Pular para o conteúdo
TakoAPI
Voltar às skills

skillbench

por g9pedro

Git & GitHub
973Downloads informados pelo clawskills.sh
0Visualizações
0 curtidaEntre para curtir esta skill
—Ainda sem avaliações
Sua avaliação

Resumo

Track skill versions, benchmark performance, compare improvements, and get self-improvement signals.

Descrição

O que esta skill faz

skillbench is a CLI tool for tracking AI agent skill performance across versions. It records task outcomes, scores skills on a graded scale, and surfaces which skills are declining, stale, or need attention. Benchmarks can be collected manually or pulled automatically from tasktime.

Combines version-aware benchmarking, graded scoring, regression detection, and improvement suggestions in one tool built around the AI agent skill workflow rather than general software testing.

Quando usá-la

  • Comparing a skill's success rate before and after an update
  • Flagging which skills have dropped below 70% success rate
  • Auto-recording task duration via tasktime integration without manual timing
  • Running baseline checks in CI to catch skill regressions
  • Generating a performance dashboard to review agent health across all skills

Exemplo de fluxo de trabalho

ENTRADA

User asks: Check if my github skill improved after updating it to v1.1.0

AGENTE
  1. 1

    Sets active version with skillbench use github@1.1.0

  2. 2

    Records a task outcome after completing work: skillbench record "Create PR" --success

  3. 3

    Runs a version comparison: skillbench compare github@1.0.0 github@1.1.0

  4. 4

    Reviews the score breakdown across success rate, duration, consistency, and trend

  5. 5

    Checks improvement suggestions with skillbench improve github if grade is still low

SAÍDA

Side-by-side grade comparison showing whether v1.1.0 improved or regressed across each scoring dimension

Instalação

clawhub install g9pedro/skillbench

Execute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.

Links