Claude Skill

blader/Claudeception

A Claude Skill for autonomous extraction and continuous learning, helping Claude Code become smarter through work. Shell-based implementation with 1.4k+ stars.

Overview

Stars1,426
Forks134
LanguageShell
Last pushed2026-01-22
Last synced2026-06-02
View on GitHub

Repository

Ownerblader
RepositoryClaudeception
Full nameblader/Claudeception
Repo ID1,136,478,079

Install this Skill

git clone https://github.com/blader/Claudeception.git ~/.claude/skills/claudeception

Registry

Typeopenclaw_skill
Quality score75/100
Verificationreadme_parsed
Last verified2026-06-02
Platforms
Claude
Capabilities
browserpdfsearchterminal
Detected files
README.mdSKILL.mdexamples
Install methods
  • git clone https://github.com/blader/Claudeception.git ~/.claude/skills/claudeception
  • git clone https://github.com/blader/Claudeception.git .claude/skills/claudeception

Summary

Claudeception is a Claude Skill designed for autonomous skill extraction and continuous learning, enabling Claude Code to become smarter as it works.

Chinese description

一个用于自主技能提取和持续学习的Claude Code技能。让Claude Code在工作中不断变得更智能。

Key features

  • Autonomous skill extraction
  • Continuous learning capability
  • Shell-based implementation
  • Designed for Claude Code enhancement
  • Self-improving system

Use cases

  • Automated skill acquisition from codebases
  • Continuous improvement of coding assistants
  • Knowledge extraction and organization
  • AI assistant capability enhancement
  • Learning from development workflows

README excerpt

# Claudeception Every time you use an AI coding agent, it starts from zero. You spend an hour debugging some obscure error, the agent figures it out, session ends. Next time you hit the same issue? Another hour. This skill fixes that. When Claude Code discovers something non-obvious (a debugging technique, a workaround, some project-specific pattern), it saves that knowledge as a new skill. Next time a similar problem comes up, the skill gets loaded automatically. ## Installation ### Step 1: Clone the skill **User-level (recommended)** ```bash git clone https://github.com/blader/Claudeception.git ~/.claude/skills/claudeception ``` **Project-level** ```bash git clone https://github.com/blader/Claudeception.git .claude/skills/claudeception ``` ### Step 2: Set up the activation hook (recommended) The skill can activate via semantic matching, but a hook ensures it evaluates every session for extractable knowledge. #### User-level setup (recommended) 1. Create the hooks directory and copy the script: ```bash mkdir -p ~/.claude/hooks cp ~/.claude/skills/claudeception/scripts/claudeception-activator.sh ~/.claude/hooks/ chmod +x ~/.claude/hooks/claudeception-activator.sh ``` 2. Add the hook to your global Claude settings (`~/.claude/settings.json`): ```json { "hooks": { "UserPromptSubmit": [ { "hooks": [ { "type": "command", "command": "~/.claude/hooks/claudeception-activator.sh" } ] } ] } } ``` #### Project-level setup 1. Create the hooks directory inside your project and copy the script: ```bash mkdir -p .claude/hooks cp .claude/skills/claudeception/scripts/claudeception-activator.sh .claude/hooks/ chmod +x .claude/hooks/claudeception-activator.sh ``` 2. Add the hook to your

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-06-02