agent hive

HR & RECRUITING

De-Identify Candidate GitHub Take-Home Repos

When a candidate's code take-home repo is submitted, clones it, rewrites the git author identity and README to a blind code.

CategoryHR & Recruiting
Enginesim
Difficultyadvanced
Triggerwebhook
Steps5
Setup~25 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWebhook receives candidate repo URLHTTP webhook
  • ActionClone repo and rewrite commit author identityShell
  • ActionScrub README and configs of identifiersOpenAI
  • ActionCreate private blind-coded reviewer repo and pushGitHubGitHub
  • OutputSend reviewer repo link to recruiting SlackSlack

What it does

Makes code take-homes truly blind. Candidate repositories carry identity everywhere: commit author names, email addresses, the README header, even the repo name. This workflow ingests a submitted repo, rewrites every author commit to a neutral anonymous identity, removes name traces from the README, and publishes a private reviewer copy named only by blind code.

When to use it

Use it for engineering hiring where candidates submit a Git repository as their take-home. Reviewers should assess code quality, not recognize a name in the commit log. Best when you already collect submissions as repo links or zipped repos in an intake channel.

How it works

  1. 1An incoming webhook fires with the candidate's submitted repo URL.
  2. 2A shell step clones the repo and rewrites all commit author and committer fields to an anonymous identity tied to a freshly minted blind code.
  3. 3An OpenAI step scrubs the README and config files of any name, email, or handle.
  4. 4The workflow creates a new private GitHub repo named by blind code and pushes the rewritten history.
  5. 5Recruiting gets a Slack message with the reviewer repo link and the code mapping.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect HTTP webhookTrigger any URL on agent actions.
  2. 2
    Connect ShellRun sandboxed commands inside the workspace.
  3. 3
    Connect OpenAIModels, embeddings, files.
  4. 4
    Connect GitHubRepos, issues, pull requests, actions.
  5. 5
    Connect SlackChannels, DMs, threads, mentions.
  6. 6
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  7. 7
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  8. 8
    Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.

Run this workflow in your colony.

14-day trial. No DevOps. No Sales call. Provisioned in under a minute.