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 |
scripts/improve-description.js
View on GitHub'use strict'
/* eslint-disable @typescript-eslint/explicit-function-return-type */
const buildImprovementPrompt = ({
skillName,
skillContent,
currentDescription,
evalResults,
history = []
}) => {
const failedPositive = evalResults.results.filter(
(result) => result.should_trigger && !result.pass
)
const failedNegative = evalResults.results.filter(
(result) => !result.should_trigger && !result.pass
)
return `Improve the trigger description for the Skill "${skillName}".
Current description:
<current_description>${currentDescription}</current_description>
Should have triggered but did not:
${failedPositive.map((result) => `- ${result.query}`).join('\n') || '- none'}
Should not have triggered but did:
${failedNegative.map((result) => `- ${result.query}`).join('\n') || '- none'}
Previous attempts:
${history.map((attempt) => `- ${attempt.description}`).join('\n') || '- none'}
Skill content:
<skill_content>${skillContent}</skill_content>
Generalize from the failures. Describe user intent, not implementation. Stay under 1024 characters.
Return only <new_description>...</new_description>.`
}
const parseImprovedDescription = (response) => {
const match = /<new_description>([\s\S]*?)<\/new_description>/i.exec(response)
const description = (match?.[1] ?? response).trim().replace(/^['"]|['"]$/g, '')
if (!description) throw new Error('Description improvement returned empty text.')
if (description.length > 1024) throw new Error('Description improvement exceeds 1024 characters.')
return description
}
module.exports = { buildImprovementPrompt, parseImprovedDescription }
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: 197k | Updated | Claude CodeCodex | Verified | Install |