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

How to let Codex run browser-grounded social research with Jev Social

Install the Jev Social skill into Codex so it can run cited social research for you.

  • Research
  • Intermediate
  • 30 minutes
  • From the README
  • Codex

Credentials. The skill drives your signed-in Chrome session, so use a separate profile or test account for sensitive research.

Who it is forA developer already working in Codex who wants social research done inside that agent session.

The problemSwitching between an agent and a separate research tool breaks the workflow, and raw run output is hard to use.

The outcomeCodex returns source-linked evidence instead of raw run JSON, using the read-only Jev Social workflow.

What you need first

  • Node 22 or newer
  • Chrome already signed in to Instagram, TikTok, or LinkedIn
  • An OpenRouter API key for the default decision provider
  • A current socai CLI (onboarding can install it on macOS and Windows; on Linux install it first and set it on PATH or SOCAI_BIN)

Steps

  1. Install GitHub CLI 2.101 or newer.
  2. gh skill install socai-io/jev-social [email protected] --agent codex --scope user
  3. Confirm a current socai CLI is installed and Chrome is signed in to the target platform.
  4. Ask Codex to research a specific goal on Instagram, TikTok, or LinkedIn.
  5. Check that returned findings cite captured source URLs and that platform availability was checked.

Prompt for your agent

With the jev-social skill installed in Codex, research <goal> on <platform> using the local socai CLI. Expected output: a short evidence summary with captured source URLs. Verify that login-gated or failed steps are reported as partial results.

Caveat. The skill pins the v0.1.13 release and requires GitHub CLI 2.101 or newer, so older GitHub CLI versions will not work.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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