DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to capture a terminal workflow as a Skill with native tools with Skill Recorder

Record commands run in the app's recorded terminal and turn them into a Skill that uses native tools.

Credentials. Commands and terminal output are captured in the session, so any token or password typed or printed in the terminal can end up in the analysis sent to GitHub's cloud.

Who it is forA developer or DevOps engineer who runs the same command sequence in a terminal and wants an agent to repeat it.

The problemReplaying terminal steps by hand is error-prone, and agents work better with direct tool calls than with copied keystrokes.

The outcomeA Skill that uses native tools such as the gh CLI where possible, built from the commands and output you recorded.

What you need first

  • A GitHub account with Copilot access (the Copilot CLI ships with the app)
  • macOS, Windows 11 (x64 or ARM64), or Ubuntu
  • Screen Recording permission on macOS, granted on first launch
  • Node.js 24 only if you develop from source

Steps

  1. Open the session-scoped terminal from the floating recording bar while recording.
  2. Run the command sequence for the task, keeping secrets out of the terminal.
  3. Finish the recording, then click Analyze and review the intent and ordered steps.
  4. Choose Review SKILL.md to confirm the Skill prefers native tools, then add or export it.

Prompt for your agent

Use the Skill Recorder repo at microsoft/skill-recorder to convert my terminal session for <workflow> into a Skill. Expected output: a SKILL.md that calls native tools such as the gh CLI instead of replaying keystrokes. Verify that no secrets appear in the generated file.

Caveat. The recorded terminal captures only the app-owned terminal for that recording, not your other terminal windows.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page