HR & RECRUITING

Build a Team Skills Inventory from GitHub Shipped Work

On a weekly schedule, scans the team's merged GitHub work to infer which languages, frameworks, and tools each engineer actually ships.

CategoryHR & Recruiting
Enginesim
Difficultyintermediate
Triggerschedule
Steps4
Setup~15 min

How it runs

The automated pipeline, trigger to output.

  • TriggerWeekly schedule fires
  • ActionFetch merged PRs and changed filesGitHubGitHub
  • LogicDerive normalized skills per contributor
  • OutputUpsert skills inventory to AirtableAirtableAirtable

What it does

This workflow turns shipped code into a living skills inventory. Once a week it pulls merged pull requests across your repositories, reads the file extensions, dependency manifests, and CI config touched in that work, and maps each contributor to the technologies they demonstrably used. The result is an Airtable table of people-to-skills with evidence and a last-seen date.

When to use it

Use it when self-reported skills drift from reality and you need an objective baseline before planning headcount or training. It is the foundation the other gap-mapping workflows read from.

How it works

  1. 1A weekly schedule fires the run.
  2. 2It fetches merged pull requests and changed files from GitHub for the lookback window.
  3. 3A logic step parses manifests and extensions to derive a normalized skill set per author, deduplicating against known aliases.
  4. 4It upserts each contributor's skills, evidence links, and last-used date into the Airtable skills inventory.
  5. 5The updated inventory is the deliverable other workflows query.

Set it up

What you configure once, before turning it on.

  1. 1
    Connect GitHubRepos, issues, pull requests, actions.
  2. 2
    Connect AirtableBases, tables, views, automations.
  3. 3
    Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
  4. 4
    Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
  5. 5
    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.