Autoskill

--- name: autoskill description: Monitor the user's screen via screenpipe, detect repeated research-workflowss, match them against existing scientific-agent:skills:and draft new skills (or composition recipes that chain existing ones) for patterns not yet covered. Use this when a user asks to analyze their recent work and propose skills based on their actual activities. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030:skills have no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM. allowed-tools: Read Write Edit Bash license: MIT license requiredenvironmentvariables: [{"name": "SCREENPIPETOKEN", "prompt": "Auth token for the local screenpipe daemon.", "requiredfor": "full functionality"}, {"name": "ANTHROPICAPIKEY", "prompt": "For Claude API calls during skill drafting.", "requiredfor": "optional features"}, {"name": "FOUNDRYAPIKEY", "prompt": "Optional Foundry access for drafting.", "requiredfor": "optional features"}] metadata: {"version": "1.1", "skill -author": "K-Dense Inc.", "openclaw": {"requires": {"bins": ["screenpipe"]}, "primaryEnv": "SCREENPIPETOKEN", "envVars": [{"name": "SCREENPIPETOKEN", "required": true, "description": "Auth token for the local screenpipe daemon."}, {"name": "ANTHROPICAPIKEY", "required": false, "description": "For Claude API calls during skill drafting."}, {"name": "FOUNDRYAPIKEY", "required": false, "description": "Optional Foundry access for drafting."}]}} --- # autoskill > 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 installation instructions. > 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 implied by its name. No other network destinations, no telemetry, no data egress to any third party. ## Overview 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 that the user can review, edit, and promote. ## When to Use This Skill Invoke this skill when the user asks to: - "Analyze my last 4 hours / day / week and suggest new skills." - "Look at what I've been doing and tell me what hasn't been covered yet." - "Draft a skill based on my recent workflow." - "Find composition recipes for workflows I repeat." Do not invoke it for one-off questions about Screenpipe itself, for real-time screen queries, or without an explicit user request:skills analyzes sensitive local content and must remain explicitly user-triggered. ## Privacy Posture - 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. - Raw OCR data 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 out emails, API keys, bearer tokens, and phone numbers as a defense-in-depth measure before any cluster summary reaches the LLM. - **LLM backend defaults to local.** The recommended setup is LM Studio running `Gemma-4-