Skip to main content
تشغيل أي مهارة في Manus
بنقرة واحدة
مستودع GitHub

SWE-Skills-Bench

يحتوي SWE-Skills-Bench على 9 من skills المجمعة من GeniusHTX، مع تغطية مهنية على مستوى المستودع وصفحات skill داخل الموقع.

skills مجمعة
9
Stars
59
محدث
2026-04-14
Forks
11
التغطية المهنية
2 فئات مهنية · 100% مصنفة
مستكشف المستودعات

Skills في هذا المستودع

add-admin-api-endpoint
مطوّرو البرمجيات

Add a new endpoint or endpoints to Ghost's Admin API at `ghost/api/admin/**`.

2026-04-14
turborepo
مطوّرو البرمجيات

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries. Use when user: configures tasks/workflows/pipelines, creates packages, sets up monorepo, shares code between apps, runs changed/affected packages, debugs cache, or has apps/packages directories.

2026-04-14
add-uint-support
مطوّرو البرمجيات

Add unsigned integer (uint) type support to PyTorch operators by updating AT_DISPATCH macros. Use when adding support for uint16, uint32, uint64 types to operators, kernels, or when user mentions enabling unsigned types, barebones unsigned types, or uint support.

2026-03-23
analytics-events
مطوّرو البرمجيات

Add product analytics events to track user interactions in the Metabase frontend

2026-03-23
analyze-ci
مطوّرو البرمجيات

Analyze failed GitHub Action jobs for a pull request.

2026-03-23
clojure-write
مطوّرو البرمجيات

Guide Clojure and ClojureScript development using REPL-driven workflow, coding conventions, and best practices. Use when writing, developing, or refactoring Clojure/ClojureScript code.

2026-03-23
implementing-jsc-classes-zig
مطوّرو البرمجيات

Creates JavaScript classes using Bun's Zig bindings generator (.classes.ts). Use when implementing new JS APIs in Zig with JSC integration.

2026-03-23
llm-evaluation
علماء البيانات

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

2026-03-23
rag-implementation
مطوّرو البرمجيات

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

2026-03-23