autoskill
Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.
- Version
- 1.3
- License
- MIT license
Pinned to revision de66e10cd0c8, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Read
- Write
- Edit
- Bash
Files
- skills/autoskill/SKILL.md
- skills/autoskill/.gitignore
- skills/autoskill/config.yaml
- skills/autoskill/references/https-proxy.md
- skills/autoskill/references/screenpipe-config.yaml
- skills/autoskill/scripts/autoskill.py
- skills/autoskill/scripts/backends.py
- skills/autoskill/scripts/cluster.py
- skills/autoskill/scripts/doctor.py
- skills/autoskill/scripts/fetch_window.py
- skills/autoskill/scripts/match_skills.py
- skills/autoskill/scripts/promote.py
- skills/autoskill/scripts/redact.py
- skills/autoskill/scripts/run.py
- skills/autoskill/scripts/synthesize.py
Every link opens the file at its source, pinned to the revision this page describes.