reflect

Analyze skill usage from session outcomes and update SKILL.md files.

Updated Jan 15, 2025
One-click install
npx skills add https://github.com/TobiasBak/dotfiles --skill reflect-tobiasbak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reflect
Source: https://github.com/TobiasBak/dotfiles/tree/main/agent-files/skills/reflect
Command: npx skills add https://github.com/TobiasBak/dotfiles --skill reflect-tobiasbak

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze and improve skills based on session outcomes, enabling you to identify which skills were used and how effective they were so you can refine behavior in future interactions.

Core Features & Use Cases

  • Identify skill usage within a session and assess outcomes.
  • Propose concrete improvements to skill instructions, triggers, or flow.
  • Support post-session retrospectives by comparing performance across sessions.

Quick Start

Review the current session, identify the skills used, and propose one concrete improvement to a skill.

Frequently Asked Questions about reflect

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

FAQPage Schema
How do I analyze session outcomes to improve my AI skills?

To analyze session outcomes and improve skills, you can run a post-session review that evaluates which skills were used, how well they performed, and where to refine them for future interactions.

How does skill analysis work during a post-session review?

Skill analysis works by reading skill definitions from the ~/.claude/skills/*/SKILL.md files, evaluating their usage and effectiveness during the session, and proposing concrete improvements to instructions or triggers.

Can I update skill definitions without breaking the original markdown structure?

Yes, you can update skill definitions while preserving the YAML frontmatter and the original markdown structure, ensuring that your formatting and metadata remain intact during the refinement process.

What is the best way to refine skill triggers and instructions after a session?

The best way to refine skill triggers and instructions is to conduct a post-session retrospective that compares performance across sessions and proposes one concrete improvement to a skill's flow or behavior.

Does this skill analysis require any external dependencies to run?

No, this skill analysis requires no external dependencies to run, as it operates independently by reading local skill files and evaluating session outcomes to generate improvement proposals.

Why should I use automated session review instead of manually tuning prompts?

Automated session review identifies which skills were used and assesses their effectiveness objectively, whereas manual prompt tuning lacks the structured comparison of performance outcomes needed to refine behavior consistently.