aipoch/open-science / resources/skills/skill-creator
skill-creator
VerifiedCreate, 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 6.5 KB |
| agents/analyzer.md | markdown | 989 B |
| agents/comparator.md | markdown | 815 B |
| agents/grader.md | markdown | 1.2 KB |
| assets/eval_review.html | other | 3.5 KB |
| eval-viewer/generate-review.js | script | 4.0 KB |
| eval-viewer/viewer.html | other | 4.6 KB |
| package.json | manifest | 25 B |
| references/schemas.md | markdown | 3.7 KB |
| scripts/aggregate-benchmark.js | script | 1.2 KB |
| scripts/generate-report.js | script | 1.4 KB |
| scripts/improve-description.js | script | 1.6 KB |
| scripts/index.js | script | 321 B |
| scripts/quick-validate.js | script | 1.9 KB |
| scripts/run-eval.js | script | 395 B |
| scripts/run-loop.js | script | 793 B |
| scripts/utils.js | script | 1.0 KB |
eval-viewer/viewer.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'; img-src data:; style-src 'unsafe-inline'; script-src 'unsafe-inline'"
/>
<title>Review __SKILL_NAME_PLACEHOLDER__ evaluation</title>
<style>
body {
font: 14px system-ui;
margin: 2rem auto;
max-width: 80rem;
padding: 0 1rem;
color: #222;
}
nav {
display: flex;
gap: 0.5rem;
margin-bottom: 1rem;
}
button {
padding: 0.5rem 0.8rem;
}
article,
section {
border: 1px solid #ddd;
border-radius: 10px;
margin: 0.75rem 0;
padding: 1rem;
}
pre {
background: #f6f6f6;
overflow: auto;
padding: 0.75rem;
white-space: pre-wrap;
}
img {
max-width: 100%;
}
textarea {
box-sizing: border-box;
min-height: 6rem;
width: 100%;
}
table {
border-collapse: collapse;
width: 100%;
}
th,
td {
border: 1px solid #ddd;
padding: 0.5rem;
text-align: left;
}
.hidden {
display: none;
}
.muted {
color: #666;
}
</style>
</head>
<body>
<h1>Review __SKILL_NAME_PLACEHOLDER__ evaluation</h1>
<nav>
<button data-view="outputs">Outputs</button><button data-view="benchmark">Benchmark</button>
</nav>
<main id="outputs"></main>
<main id="benchmark" class="hidden"></main>
<button id="submit" type="button">Download feedback</button>
<script>
const data = __REVIEW_DATA_PLACEHOLDER__
const feedback = new Map()
const element = (tag, text) => {
const node = document.createElement(tag)
if (text !== undefined) node.textContent = text
return node
}
const outputs = document.querySelector('#outputs')
for (const run of data.runs || []) {
const article = element('article')
article.append(element('h2', run.id), element('p', run.prompt))
for (const file of run.outputs || []) {
const section = element('section')
section.append(element('h3', file.name))
if (file.type === 'text') section.append(element('pre', file.content))
else if (file.type === 'image') {
const image = element('img')
image.src = file.data_uri
image.alt = file.name
section.append(image)
} else
section.append(
element('p', file.reason || `${file.type} file (${file.size || 0} bytes)`)
)
article.append(section)
}
if (run.grading) {
const details = element('details')
details.append(
element('summary', 'Formal grading'),
element('pre', JSON.stringify(run.grading, null, 2))
)
article.append(details)
}
const area = element('textarea')
area.placeholder = 'What should change? Leave empty when this output is acceptable.'
area.addEventListener('input', () => feedback.set(run.id, area.value))
article.append(area)
outputs.append(article)
}
if (!(data.runs || []).length) outputs.append(element('p', 'No evaluation outputs found.'))
const benchmark = document.querySelector('#benchmark')
benchmark.append(
element(
'pre',
data.benchmark ? JSON.stringify(data.benchmark, null, 2) : 'No benchmark data found.'
)
)
document.querySelectorAll('[data-view]').forEach((button) =>
button.addEventListener('click', () => {
document
.querySelectorAll('main')
.forEach((panel) => panel.classList.toggle('hidden', panel.id !== button.dataset.view))
})
)
document.querySelector('#submit').addEventListener('click', () => {
const reviews = (data.runs || []).map((run) => ({
run_id: run.id,
feedback: feedback.get(run.id) || '',
timestamp: new Date().toISOString()
}))
const blob = new Blob(
[JSON.stringify({ schema_version: 1, reviews, status: 'complete' }, null, 2)],
{ type: 'application/json' }
)
const link = element('a')
link.href = URL.createObjectURL(blob)
link.download = 'feedback.json'
link.click()
URL.revokeObjectURL(link.href)
})
</script>
</body>
</html>
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |