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

How to score the describer and builder with the eval suite with Skill Recorder

Run the fixture-based evals to check how well a Skill generalizes from one recording.

Who it is forA developer changing Skill Recorder's prompts or builder who needs to check that generalization did not regress.

The problemChanges to the describer or builder can quietly weaken the generated Skills, and manual review does not scale.

The outcomeScores for the describer, terminal use, and builder generalization against synthetic recordings.

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. Check out a release revision of the repo.
  2. Run npm ci.
  3. Run npm run compliance:licenses.
  4. Run npm run eval:builder to score the skill and automation generalization.
  5. Run npm run eval and npm run eval:terminal to score the describer and terminal redaction.

Prompt for your agent

Use the microsoft/skill-recorder repo to run the builder eval after my change to <file>. Expected output: scores for skill and automation generalization compared with the previous revision. Verify that the score for terminal redaction did not drop.

Caveat. The README says the developer setup requires Node.js 24, and the eval scripts run against synthetic recordings, not your own work sessions.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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