Agent skill

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

vibeevalgithub.com/vibeevalGitHub ↗
claude-codeships scriptsMIT
Install
npx skills add vibeeval/vibecosystem --skill continuous-learning-v2 --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 6
SKILL.md size: 8 KB
Bundled scripts: yes
Version: 2.0.0
Path: skills/continuous-learning-v2/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 521
Language: C#

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Continuous Learning v2 - Instinct-Based Architecture An advanced learning system that turns your Claude Code sessions into reusable knowledge through atomic "instincts" - small learned behaviors with confidence scoring. ## What's New in v2 | Feature | v1 | v2 | |---------|----|----| | Observation | Stop hook (session end) | PreToolUse/PostToolUse (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 | ## The Instinct Model An instinct is a small learned behavior: ```yaml --- id: prefer-functional-style trigger: "when writing new functions" confidence: 0.7 domain: "code-style" source: "session-observation" --- # Prefer Functional Style ## Action Use functional patterns over classes when appropriate. ## Evidence - Observed 5 instances of functional pattern preference - User corrected class-based approach to functional on 2025-01-15 ``` **Properties:** - **Atomic** — one trigger, one action - **Confidence-weighted** — 0.3 = tentative, 0.9 = near certain - *

What's inside
Steps it walks through
  1. What's New in v2
  2. The Instinct Model
  3. How It Works
  4. Quick Start
  5. 1. Enable Observation Hooks
  6. 2. Initialize Directory Structure
  7. 3. Use the Instinct Commands
  8. Commands
  9. Configuration
  10. File Structure
  11. Integration with Skill Creator
  12. Confidence Scoring
  13. Why Hooks vs Skills for Observation?
  14. Backward Compatibility
Ships with 5 files
  • agents/observer.md
  • agents/start-observer.sh
  • config.json
  • hooks/observe.sh
  • scripts/instinct-cli.py
Commands it runs
mkdir -p ~/.claude/homunculus/{instincts/{personal,inherited},evolved/{agents,skills,commands}}
touch ~/.claude/homunculus/observations.jsonl
More from vibecosystem
All skills →
About this skill
What does the continuous-learning-v2 skill do?

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

How do I install it?

Run `npx skills add vibeeval/vibecosystem --skill continuous-learning-v2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From vibeeval/vibecosystem, a repository with 521 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going