Liste des compétences Claude

Produces clean, functional code that matches the architecture and checklists.

Cleans up and improves existing code without changing behavior.

Verifies specified behavior through appropriate tests and truthful coverage reports.

Translates user intent into a precise, unambiguous specification and requirements.

Fetch any X/Twitter post as clean LLM-friendly JSON. Converts x.com, twitter.com, or adhx.com links into structured data with full article content, author info, and engagement...

Admin account register: system, main and backup admin, seats, plan, 2FA, shared logins and access-review dates, as CSV, SQL, JSON Schema or Notion on request. Use for access...

Dashboard metric register: metric, source module, formula, period, value, target, trend, owner and last-updated, as CSV, SQL, JSON Schema or Notion on request. Use for KPI...

Design LLM-as-judge rubrics, direct scores and pairwise comparisons. Use for judge models, evals, position bias and calibration against human labels.

Assistente de pesquisa informativa, sem credenciais profissionais, sobre em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas,...

Apoio a pesquisa juridica brasileira, organizacao de fatos e minutas, com verificacao em fontes oficiais e revisao profissional para casos concretos.

Autonomous DevSecOps & FinOps Guardrails. Guide to reviewing Linux kernel patches, Terraform cost changes and Kubernetes policy with a separately reviewed upstream tool and...

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating...

Use when summarizing agent evaluations where autonomous, assisted, failed, timed-out, or invalid outcomes must remain distinct and comparable.

Evaluate agent behavior with versioned cases and explicit verifiers. Use when comparing agent or prompt changes, reproducing failures, or running agent regression tests.

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) in an explicitly authorized workspace.

Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Design tenant-scoped memory, retrieval and retention for agents. Use when planning RAG, conversation history, vector stores or remembering across sessions.