Skip to content

aipoch/open-science / resources/skills/skill-creator

skill-creator

Verified

Create, revise, evaluate, publish, and improve Open-Science Skills through the native JavaScript host.skills composer. Use when the user wants a reusable workflow, an existing Skill changed, test cases or benchmarks for a Skill, or better Skill triggering.

assets/eval_review.html

View on GitHub
<!doctype html>
<html lang="en">
  <head>
    <meta charset="utf-8" />
    <meta name="viewport" content="width=device-width,initial-scale=1" />
    <meta
      http-equiv="Content-Security-Policy"
      content="default-src 'none'; style-src 'unsafe-inline'; script-src 'unsafe-inline'"
    />
    <title>Review __SKILL_NAME_PLACEHOLDER__ trigger cases</title>
    <style>
      body {
        font: 14px system-ui;
        margin: 2rem auto;
        max-width: 72rem;
        padding: 0 1rem;
        color: #222;
      }
      header {
        margin-bottom: 1.5rem;
      }
      article {
        border: 1px solid #ddd;
        border-radius: 10px;
        margin: 0.75rem 0;
        padding: 1rem;
      }
      textarea {
        box-sizing: border-box;
        min-height: 5rem;
        width: 100%;
      }
      button {
        margin: 0.4rem 0.4rem 0.4rem 0;
        padding: 0.5rem 0.8rem;
      }
      .row {
        align-items: center;
        display: flex;
        gap: 0.6rem;
      }
      .muted {
        color: #666;
      }
    </style>
  </head>
  <body>
    <header>
      <h1>Review trigger cases for __SKILL_NAME_PLACEHOLDER__</h1>
      <p class="muted">__SKILL_DESCRIPTION_PLACEHOLDER__</p>
    </header>
    <main id="cases"></main>
    <button id="add" type="button">Add case</button
    ><button id="export" type="button">Export eval set</button>
    <script>
      let items = __EVAL_DATA_PLACEHOLDER__
      const root = document.querySelector('#cases')
      const render = () => {
        root.replaceChildren()
        items.forEach((item, index) => {
          const article = document.createElement('article')
          const textarea = document.createElement('textarea')
          textarea.value = item.query || ''
          textarea.addEventListener('input', () => {
            items[index].query = textarea.value
          })
          const label = document.createElement('label')
          const check = document.createElement('input')
          check.type = 'checkbox'
          check.checked = Boolean(item.should_trigger)
          check.addEventListener('change', () => {
            items[index].should_trigger = check.checked
          })
          label.append(check, ' should trigger')
          const remove = document.createElement('button')
          remove.type = 'button'
          remove.textContent = 'Remove'
          remove.addEventListener('click', () => {
            items.splice(index, 1)
            render()
          })
          const row = document.createElement('div')
          row.className = 'row'
          row.append(label, remove)
          article.append(textarea, row)
          root.append(article)
        })
      }
      document.querySelector('#add').addEventListener('click', () => {
        items.push({ query: '', should_trigger: true })
        render()
      })
      document.querySelector('#export').addEventListener('click', () => {
        const triggerEvals = {
          schema_version: 1,
          kind: 'trigger',
          cases: items.map((item, index) => ({
            id: item.id || `trigger-${index + 1}`,
            query: item.query || '',
            should_trigger: Boolean(item.should_trigger)
          }))
        }
        const blob = new Blob([JSON.stringify(triggerEvals, null, 2)], {
          type: 'application/json'
        })
        const link = document.createElement('a')
        link.href = URL.createObjectURL(blob)
        link.download = 'trigger-evals.json'
        link.click()
        URL.revokeObjectURL(link.href)
      })
      render()
    </script>
  </body>
</html>
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 322kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 322kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 322kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall