Write once, runs everywhere

Look again at where you were told to put the skill: .github/skills, .claude/skills, or .agents/skills. Those last two names should have nagged at you. Why would a Copilot feature read a folder named .claude? Because it isn’t a Copilot feature. Agent Skills is an open standard, and the SKILL.md you just wrote is not a Copilot file that happens to work elsewhere — it’s a standard file that Copilot happens to read.

One file, every surface

The audit-event skill you authored is understood across Copilot’s own surfaces without any change:

• VS Code — where you’ve worked this whole chapter, Copilot pulls it in when a task matches the description.
• The Copilot CLI — the same skill, same folder, applied from the terminal.
• The cloud coding agent — when you reach the automation chapter and hand a follow-up issue to Copilot to resolve in the background, it sees the audit-event skill too, and the draft PR it opens follows your convention without you re-stating it.

So the procedure you wrote once travels with the work, whoever — or whatever — picks it up.

The convergence payoff

Now the part that reaches past Copilot entirely. Back in the Rules chapter you saw the first convergence beat: the AGENTS.md and CLAUDE.md files you’d written for another agent were read natively by Copilot, no translation. The same context, honored by a different tool.

Skills are the second beat of the same story. The SKILL.md you wrote for the audit-event convention here is the exact file format a reader wrote for the Claude Code course and the Codex course. If you authored an audit-event skill there, it works here unchanged. If you write it here, it works there. The folder names — .claude/skills, .agents/skills — are the standard announcing itself: these tools agreed to read the same files on purpose.

That’s the quiet thesis of this whole site arriving twice over. The hard part of working with agents isn’t the tool — it’s closing the gap between what the agent knows and what your team knows: your conventions, your procedures, the audit-event shape everyone on the Platform squad has in their head. You close that gap by writing it down once. Rules proved your always-on context survives the jump between tools. Skills prove your invokable procedures do too. You’re not re-teaching the audit convention to each new agent you adopt — you taught it once, in a standard format, and every conforming tool already speaks it.

Where this leaves the work

You’ve now packaged the team’s audit-event convention as a portable skill Copilot invokes on its own, in both repos, in a format your other agents already understand. The procedure is handled. What’s still missing is reach: the skill knows how to record an event, but it can’t yet see the internal systems the work depends on — the issue tracker, the service registry that lists which of the dozen consumers a shared-lib change touches. To give Copilot a live line into a system outside the repo, you wire up an MCP server. Next chapter: extending Copilot over MCP.