convez.ai
SkillAutomaçãoAvançado
mattdweigand-sketch

Agent Skills

mattdweigand-sketch/agent-skills

Skills portáteis para agentes: eval loops, research, escrita e limpeza de projetos

Ver no GitHub
InicialPluginScore · de 0 a 100

Biblioteca portátil de skills reutilizáveis para agentes de IA (Codex, Claude Code, Cursor e similares). Cobre fluxos de avaliação, pesquisa, escrita, auditoria de código e higiene de projetos com 16 skills prontos para uso.

Instalação

$npx convez-ai mattdweigand-sketch/agent-skills

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
42%
Último commit
há 4 dias
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Auditar e otimizar alocação de lógica em projetos (60-30-10)
  • Melhorar prompts e workflows através de teste iterativo (autoresearch)
  • Refatorar grandes bases de código com múltiplas worktrees em paralelo
  • Validar se sistemas de julgamento fecham loops entre padrões capturados e resultados reais
  • Humanizar prosa gerada por IA para soar mais natural
  • Definir e auditar estrutura limpa de repositórios

Veredito

Conjunto robusto de skills bem documentado para quem trabalha com agentes de IA em fluxos de desenvolvimento. Excelente para equipes que precisam padronizar e auditar workflows de agentes, embora exija familiaridade com arquitetura de prompts e lógica de avaliação.

README

A tradução para o português deste README ainda está na fila.

Agent Skills

License: MIT

Portable skill library for repo work, eval loops, research, writing, and agent workflow hygiene. These skills are written to work across Codex, Claude Code, Cursor, and other AGENTS-aware tools.

Included Skills

Each skill keeps its full workflow in skills/<skill-name>/SKILL.md.

SkillDescription
60-30-10Evaluate where a project keeps its judgment, and whether the allocation matches the durable shape: mostly owned data, partly deterministic code, only a thin layer of live model.
autoresearchImproves a prompt, config, or workflow by testing one change at a time against a fixed score.
context-window-auditFinds startup context, settings, wrappers, and memory entries that waste context-window space.
cyborg-checkAudits whether a judgment system closes the loop between captured patterns and real outcomes, or is spreading unverified judgment.
humanizerRewrites prose so it sounds clearer, more natural, and less AI-generated.
karpathy-guidelinesKeeps coding work simple, scoped, and easy to verify.
n-agentic-harnessesHelps design or review the system around AI agents, tools, memory, permissions, and evals.
parallel-refactorCoordinates a large refactor across multiple isolated worktrees.
ralf-loopRuns a repeatable test-and-fix loop until the work passes, blocks, or needs a decision.
repo-structure-auditDefines and audits a clean repo layout for code and knowledge projects.
research-synthesisTurns a source set into clear findings, contradictions, gaps, and next questions.
quality-check-evalSorts AI output quality checks into four buckets: automate in code, judge with an LLM, keep for human review, or remove.
run-kitTurns fuzzy agent work into a scoped run, then helps review or cross-check the result.
runtime-guardPrevents an agent from editing or publishing without clearly defined authority, boundaries, stop conditions, or rollback.
skill-creator-v3Creates, improves, tests, and packages reusable skills.
skill-tuneAudit or refactor a skill or prompt artifact for prompt technical debt.
weekly-signal-diff-aiSummarizes what structurally changed in AI this week and why it matters.

Install

Copy all skills into the skill directory used by your agent:

cp -R skills/* ~/.agents/skills/

For Codex, use:

cp -R skills/* ~/.codex/skills/

Install one skill by copying only that folder:

cp -R skills/ralf-loop ~/.agents/skills/ralf-loop

License

MIT

Ver o original no GitHub

Bom para

Relacionados