diff --git a/skills/vercel-sandbox/SKILL.md b/skills/vercel-sandbox/SKILL.md
index df6d0cb..ce61079 100644
--- a/skills/vercel-sandbox/SKILL.md
+++ b/skills/vercel-sandbox/SKILL.md
@@ -1,7 +1,7 @@
 ---
 name: vercel-sandbox
 description: Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
-summary: "Run untrusted/AI-generated code in ephemeral Firecracker microVMs via @vercel/sandbox. Core loop: `const s = await Sandbox.create(); try { const r = await s.runCommand('python3', ['-c', code]); } finally { await s.stop(); }`. runCommand has no shell (wrap pipes/redirects in `bash -c`) and does not throw on non-zero exit (check r.exitCode). Default image is Ubuntu (`apt-get update` before install). Persistence is on by default (auto-snapshot on stop, resume by name; only the filesystem survives). For untrusted code use `networkPolicy: 'deny-all'`, a short `timeout`, and `persistent: false`. Credential brokering: a firewall `transform` injects a secret header on egress so the VM never holds it. AI agents reach models with no API key via the AI Gateway (`https://ai-gateway.vercel.sh`, `Authorization: Bearer $VERCEL_OIDC_TOKEN`) — the token is not auto-injected, so pass it via `env` or broker it. Full docs: https://vercel.com/docs/sandbox"
+summary: "Run untrusted/AI-generated code in ephemeral Firecracker microVMs via @vercel/sandbox. Core loop: `const s = await Sandbox.create(); try { const r = await s.runCommand('python3', ['-c', code]); } finally { await s.stop(); }`. runCommand has no shell (wrap pipes/redirects in `bash -c`) and does not throw on non-zero exit (check r.exitCode). Default image is Ubuntu (`apt-get update` before install). Persistence is on by default (auto-snapshot on stop, resume by name; only the filesystem survives). For untrusted code use `networkPolicy: 'deny-all'`, a short `timeout`, and `persistent: false`. Credential brokering: a firewall `transform` injects a secret header on egress so the VM never holds it. AI agents reach models with no API key via the AI Gateway (`https://ai-gateway.vercel.sh`, `Authorization: Bearer $VERCEL_OIDC_TOKEN`) — the token is not auto-injected, so pass it via `env` or broker it. Drive sizes must be multiples of 4096 bytes. Full docs: https://vercel.com/docs/sandbox"
 metadata:
   priority: 4
   docs:
diff --git a/skills/vercel-sandbox/overlay.yaml b/skills/vercel-sandbox/overlay.yaml
index fd5f91f..c8e053b 100644
--- a/skills/vercel-sandbox/overlay.yaml
+++ b/skills/vercel-sandbox/overlay.yaml
@@ -1,6 +1,6 @@
 name: vercel-sandbox
 description: Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
-summary: "Run untrusted/AI-generated code in ephemeral Firecracker microVMs via @vercel/sandbox. Core loop: `const s = await Sandbox.create(); try { const r = await s.runCommand('python3', ['-c', code]); } finally { await s.stop(); }`. runCommand has no shell (wrap pipes/redirects in `bash -c`) and does not throw on non-zero exit (check r.exitCode). Default image is Ubuntu (`apt-get update` before install). Persistence is on by default (auto-snapshot on stop, resume by name; only the filesystem survives). For untrusted code use `networkPolicy: 'deny-all'`, a short `timeout`, and `persistent: false`. Credential brokering: a firewall `transform` injects a secret header on egress so the VM never holds it. AI agents reach models with no API key via the AI Gateway (`https://ai-gateway.vercel.sh`, `Authorization: Bearer $VERCEL_OIDC_TOKEN`) — the token is not auto-injected, so pass it via `env` or broker it. Full docs: https://vercel.com/docs/sandbox"
+summary: "Run untrusted/AI-generated code in ephemeral Firecracker microVMs via @vercel/sandbox. Core loop: `const s = await Sandbox.create(); try { const r = await s.runCommand('python3', ['-c', code]); } finally { await s.stop(); }`. runCommand has no shell (wrap pipes/redirects in `bash -c`) and does not throw on non-zero exit (check r.exitCode). Default image is Ubuntu (`apt-get update` before install). Persistence is on by default (auto-snapshot on stop, resume by name; only the filesystem survives). For untrusted code use `networkPolicy: 'deny-all'`, a short `timeout`, and `persistent: false`. Credential brokering: a firewall `transform` injects a secret header on egress so the VM never holds it. AI agents reach models with no API key via the AI Gateway (`https://ai-gateway.vercel.sh`, `Authorization: Bearer $VERCEL_OIDC_TOKEN`) — the token is not auto-injected, so pass it via `env` or broker it. Drive sizes must be multiples of 4096 bytes. Full docs: https://vercel.com/docs/sandbox"
 metadata:
   priority: 4
   docs: