the tests first, then the Build artifact for the intent. Then one agent per area, each with read-only tools, the diff, the intent, the project's rules and its own question, and not your own reading. The areas and their questions are in [quality areas](references/quality-areas.md), with two more that only a change has:

| Area | Reads against |
|---|---|
| Conformance | Whether the diff does what the Build artifact says, naming work that is missing, extra or misunderstood |
| Style | Whether naming, structure and local patterns stay consistent, with no comment or abstraction noise |

Architecture takes `dim query prior-art "<path fragment>"` as grounding. For a defect, [bug](references/bug.md) under Review.

## Before returning

- Each finding names a file the diff changed, a line that file has at the head commit, what fails, the fix and its severity.
- An earlier finding whose answer does not settle it at this head is raised again, saying why.
- An area whose agent did not return is named under `unverified`.

Attribution

cniskacniska
View sourceSee grades on GitHubMore from cniska →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman Commit

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

1100021 votes

Caveman Review

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

1100021 votes

Verification Loop

一个全面的 Claude Code 会话验证系统。

2456590 votes

Django Verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

2456590 votes

Springboot Verification

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

2456590 votes
View all in code-quality →