Smithery Logo
MCPsSkillsDocsPricing
Login
Smithery Logo

Accelerating the Agent Economy

Resources

DocumentationPrivacy PolicySystem Status

Company

PricingAboutBlog

Connect

© 2026 Smithery. All rights reserved.

    atlasrox

    continuous-learning

    atlasrox/continuous-learning
    Coding
    1 installs

    About

    SKILL.md

    Install

    Install via Skills CLI

    or add to your agent
    • Claude Code
      Claude Code
    • Codex
      Codex
    • OpenClaw
      OpenClaw
    • Cursor
      Cursor
    • Amp
      Amp
    • GitHub Copilot
      GitHub Copilot
    • Gemini CLI
      Gemini CLI
    • Kilo Code
      Kilo Code
    • Junie
      Junie
    • Replit
      Replit
    • Windsurf
      Windsurf
    • Cline
      Cline
    • Continue
      Continue
    • OpenCode
      OpenCode
    • OpenHands
      OpenHands
    • Roo Code
      Roo Code
    • Augment
      Augment
    • Goose
      Goose
    • Trae
      Trae
    • Zencoder
      Zencoder
    • Antigravity
      Antigravity
    ├─
    ├─
    └─

    About

    Automatically extract reusable patterns from Antigravity Code sessions and save them as learned skills for future use.

    SKILL.md

    Continuous Learning Skill

    Automatically evaluates Antigravity Code sessions on end to extract reusable patterns that can be saved as learned skills.

    How It Works

    This skill runs as a Stop hook at the end of each session:

    1. Session Evaluation: Checks if session has enough messages (default: 10+)
    2. Pattern Detection: Identifies extractable patterns from the session
    3. Skill Extraction: Saves useful patterns to ~/.claude/skills/learned/

    Configuration

    Edit config.json to customize:

    {
      "min_session_length": 10,
      "extraction_threshold": "medium",
      "auto_approve": false,
      "learned_skills_path": "~/.claude/skills/learned/",
      "patterns_to_detect": [
        "error_resolution",
        "user_corrections",
        "workarounds",
        "debugging_techniques",
        "project_specific"
      ],
      "ignore_patterns": [
        "simple_typos",
        "one_time_fixes",
        "external_api_issues"
      ]
    }
    

    Pattern Types

    Pattern Description
    error_resolution How specific errors were resolved
    user_corrections Patterns from user corrections
    workarounds Solutions to framework/library quirks
    debugging_techniques Effective debugging approaches
    project_specific Project-specific conventions

    Hook Setup

    Add to your ~/.claude/settings.json:

    {
      "hooks": {
        "Stop": [{
          "matcher": "*",
          "hooks": [{
            "type": "command",
            "command": "~/.claude/skills/continuous-learning/evaluate-session.sh"
          }]
        }]
      }
    }
    

    Why Stop Hook?

    • Lightweight: Runs once at session end
    • Non-blocking: Doesn't add latency to every message
    • Complete context: Has access to full session transcript

    Related

    • The Longform Guide - Section on continuous learning
    • /learn command - Manual pattern extraction mid-session

    Comparison Notes (Research: Jan 2025)

    vs Homunculus (github.com/humanplane/homunculus)

    Homunculus v2 takes a more sophisticated approach:

    Feature Our Approach Homunculus v2
    Observation Stop hook (end of session) PreToolUse/PostToolUse hooks (100% reliable)
    Analysis Main context Background agent (Haiku)
    Granularity Full skills Atomic "instincts"
    Confidence None 0.3-0.9 weighted
    Evolution Direct to skill Instincts → cluster → skill/command/agent
    Sharing None Export/import instincts

    Key insight from homunculus:

    "v1 relied on skills to observe. Skills are probabilistic—they fire ~50-80% of the time. v2 uses hooks for observation (100% reliable) and instincts as the atomic unit of learned behavior."

    Potential v2 Enhancements

    1. Instinct-based learning - Smaller, atomic behaviors with confidence scoring
    2. Background observer - Haiku agent analyzing in parallel
    3. Confidence decay - Instincts lose confidence if contradicted
    4. Domain tagging - code-style, testing, git, debugging, etc.
    5. Evolution path - Cluster related instincts into skills/commands

    See: /Users/affoon/Documents/tasks/12-continuous-learning-v2.md for full spec.

    Recommended Servers
    Vercel Grep
    Vercel Grep
    Browserbase
    Browserbase
    Nimble MCP Server
    Nimble MCP Server
    Repository
    atlasrox/super-fiesta
    Files