MILTONADINA
@MILTONADINA
Public Skills
plan-decomposition
by MILTONADINA
Break an approved spec into atomic, ordered, verifiable tasks before any code is written. Use after spec-extraction confirms a spec is approved and before invoking goal-loop. Each task has its own success criteria, estimated effort, and explicit dependencies. Prevents both "where do I start" paralysis and "ship-and-pray" rushes.
baton-handoff
by MILTONADINA
Write a complete handoff document at session end so the next agent (Claude Code, Codex, Cursor, Antigravity, Kiro, or local LLM) resumes exactly where this one stopped. Use whenever a session is approaching its limit, the user types /checkpoint, or the agent recognizes natural completion of a task. Surgical honesty - no context loss across tool boundaries.
coppa-audit
by MILTONADINA
Audit code, data flows, and UI for COPPA (Children's Online Privacy Protection Act) compliance. Use whenever the project handles or might handle data from users under 13 - kid-targeted apps, educational tools, or general apps with under-13 user segments. Triggers on terms like "children", "minor", "under 13", "K-12", "education", "kid", "youth".
openapi-first
by MILTONADINA
Generate API code, types, validators, mock servers, and client SDKs from a single OpenAPI 3.1 specification. Use whenever building or modifying an HTTP API endpoint. The OpenAPI doc is source of truth - drift between doc and code is a contract violation caught by tests. Triggers on requests involving REST endpoints, API design, or client/server contracts.
owasp-asi-threat-model
by MILTONADINA
Produce a STRIDE + OWASP Top 10 for Agentic Applications (ASI) 2026 threat model for any new feature, API, or system. Use whenever designing a feature that touches auth, data, agents, tools, or external inputs. Triggers on terms like "design", "architecture", "new endpoint", "new agent", "new MCP", or "security review". The ASI 2026 framework (released Dec 2025) is the industry standard for agentic AI security.
observability-instrument
by MILTONADINA
Add OpenTelemetry spans with user_id and tenant_id in baggage to any new code path that handles requests, runs agents, or performs billable operations. Use whenever creating a new API endpoint, background job, agent invocation, or external API call. Inline PII redaction at the span exporter is mandatory before any production deploy.