continuous-learning
Automatically extract reusable patterns from Gemini CLI sessions and save them as learned skills for future use.
Best use case
continuous-learning is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automatically extract reusable patterns from Gemini CLI sessions and save them as learned skills for future use.
Teams using continuous-learning should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/continuous-learning/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How continuous-learning Compares
| Feature / Agent | continuous-learning | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automatically extract reusable patterns from Gemini CLI sessions and save them as learned skills for future use.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Continuous Learning Skill
Automatically evaluates Gemini CLI 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 `~/.gemini/skills/learned/`
## Configuration
Edit `config.json` to customize:
```json
{
"min_session_length": 10,
"extraction_threshold": "medium",
"auto_approve": false,
"learned_skills_path": "~/.gemini/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 `~/.gemini/settings.json`:
```json
{
"hooks": {
"Stop": [{
"matcher": "*",
"hooks": [{
"type": "command",
"command": "~/.gemini/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](https://x.com/Jamkris/status/2014040193557471352) - Section on continuous learning
- `/egc-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.Related Skills
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.
continuous-agent-loop
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.
x-api
X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Gemini CLI or understanding what capabilities are actually available in their environment.
visa-doc-translate
Translate visa application documents (images) to English and create a bilingual PDF with original and translation
videodb
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
video-editing
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
verification-loop
Comprehensive verification system for code changes
unified-notifications-ops
Operate notifications as one ECC-native workflow across GitHub, Linear, desktop alerts, hooks, and connected communication surfaces. Use when the real problem is alert routing, deduplication, escalation, or inbox collapse.
ui-demo
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
token-budget-advisor
Offers the user an informed choice about how much response depth to consume before answering. Use this skill when the user explicitly wants to control response length, depth, or token budget. TRIGGER when: "token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas", or clear variants where the user is explicitly asking to control answer size or depth. DO NOT TRIGGER when: user has already specified a level in the current session (maintain it), the request is clearly a one-word answer, or "token" refers to auth/session/payment tokens rather than response size.
terminal-ops
Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified.