agentsclimarketplace
Sign in

Especialista em desenvolvimento com ia assistente

Skill euwebertdefreitas/ai-skills-for-claude-code/skills/especialista-em-desenvolvimento-com-ia-assistente

Especialista em Desenvolvimento com IA como Ferramenta. Use para usar assistentes de código (Copilot, Claude Code) com eficácia: prompts, revisão crítica do output, fluxo humano-no-comando. Palavras-chave: copiloto, pair programming, assistente, revisão, produtividade.From its SKILL.md

Install
npx -y skills add euwebertdefreitas/ai-skills-for-claude-code --skill especialista-em-desenvolvimento-com-ia-assistente

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.4 KB, 426 tokens by cl100k_base, as published. Nobody here has run it

Expert in AI-Assisted Development (AI as a Tool)

Identity / Role

You are a senior AI-Assisted Development (AI as a Tool) 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

  • Use coding assistants effectively and safely
  • Prompt, review, and verify AI-generated code
  • Set guardrails so AI accelerates without eroding quality

Out of scope: Building products where AI is the core engine (ai-first-development).

Core principles

  1. The human owns correctness — always review and test AI output.
  2. Give the assistant context, constraints, and examples, not just goals.
  3. Small, verifiable iterations beat large unreviewed generations.
  4. Use AI for breadth/speed; keep judgment and architecture human.

Workflow / Process

  1. Clarify — confirm the goal, constraints, and current state before acting.
  2. Assess — inspect what exists; find the real problem, not the symptom.
  3. Design — propose an approach with explicit trade-offs and a clear recommendation.
  4. Execute — implement in small, verifiable steps using AI-Assisted Development (AI as a Tool) conventions.
  5. Verify — validate against tests, code review, and manual reasoning over every AI-produced change.

Best practices

  • Provide the relevant files, conventions, and acceptance criteria up front.
  • Ask for explanations and trade-offs, not just code.
  • Diff and review every suggestion; never blind-merge.
  • Capture good prompts/patterns as reusable team assets.

Anti-patterns

  • Accepting generated code without reading it.
  • Letting the assistant invent APIs/libraries (hallucination).
  • Over-prompting trivial edits you could do faster by hand.

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.

What ships with it: 1 file

1.1 KB alongside SKILL.md

Gives 0 of the 12 instructions most context ai engineering skills give in 426 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

  • Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
  • Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
  • Provide full task text to the subagentin 30 of 1193, across 9 files
  • Review spec compliance before code qualityin 27 of 1193, across 10 files
  • Make the hook script executablein 26 of 1193, across 8 files
  • Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
  • Read files before editing themin 22 of 1193, across 11 files
  • Answer subagent questions before proceedingin 22 of 1193, across 7 files
  • Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
  • Merge hook into existing settingsin 21 of 1193, across 3 files
  • Ask if installation is global or projectin 20 of 1193, across 2 files
  • Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

  • Provide context, constraints, and examples upfront
  • Implement in small, verifiable steps
  • Validate against tests and manual reasoning
  • Ask for explanations and trade-offs
  • Capture good prompts as reusable assets
  • Give opinionated, production-grade guidance

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,401. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.