skills.rest
nhouseholder
nhouseholderCOMMUNITY
Explore all skills by this author →
GitHub

reflexion

Run opt-in reflect or critique modes for AI output self-review.

Updated Aug 23, 2026
Search Tags:#review#code-quality#critique#self-assessment#design-review#reflect#ai-tooling
One-click install
npx skills add https://github.com/nhouseholder/nicks-claude-code-superpowers --skill reflexion-nhouseholder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reflexion
Source: https://github.com/nhouseholder/nicks-claude-code-superpowers/tree/main/skills/reflexion
Command: npx skills add https://github.com/nhouseholder/nicks-claude-code-superpowers --skill reflexion-nhouseholder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Self-refinement and comprehensive review framework that improves AI output quality by enabling opt-in quick self-assessment (reflect) and deep multi-dimensional critique (critique). Opt-in only — fires on explicit user request, high-risk changes, or after 2+ failed bug fixes.

Core Features & Use Cases

  • Two modes: Reflect for quick self-assessment and Critique for deep review.
  • Opt-in workflow to avoid auto-fire on routine tasks.
  • Structured evaluation across requirements, design, and code quality via a reviewer agent.
  • Guardrails for high-risk changes and escalation when needed.

Quick Start

Prompt with /reflexion:reflect to run a quick self-assessment or /reflexion:critique to initiate a deep, multi-dimensional review.

Frequently Asked Questions about reflexion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run a self-assessment on my AI outputs?▼

To run a self-assessment on AI outputs, prompt with /reflexion:reflect to initiate a quick quality check and structured self-refinement of your current task.

What's the best way to perform a deep code review on high-risk changes?▼

For high-risk changes, deep multi-dimensional critique is performed by prompting /reflexion:critique to evaluate requirements, design, and code quality thoroughly.

When should I use a self-refinement workflow instead of just regenerating an AI response?▼

Use a self-refinement workflow when you need fast quality checks on outputs or after 2+ failed bug fixes, and require structured evaluation rather than simple regeneration.

Can I use this critique workflow for evaluating design proposals and plans?▼

Yes, the critique workflow supports thorough evaluation of high-risk changes, proposals, and bug fixes across outputs, designs, and plans through a reviewer agent.

Does the self-review workflow fire automatically on routine code generation?▼

No, the self-review workflow is opt-in only and does not fire automatically on routine tasks. It activates solely on explicit request or for high-risk changes.

Why does my AI need a structured critique workflow after multiple failed bug fixes?▼

A structured critique workflow breaks the failure loop by applying multi-dimensional evaluation to requirements, design, and code quality, escalating issues that simple retries miss.

Related Skills

Explore More Software Engineering Skills→
hkcm91hkcm91

self-improving-ai

Automate AI self-evaluation and prompt refinement cycles for continuous improvement.

Community
Advanced
vchelaruvchelaru
11

agentic-eval

Coordinate generate-evaluate-critique-refine loops to improve AI agent outputs.

Community
Intermediate
KajabiKajabi
26

sage-run-gauntlet

Launch parallel reviewer agents to analyze sage-lib diffs and consolidate feedback by severity.

Official
Intermediate
flexphereflexphere
7

self-review

Automates a three-round self-review workflow for code changes.

Community
Advanced