k-dense-ai/scientific-agent-skills · skills/autoskill/SKILL.md

autoskill skillA

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 ru

Latest version
mdr add k-dense-ai/scientific-agent-skills/autoskill@v1.4
Exact content
mdr add k-dense-ai/scientific-agent-skills/autoskill@sha256:6c342b90d218115c
Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pozflhmrh5ldvvv3.svg)](https://markdownregistry.com/a/art_pozflhmrh5ldvvv3)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
v1.4 latest2026-09-02 1e5eeff 12,789 BA view · diff
v1.32026-07-28 0e45106 11,831 BA view · diff
v1.22026-07-26 2f2022d 11,831 BA view · diff
v1.12026-07-26 b085e11 11,809 BA view · diff
git:20260611.c1150bd2026-06-11 c1150bd 12,201 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.

Source

GitHub

k-dense-ai/scientific-agent-skills · 42,925 stars · license MIT · pushed 2026-09-02 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pozflhmrh5ldvvv3
GET https://markdownregistry.com/api/v1/resolve?ref=k-dense-ai/scientific-agent-skills/autoskill
GET https://markdownregistry.com/api/v1/blob/6c342b90d218115cdeb959b177c2db1b7715c84e6441074a2e70c896b137b855