Benjamin Cane

#Bengineering 🧐

Short-form distributed-systems tradeoffs, reliability patterns, lessons learned, and leadership notes — shared weekly.

35 posts August 8, 2025 → April 9, 2026
Portrait of Benjamin Cane

Subscribe to:

#Bengineering 🧐

Prefer your posts in a reader? Subscribe to the RSS feed or catch me on LinkedIn.

RSS Feed LinkedIn

Latest Drop

Portrait of Benjamin Cane
Benjamin Cane
April 9, 2026

Use Agent Skills to capture institutional knowledge and make it usable by coding agents.

Every organization has institutional knowledge.

  • Internal frameworks
  • Preferred practices
  • Platform-specific capabilities

It exists everywhere. But it’s often undocumented… or buried in a wiki no one reads.

As coding agents take on more work, this problem gets worse.

If you ask an agent to build a new service, you want it to use your internal framework, follow your patterns, and respect your organizational constraints.

A human engineer would ask questions. An agent won’t, unless you give it that context.

📚 Agent Skills as Knowledge Distribution

Most people think about Agent Skills as actions:

  • Convert markdown to PDF
  • Review this pull request
  • Commit my changes

But the more interesting use case is guidance.

Skills aren’t just for doing things. They’re for shaping agent output.

Agents discover and use skills based on intent.

If a user asks: “Create a new Python service.”

The agent looks for relevant skills:

  • Language conventions (PEP 8, etc.)
  • Internal frameworks
  • Organizational standards

That’s where institutional knowledge belongs.

Instead of hoping engineers remember to tell the agent:

  • “We use Flask, not Django.”
  • “Stick to the standard library.”
  • “Follow this service layout.”

You capture that into a skill. The agent applies it automatically.

🧠 Why This Matters

Institutional knowledge only works if it's:

  • Discoverable
  • Applied consistently

Agent Skills give you both.

They turn tribal knowledge into something agents can find, understand, and use.

⚠️ The Tradeoff (For Now)

Right now, this introduces duplication.

Most teams already have internal docs, style guides, & wikis.

And now you’re putting the same information into skills. Which feels like extra work.

But it poses an interesting question:

As agents become the primary interface… Will engineers read the wiki? Or ask the agent?

🧠 Final Thoughts

As agents take on more of the implementation work, where you store knowledge becomes more important. Making that knowledge accessible to agents becomes essential.

Agent Skills aren’t just automation tools.

They are becoming the interface for standards, practices, and institutional knowledge.

And teams that embrace that early will see more consistent output from both humans and agents.

Previous Posts

  • April 2, 2026 Saved Prompts Are Dead. Agent Skills Are the Future.
  • March 26, 2026 Generating Code Faster Is Only Valuable If You Can Validate Every Change With Confidence
  • March 19, 2026 When You Go to Production with gRPC, Make Sure You’ve Solved Load Distribution First

Archive

  • April 9, 2026
  • April 2, 2026
  • March 26, 2026
  • March 19, 2026
  • March 12, 2026
  • March 5, 2026
  • February 26, 2026
  • February 19, 2026
  • February 12, 2026
  • February 5, 2026
  • January 29, 2026
  • January 22, 2026
  • January 15, 2026
  • January 8, 2026
  • January 1, 2026
  • December 26, 2025
  • December 19, 2025
  • December 12, 2025
  • December 5, 2025
  • November 28, 2025
  • November 21, 2025
  • November 14, 2025
  • November 7, 2025
  • October 31, 2025
  • October 27, 2025
  • October 24, 2025
  • October 10, 2025
  • October 3, 2025
  • September 26, 2025
  • September 19, 2025
  • September 12, 2025
  • September 5, 2025
  • August 22, 2025
  • August 15, 2025
  • August 8, 2025

Made with Eleventy and a dash of #Bengineering energy.