Explorar skills

Test authentication and session management controls for bypass and account takeover scenarios.

Set up authorized C2 simulation workflows and measure defensive detection outcomes.

Generate production-ready CRUD REST API endpoints with validation, auth, error handling, pagination, tests, and OpenAPI docs. Auto-triggers when asked to create API endpoints, REST resources, or backend CRUD operations.

Use when running the full audit sweep on a scope — runs the focused audit dimensions (necessity, structure, patterns, correctness, error handling, logs, perf, security, tests, complexity, comments) as a parallel-worktree workflow that integrates in dependency order. Triggers on "audit", "full audit", "audit everything".

Integrate authentication and authorization flows with provider-specific setup and RBAC safeguards.

Use when the user has an error, bug, stack trace, failing test, or unexpected behavior to diagnose.

Test API endpoints for correctness, edge cases, auth handling, and OpenAPI contract compliance.

Assess mobile applications with static and dynamic analysis aligned to OWASP MASTG and MASVS.

Polish a long-form technical draft for pacing, scan-ability, and tightness. Cover paragraph and sentence rhythm, the scan reader's experience (headings, callouts, pull quotes, white space, lists, tables), the 30% cut discipline for removing filler, and the read-aloud test for finding bumps. Distinct from short-form line-level editing — this skill works at the paragraph and section level for pieces

MCP (Model Context Protocol) server development — use when the user mentions MCP, Model Context Protocol, FastMCP, MCP server, MCP tool, Claude Code plugin, or building agent tools with MCP. Covers server implementation in Python or TypeScript, evaluation testing, production deployment, and plugin packaging. NOT for designing tool interfaces or tool consolidation patterns for agents (use tool-desi

Plan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize tracking-ready experiment definitions.

Generates comprehensive unit tests for any function or module with edge cases.