← back
Combine Skills and MCP to Close the Context Gap — Pedro Rodrigues, Supabase
Takeaway
MCP supplies access, while carefully structured skills supply the product knowledge needed to use that access correctly.
Summary
- A Supabase experiment compared MCP alone with MCP plus a skill; only the latter correctly set security_invoker=true for a view over RLS-protected data.
- Product skills should direct agents to current documentation instead of duplicating facts that become stale.
- Critical security guidance belongs in SKILL.md because agents may skip linked reference files.
- Supabase encodes an opinionated schema workflow: iterate in development, run advisors, fix issues, and then create migration files; it also experiments with documentation access over SSH.
supabaseagent-skillsmcp
Original description
Agents working with Postgres will confidently create a view over a table with row-level security enabled and silently bypass that security in the process. Not because they can't reason. Because they don't know about the security_invoker flag, and nobody told them. Pedro Rodrigues from Supabase ran this exact test: same agent, same task, MCP alone versus MCP plus a skill. The one without the skill shipped a query that exposed data it shouldn't have. The talk covers what Supabase learned building their agent skill from scratch: critical security rules go directly in skill.md because agents will reliably skip reference files, skills should point to living documentation rather than duplicate it, and opinionated workflow guidance matters more than comprehensive coverage. Their evals ran across Claude and GPT models in three conditions and the result was unanimous. Skills without MCP underperform. MCP without skills misses environment-specific constraints. Together they close the gap that makes agents unreliable on real production systems. Speaker info: https://x.com/rodriguespn23 / pedro-neves-rodrigues https://github.com/Rodriguespn