develop-screenpipe-win…
Develop and test Screenpipe Windows-native changes on a disposable Azure VM created from the…
Identify repeated work from recorded activity and assess which steps could be automated.
$ npx -y skills add screenpipe/screenpipe --skill screenpipe-workflow-discovery --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/screenpipe-workflow-discoveryContext preview
The summary Claude sees to decide when to auto-load this skill.
Identify repeated work from recorded activity and assess which steps could be automated.
name: screenpipe-workflow-discovery description: "Identify repeated work from recorded activity or starred examples and assess which steps could be automated."
Resolve the work area and review period. Use screenpipe-api to find multiple distinct occurrences of a candidate workflow. Describe the trigger, inputs, observed steps, outputs, exceptions, and human decisions with source pointers.
Count independent occurrences, not repeated frames or repeated discussion of one occurrence. Separate observed steps from inferred steps. If timing matters, use authoritative active time where available and label missing coverage; frame counts are not effort.
Assess a small automation candidate by its available tools, permissions, reversible boundaries, and observable completion criterion. Identify the decisions that still require a person. Do not claim time savings without a baseline or create a schedule, integration, or external action merely from discovering a pattern.
For starred work, retrieve captured evidence directly with screenpipe-api's starred-only search and a bounded time range. For broader workflow review, use the activity summary's starred intervals to prioritize existing evidence; retrieve missing steps only when needed. A star indicates intent, not repetition, completion or time savings. Do not add interval history to standing prompts.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
Repo: mediar-ai/screenpipe
Develop and test Screenpipe Windows-native changes on a disposable Azure VM created from the…
Release the screenpipe monorepo. Bumps versions, triggers GitHub Actions for app, CLI, MCP,…
Query the user's local and synced-device Screenpipe data via the REST API at localhost:3030.…
Manage screenpipe pipes (scheduled AI automations) and connections (Telegram, Slack, Discord,…
Check Screenpipe health status, process state, and diagnose common issues
Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging