Sponsor Suno AI Music arrow_forward
Slash Command

Structured Review

Start a structured review workflow with evidence logging and formatted output

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Structured Review is

Structured Review is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Structured Review gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Structured Review

Claude Code

  1. Download structured-review.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/imbue/commands/structured-review.md, shared under the repository's MIT license. Read the full file on GitHub.

Initializes a structured review workflow using imbue's core methodology: context establishment, scope inventory, evidence capture, and deliverable structuring.

Usage

# Start review of current branch
/structured-review

# Review specific target
/structured-review src/auth/

# Review with specific focus
/structured-review --focus security src/api/

What It Does

  1. Establishes Context: Confirms repository, branch, and comparison baseline
  2. Inventories Scope: Lists relevant artifacts for review
  3. Prepares Evidence Log: Initializes tracking for commands and citations
  4. Structures Deliverables: Sets up report template with sections

Workflow Integration

This command orchestrates multiple imbue skills:

  • review-core - Core workflow scaffolding
  • proof-of-work - Reproducible evidence capture
  • structured-output - Consistent deliverable formatting
  • diff-analysis - Change categorization (if diffs involved)

Examples

/structured-review
# Output:
# Review Workflow Initialized
# ===========================
# Repository: my-project
# Branch: feature/auth-overhaul
# Baseline: main (3 commits behind)
#
# TodoWrite items created:
# - [ ] review-core:context-established
# - [ ] review-core:scope-inventoried
# - [ ] review-core:evidence-captured
# - [ ] review-core:deliverables-structured

/structured-review src/api --focus performance
# Scoped review with performance focus

Output

Creates structured review scaffold with:

  • Context summary (repo, branch, baseline)
  • Scope inventory (files, configs, specs)
  • Evidence log template
  • Deliverable outline

Feature Review Mode

When invoked with --mode feature or --features, structured-review runs a feature-focused review workflow (formerly the standalone /feature-review command). This mode discovers, classifies, scores, and suggests features using evidence-based prioritization.

Feature Review Usage

# Full feature review: inventory, score, suggest
/structured-review --mode feature

# Only inventory current features
/structured-review --mode feature --inventory

# Generate new feature suggestions
/structured-review --mode feature --suggest

# Create GitHub issues for accepted suggestions
/structured-review --mode feature --suggest --create-issues

# Validate configuration file
/structured-review --mode feature --validate-config

Feature Review Phases

  1. Discovers implemented features from codebase (commands, skills, agents, hooks, APIs)
  2. Classifies features as proactive/reactive and static/dynamic
  3. Scores features using hybrid RICE+WSJF framework
  4. Analyzes tradeoffs across quality dimensions (Quality, Latency, Token Usage, Resource Usage, Redundancy, Readability, Scalability, Integration, API Surface)
  5. Suggests new features based on gaps and opportunities
  6. Creates GitHub issues for accepted suggestions (with --create-issues)

Scoring

Score = (Value Score / Cost Score) * Confidence

Thresholds:

  • > 2.5: High priority (implement soon)
  • 1.5 - 2.5: Medium priority (roadmap)
  • < 1.5: Low priority (backlog)

Configuration

Create .feature-review.yaml in project root to customize scoring weights, classification patterns, tradeoff dimension weights, and GitHub integration settings. See Skill(imbue:feature-review) for full configuration reference.

Feature Review Integration

This mode uses:

  • Skill(imbue:feature-review) - Core scoring and classification
  • Skill(imbue:scope-guard) - Budget validation for suggestions
  • Skill(imbue:review-core) - Evidence-based methodology

Exit Criteria

  • All TodoWrite items from review-core created
  • Evidence log initialized with session context
  • Deliverable template ready for findings

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Structured Review?

Structured Review is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Start a structured review workflow with evidence logging and formatted output

How do I install Structured Review in Claude Code?

Download structured-review.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Structured Review in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Structured Review safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.