GenericAgent vs skill-recorder
GenericAgent is much bigger: 14.1k stars against 3.8k. Over the days we have tracked them GenericAgent moved +11.8% and skill-recorder +224.4%, so skill-recorder is growing faster right now.
GenericAgent leads on context depth and model freedom. skill-recorder does not take any axis by a clear margin.
Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.
Where they stand today
Self-evolving agent that crystallizes each solved task into a persistent, reusable personal skill tree from a minimal (~3K-line) seed.
- Stars
- 14.1k
- Tracked growth
- +11.8%
- Maturity
- ●●●●●
- Last commit
- 2d ago
- Language
- Python
- License
- MIT
- Cost to run
- Your LLM API key; provider charges apply
Converts a single on-screen recording (clicks, window switches, URLs, and optional narration) into a generalized, reusable Skill or scheduled Automation using the GitHub Copilot CLI.
- Stars
- 3.8k
- Tracked growth
- +224.4%
- Maturity
- ●●●●●
- Last commit
- 1d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Requires GitHub Copilot access
Six axes, head to head
Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.
| Axis | GenericAgent | skill-recorder |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Whole-repo analysis | ●●●●● Recording only |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Human-in-the-loop | ●●●●● Manual review/edit |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config & prompts | ●●●●● Manual edits only |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Cloud API key | ●●●●● Copilot cloud required |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own-key | ●●●●● Copilot only |
Setup ease What it takes to get a first useful run out of it. | ●●●●● One-line installer | ●●●●● One-command install |
Which one to pick
Pick GenericAgent if…
Self-evolving — pick this when you want an agent that autonomously builds reusable skills and gains system-level desktop/browser control over time.
- Context depth: Whole-repo analysis (5/5 against 1/5)
- Model freedom: Bring-your-own-key (5/5 against 1/5)
Pick skill-recorder if…
Privacy-aware — captures and processes recordings locally and only uploads event data and images to GitHub Copilot when you explicitly choose Analyze, making it easy to create real-world reusable agent skills from one run.
What people want from each one
lsdefine/GenericAgent
microsoft/skill-recorder
Questions people ask
Is GenericAgent better than skill-recorder?
GenericAgent leads on context depth and model freedom. skill-recorder does not take any axis by a clear margin. GenericAgent is worth picking when self-evolving — pick this when you want an agent that autonomously builds reusable skills and gains system-level desktop/browser control over time.
Which of GenericAgent and skill-recorder keeps my code private?
GenericAgent: Cloud API key (3/5). skill-recorder: Copilot cloud required (2/5).
What does each one cost to run?
GenericAgent: Your LLM API key; provider charges apply. skill-recorder: Requires GitHub Copilot access.
Full profiles: lsdefine/GenericAgent and microsoft/skill-recorder. Everything else in Computer use.