claude-reflect
A system that captures user feedback and corrections during coding sessions to improve future AI behavior.
Install
mkdir -p .claude/skills/claude-reflect && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/3079" && unzip -o skill.zip -d .claude/skills/claude-reflect && rm skill.zipInstalls to .claude/skills/claude-reflect
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute self-learning system that captures corrections during sessionsKey capabilities
- →Capture user corrections during sessions
- →Queue captured learnings for review
- →Process queued learnings with human review
- →Apply learnings to global or project-specific CLAUDE.md files
- →Scan past sessions for missed learnings
- →Preview changes without applying them
How it works
The system automatically captures user corrections based on specific patterns and queues them. Users then manually review and apply these queued learnings to update `CLAUDE.md` files, ensuring the agent learns from feedback.
Inputs & outputs
When to use claude-reflect
- →Saving project-specific coding preferences
- →Recording architectural decisions
- →Syncing user feedback into CLAUDE.md
- →Reviewing past interaction learnings
About this skill
Claude Reflect - Self-Learning System
A two-stage system that helps Claude Code learn from user corrections.
How It Works
Stage 1: Capture (Automatic)
Hooks detect correction patterns ("no, use X", "actually...", "use X not Y") and queue them to ~/.claude/learnings-queue.json.
Stage 2: Process (Manual)
User runs /reflect to review and apply queued learnings to CLAUDE.md files.
Available Commands
| Command | Purpose |
|---|---|
/reflect | Process queued learnings with human review |
/reflect --scan-history | Scan past sessions for missed learnings |
/reflect --dry-run | Preview changes without applying |
/skip-reflect | Discard all queued learnings |
/view-queue | View pending learnings without processing |
When to Remind Users
Remind users about /reflect when:
- They complete a feature or meaningful work unit
- They make corrections you should remember for future sessions
- They explicitly say "remember this" or similar
- Context is about to compact and queue has items
Correction Detection Patterns
High-confidence corrections:
- Tool rejections (user stops an action with guidance)
- "no, use X" / "don't use Y"
- "actually..." / "I meant..."
- "use X not Y" / "X instead of Y"
- "remember:" (explicit marker)
CLAUDE.md Destinations
~/.claude/CLAUDE.md- Global learnings (model names, general patterns)./CLAUDE.md- Project-specific learnings (conventions, tools, structure)
Example Interaction
User: no, use gpt-5.1 not gpt-5 for reasoning tasks
Claude: Got it, I'll use gpt-5.1 for reasoning tasks.
[Hook captures this correction to queue]
User: /reflect
Claude: Found 1 learning queued. "Use gpt-5.1 for reasoning tasks"
Scope: global
Apply to ~/.claude/CLAUDE.md? [y/n]
Overview
Execute self-learning system that captures corrections during sessions and syncs them to CLAUDE.
Prerequisites
- Access to the Claude Reflect environment or API
- Required CLI tools installed and authenticated
- Familiarity with Claude Reflect concepts and terminology
Instructions
- Assess the current state of the Claude Reflect configuration
- Identify the specific requirements and constraints
- Apply the recommended patterns from this skill
- Validate the changes against expected behavior
- Document the configuration for team reference
Output
- Configuration files or code changes applied to the project
- Validation report confirming correct implementation
- Summary of changes made and their rationale
Error Handling
| Error | Cause | Resolution |
|---|---|---|
| Authentication failure | Invalid or expired credentials | Refresh tokens or re-authenticate with Claude Reflect |
| Configuration conflict | Incompatible settings detected | Review and resolve conflicting parameters |
| Resource not found | Referenced resource missing | Verify resource exists and permissions are correct |
Examples
Basic usage: Apply claude reflect to a standard project setup with default configuration options.
Advanced scenario: Customize claude reflect for production environments with multiple constraints and team-specific requirements.
Resources
- Official Claude Reflect documentation
- Community best practices and patterns
- Related skills in this plugin pack
When not to use it
- →When the user does not want corrections to be remembered
- →When the user explicitly discards all queued learnings
- →When the user does not want to review and apply learnings
Prerequisites
Limitations
- →Requires explicit user action to process and apply queued learnings
- →Correction detection relies on specific linguistic patterns
- →Requires CLI tools to be installed and authenticated
How it compares
This skill provides a structured two-stage process for capturing and applying user corrections to a knowledge base, unlike simply acknowledging feedback which may not persist.
Compared to similar skills
claude-reflect side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| claude-reflect (this skill) | 1 | 27d | Review | Beginner |
| slidev | 371 | 9mo | Review | Intermediate |
| obsidian | 29 | 27d | No flags | Intermediate |
| changelog-automation | 8 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
slidev
XIYO
Comprehensive guide for Slidev - a web-based presentation framework for developers. Covers Markdown syntax, layouts, components, animations, theming, and exporting. Use this skill when creating or working with developer presentations using Slidev.
obsidian
gapmiss
Comprehensive guidelines for Obsidian.md plugin development including all 27 ESLint rules, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, and submission requirements. Use when working with Obsidian plugins, main.ts files, manifest.json, Plugin class, MarkdownView, TFile, vault operations, or any Obsidian API development.
changelog-automation
wshobson
Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.
configured-agent
anthropics
This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.
markdown-to-html
github
Convert Markdown files to HTML similar to `marked.js`, `pandoc`, `gomarkdown/markdown`, or similar tools; or writing custom script to convert markdown to html and/or working on web template systems like `jekyll/jekyll`, `gohugoio/hugo`, or similar web templating systems that utilize markdown documents, converting them to html. Use when asked to "convert markdown to html", "transform md to html", "render markdown", "generate html from markdown", or when working with .md files and/or web a templating system that converts markdown to HTML output. Supports CLI and Node.js workflows with GFM, CommonMark, and standard Markdown flavors.
lecture-transcript-slide-matcher
az9713
Combines YouTube lecture transcripts with PDF slides to create an interactive HTML page. Matches each slide to corresponding transcript segments, organized by key concepts. Use when users want to create synchronized lecture notes from transcript text files and slide PDFs.