autoskill

Name: autoskill
Author: K-Dense-AI

712installs3.1kforks

How to install autoskill?

k-dense-ai/scientific-agent-skills/autoskill

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill autoskill

Installs into the current project.

Summary

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 rece

Files · 1

View on GitHub

SKILL.md

1	# autoskill
2
3	> Requires a running [screenpipe](https://github.com/screenpipe/screenpipe) daemon. This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http://localhost:3030`). If the daemon isn't running, `run()` raises `ScreenpipeUnreachable` with install instructions.
4
5	> Network access & environment variables. This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http://localhost:1234/v1` (LM Studio, default), `https://api.anthropic.com` (opt-in Claude), or a user-supplied BYOK Foundry gateway. The skill reads three environment variables — `SCREENPIPE_TOKEN`, `ANTHROPIC_API_KEY`, `FOUNDRY_API_KEY` — and uses each only to authenticate to the single endpoint its name implies. No other network destinations, no telemetry, no data egress to any third party.
6
7	## Overview
8
9	Turn the user's own workflow history — captured passively by the local [screenpipe](https://github.com/screenpipe/screenpipe) daemon — into new skills. This skill is on-demand: the user invokes it with a time window, it queries screenpipe's local HTTP API, clusters repeated workflow patterns, compares each pattern against the existing skills in this repo, and produces a staged folder of proposals the user can review, edit, and promote.
10
11	## When to Use This Skill
12
13	Invoke this skill when the user asks to:
14	- "Analyze my last 4 hours / day / week and propose new skills."
15	- "Look at what I've been doing and tell me what's not covered yet."
16	- "Draft a skill from my recent workflow."
17	- "Find composition recipes for workflows I repeat."
18
19	Do not invoke it for one-off questions about screenpipe itself, for real-time screen queries, or without an explicit user request — the skill analyzes sensitive local content and must stay explicitly user-triggered.
20
21	## Privacy Posture
22
23	- Screenpipe handles app/window filtering at capture time. Install a starter deny-list by copying `references/screenpipe-config.yaml` into the user's screenpipe config. Sensitive apps (password managers, messaging, banking) are never OCR'd in the first place.
24	- Raw OCR never leaves the machine. `scripts/fetch_window.py` pulls data over localhost HTTP. `scripts/cluster.py` reduces the timeline to app/duration/title summaries. `scripts/redact.py` strips emails, API keys, bearer tokens, and phone numbers as defense-in-depth before any cluster summary reaches the LLM.
25	- LLM backend defaults to `local`. The recommended setup is [LM Studio](https://lmstudio.ai/) running `Gemma-4-31B-it` — strong reasoning at a size that fits on most workstation GPUs, and no data ever leaves your machine. Cloud backends (`claude`, `foundry`) are opt-in and documented in `config.yaml` for users who explicitly want them. Detection and embeddings always run locally regardless of backend choice.
26	- Dry-run mode (`--plan`) prints the exact timeline that will be analyzed before any LLM call.
27	- TLS for localhost (optional, for corporate policy): see `references/https-proxy.md` for the Caddy pattern.
28
29	## Prerequisites
30
31	### 1. Screenpipe daemon
32
33	Either install the official release or build from source. Either way the daemon binds HTTP on `localhost:3030` by default.
34
35	From source (recommended if you want the CLI daemon without the desktop GUI):
36
37	```bash
38	git clone --depth 1 https:/

People who liked this also viewed

6 picks

Type

autoskill

712installs3.1kforks

View on GitHub

How to install autoskill?

k-dense-ai/scientific-agent-skills/autoskill

$npx -y skills add K-Dense-AI/scientific-agent-skills --skill autoskill

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# autoskill
2
3	> Requires a running [screenpipe](https://github.com/screenpipe/screenpipe) daemon. This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http://localhost:3030`). If the daemon isn't running, `run()` raises `ScreenpipeUnreachable` with install instructions.
4
5	> Network access & environment variables. This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http://localhost:1234/v1` (LM Studio, default), `https://api.anthropic.com` (opt-in Claude), or a user-supplied BYOK Foundry gateway. The skill reads three environment variables — `SCREENPIPE_TOKEN`, `ANTHROPIC_API_KEY`, `FOUNDRY_API_KEY` — and uses each only to authenticate to the single endpoint its name implies. No other network destinations, no telemetry, no data egress to any third party.
6
7	## Overview
8
9	Turn the user's own workflow history — captured passively by the local [screenpipe](https://github.com/screenpipe/screenpipe) daemon — into new skills. This skill is on-demand: the user invokes it with a time window, it queries screenpipe's local HTTP API, clusters repeated workflow patterns, compares each pattern against the existing skills in this repo, and produces a staged folder of proposals the user can review, edit, and promote.
10
11	## When to Use This Skill
12
13	Invoke this skill when the user asks to:
14	- "Analyze my last 4 hours / day / week and propose new skills."
15	- "Look at what I've been doing and tell me what's not covered yet."
16	- "Draft a skill from my recent workflow."
17	- "Find composition recipes for workflows I repeat."
18
19	Do not invoke it for one-off questions about screenpipe itself, for real-time screen queries, or without an explicit user request — the skill analyzes sensitive local content and must stay explicitly user-triggered.
20
21	## Privacy Posture
22
23	- Screenpipe handles app/window filtering at capture time. Install a starter deny-list by copying `references/screenpipe-config.yaml` into the user's screenpipe config. Sensitive apps (password managers, messaging, banking) are never OCR'd in the first place.
24	- Raw OCR never leaves the machine. `scripts/fetch_window.py` pulls data over localhost HTTP. `scripts/cluster.py` reduces the timeline to app/duration/title summaries. `scripts/redact.py` strips emails, API keys, bearer tokens, and phone numbers as defense-in-depth before any cluster summary reaches the LLM.
25	- LLM backend defaults to `local`. The recommended setup is [LM Studio](https://lmstudio.ai/) running `Gemma-4-31B-it` — strong reasoning at a size that fits on most workstation GPUs, and no data ever leaves your machine. Cloud backends (`claude`, `foundry`) are opt-in and documented in `config.yaml` for users who explicitly want them. Detection and embeddings always run locally regardless of backend choice.
26	- Dry-run mode (`--plan`) prints the exact timeline that will be analyzed before any LLM call.
27	- TLS for localhost (optional, for corporate policy): see `references/https-proxy.md` for the Caddy pattern.
28
29	## Prerequisites
30
31	### 1. Screenpipe daemon
32
33	Either install the official release or build from source. Either way the daemon binds HTTP on `localhost:3030` by default.
34
35	From source (recommended if you want the CLI daemon without the desktop GUI):
36
37	```bash
38	git clone --depth 1 https:/

People who liked this also viewed

6 picks

Type