Agent Claude Code
Compliance audit — LGPD, GDPR, HIPAA, SOX, PCI-DSS, ISO regulations.
Agent Claude Code
Compliance audit — LGPD, GDPR, HIPAA, SOX, PCI-DSS, ISO regulations.
Agent Claude Code
Performance audit — N+1 queries, unbounded loops, missing indexes, payload sizes, caching, pagination.
Agent Claude Code
Quality audit — tests, observability, performance, documentation, Definition of Done.
Agent Claude Code
Security audit — OWASP, secrets, injection, auth, dependencies.
Command Claude Code
Clean AI-generated slop from code.
Command Claude Code
Scan codebase for technical debt and produce a prioritized report.
Command Claude Code
Systematic debugging: reproduce, isolate, hypothesize, fix, verify, document.
Command Claude Code
Run the project deploy checklist.
Command Claude Code
Legacy code archaeology and context bootstrap. Reads code, git history, Jira (when configured), and remote PRs/issues to reconstruct WHY a module exists. Produces discovery notes in memory/, ADR candidates and PRD candidates in docs/ for human review, then re-indexes memory.
Command Claude Code
Implement a feature from a PRD.
Command Claude Code
Analyze recent work and extract patterns to improve skills and conventions.
Command Claude Code
Long-term memory operations for the project.
Command Claude Code
Persistence mode: implement from PRD and don't stop until all acceptance criteria pass.
Command Claude Code
Safe code refactoring: change structure without changing behavior.
Command Claude Code
Run a specification review on the given code or document.
Settings file Claude Code
Agent settings declaring 9 allowed tools.
Skill Claude CodeCodex
Skill "[SPEC] skill-name" from rtazima/claude-proj-blueprint, covering rules, checklist, examples and references.
Skill Claude CodeCodex
Create Architecture Decision Records. Activated when the user mentions ADR, architectural decision, or technical trade-off.
Skill Claude CodeCodex
API design and contract definition. Activated when the user says "design API", "new endpoint", "API contract", "REST", "GraphQL", "OpenAPI", "swagger", "API spec", or wants to define API endpoints before implementation.
Skill Claude CodeCodex
Reconcile a Claude Design handoff bundle (PROMPT.md) with the project's PRD and conventions. Activated when the PRD references a Claude Design handoff, when a PROMPT.md exists in docs/design/, or when the user mentions "Claude Design", "design handoff", or "PROMPT.md".
Skill Claude CodeCodex
Code review following project conventions. Activated when the user asks for a review, CR, or code revision.
Skill Claude CodeCodex
Context engineering — proactive context window management. Activated when working on large tasks, long sessions, multi-file changes, or when context is getting bloated. Keywords: "context", "too much code", "split this task", "focus", "scope down", "token budget", "keep it small". Complements the reactive…
Skill Claude CodeCodex
Legacy code archaeology — multi-phase discovery that reads the codebase, git history, and optionally Jira to reconstruct WHY code exists. Produces discovery notes, ADR candidates, and PRD candidates for human review. Activated when user says 'descobrir módulo', 'arqueologia de código', 'entender legado', 'contexto do…
Skill Claude CodeCodex
Systematic debugging workflow. Activated when the user says "debug", "why is this failing", "root cause", "broken", "investigate", "trace error", "bug", "not working", or wants to systematically investigate a problem.