DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to teach agents your standards with skills and briefs with Agents Office

Give agents a brief or a skill so their output follows how you actually work.

Who it is forA team lead whose first agent results are generic and who wants them to match a house style, template or set of red lines.

The problemOut of the box agents know only a one-line job, so results need heavy rewriting before anyone can use them.

The outcomeA skill folder or brief that the agent reads before each task, plus a feedback file that records your corrections as rules.

What you need first

  • macOS or Linux (Windows can use the npm commands directly, since ./setup is Bash only)
  • Node.js 20+
  • git
  • Claude Code logged in with your Claude account, or an ANTHROPIC_API_KEY (tool use needs the Claude Code login)

Steps

  1. Open your brain folder and create a skill folder under Agents Office/skills with a SKILL.md file and the template beside it.
  2. Bind the skill to an agent or department in its front matter, or add a brief field to that agent in office.agents.local.json.
  3. Run npm run check to validate the skills and briefs.
  4. Open http://localhost:4520/api/skills to confirm who has which skill.
  5. Send a deliverable back with revise: ... in the agent's chat so the correction is recorded as a standing rule or a one-off. (inferred, check the README)

Prompt for your agent

In the agents-office repo at https://github.com/ajsahni/agents-office, write a skill for the <agent name> agent from the example document <path to example>. Run npm run check and report the skill file created and any validation errors. Verify http://localhost:4520/api/skills lists the skill for that agent.

Caveat. Skills and briefs take effect on the next task with no restart, but agents only use what is in your brain folder and the shipped roster.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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