feat: add agent-os bootstrap bundle

bootstrap/templates/generic/skills/_template/context/handoff.md

@@ -0,0 +1,21 @@
+# Handoff
+
+## Objective
+
+-
+
+## Completed
+
+-
+
+## Validation
+
+-
+
+## Risks
+
+-
+
+## Next Action
+
+-

bootstrap/templates/generic/skills/_template/eval.json

@@ -0,0 +1,17 @@
+{
+  "schema_version": 1,
+  "criteria": [
+    {
+      "name": "correctness",
+      "description": "The skill produces the requested result without inventing facts."
+    },
+    {
+      "name": "safety",
+      "description": "The skill respects credentials, approvals, and operational limits."
+    },
+    {
+      "name": "handoff_quality",
+      "description": "The skill writes clear output and next steps for humans or other agents."
+    }
+  ]
+}

bootstrap/templates/generic/skills/_template/learnings.md

@@ -0,0 +1,5 @@
+# Learnings
+
+Append stable lessons from real runs. Keep this concise and actionable.
+
+-

bootstrap/templates/generic/skills/_template/skill.md

@@ -0,0 +1,26 @@
+# Skill Name
+
+## Purpose
+
+Describe what this skill does and when an agent should use it.
+
+## Inputs
+
+-
+
+## Workflow
+
+1. Read the relevant context.
+2. Perform the smallest safe action that satisfies the request.
+3. Write outputs to the documented runtime paths.
+4. Record useful learnings in `learnings.md`.
+
+## Outputs
+
+- `/opt/agent-os/logs/<agent>/last-run.json`
+- `/opt/sites/<short-name>/last-output.md`
+
+## Safety
+
+- Do not expose secrets.
+- Ask for approval before destructive or high-impact actions.