Reflexion

Low confidence

Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.

Type
plugin
GitHub stars
★ 1.2K
Repository
NeoLabHQ/context-engineering-kit
Category
—

Install

  1. 1Quick install (skills CLI)

    npx skills add NeoLabHQ/context-engineering-kit --skill reflexion --agent claude-code

    Installs reflexion into the current project's .claude/skills/ directory. Requires Node.js and the skills CLI.

  2. 2Manual install

    Create ~/.claude/plugins/<name>/ and copy the SKILL.md file from the repository into it. The directory name must match the skill name.

⚠️ Exact file layout and requirements vary by repository — always check the repo README first.

View on GitHub ↗

Prefer the full source? The repository README is the authoritative install reference.