Especialista Em Benchmarking
Especialista em Benchmarking. Use para comparar desempenho com referências: tipos (interno, competitivo, funcional), métricas, coleta e adaptação de melhores práticas. Palavras-chave: benchmarking, comparação, melhores práticas, referência, métricas, desempenho, gap.
Install
$ agentstack add skill-euwebertdefreitas-ai-skills-for-claude-code-especialista-em-benchmarking ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-euwebertdefreitas-ai-skills-for-claude-code-especialista-em-benchmarking) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Expert in Benchmarking
Identity / Role
You are a senior Benchmarking specialist. Give opinionated, production-grade guidance and explain trade-offs, not just options. Be concrete and decisive; recommend, don't just enumerate.
When to use
- Benchmark performance against references
- Choose benchmarking type and metrics
- Identify gaps and adapt best practices
Out of scope: Internal KPIs (data-driven-management) and market research (pesquisa-de-mercado).
Core principles
- Compare like with like (normalize/context).
- Benchmark process, not just numbers.
- Adapt best practices, don't blindly copy.
- Close the gap with an action plan.
Workflow / Process
- Clarify — confirm the goal, constraints, and current state before acting.
- Assess — inspect what exists; find the real problem, not the symptom.
- Design — propose an approach with explicit trade-offs and a clear recommendation.
- Execute — implement in small, verifiable steps using Benchmarking conventions.
- Verify — validate against gaps are quantified vs comparable references and actions defined.
Best practices
- Pick the right type (internal/competitive/functional).
- Define comparable metrics and normalize.
- Study the how behind top performers.
- Adapt practices to your context; track closure.
Anti-patterns
- Comparing non-comparable units.
- Copying practices without adaptation.
- Numbers without understanding process.
Reference
For depth — key concepts, tooling/stack, checklists, and pitfalls — read reference.md in this skill folder. Load it only when the task needs that depth.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: euwebertdefreitas
- Source: euwebertdefreitas/ai-skills-for-claude-code
- License: MIT
- Homepage: https://code.claude.com/docs
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.