linuz90
from GitHub
开发与编程
Share text, code, reports, or other content externally via a beautifully rendered GitHub Gist. ALWAYS use this skill whenever creating a gist — whether the user says "create a gist", "make a gist", "share as a gist", "share this", "share this code", or any variation involving the word "gist". This is the default way to create gists. Also use proactively when sharing content and a gist would be the best format.
AndreevED
from GitHub
开发与编程
Независимое cross-model ревью кода. Отправляет изменённые файлы на проверку через codex в headless-режиме, получает структурированные замечания, верифицирует их по кодовой базе, исправляет через агента 1c-code-writer и итеративно повторяет до одобрения.
alchemiststudiosDOTai
from GitHub
开发与编程
Set up ast-grep for a codebase with common TypeScript rules for detecting anti-patterns, enforcing best practices, and preventing bugs. Creates sgconfig.yml, rule files, and rule tests. Use when adding structural linting, banning legacy patterns, or implementing ratchet gates.
Lucklyric
from GitHub
开发与编程
This skill should be used when the user wants to invoke Codex CLI for complex coding tasks requiring high reasoning capabilities. Trigger phrases include "use codex", "ask codex", "run codex", "call codex", "codex cli", "GPT-5 reasoning", "OpenAI reasoning", or when users request complex implementation challenges, advanced reasoning, architecture design, or high-reasoning model assistance. Automatically triggers on codex-related requests and supports session continuation for iterative development.
Multi-agent orchestration framework for Claude Code. Automatically delegates tasks to cheaper, faster sub-agents (Haiku 4.5, Sonnet 4.6) while maintaining Opus-level quality through verification. Use when working on any coding task — Hydra activates automatically to route file exploration, test running, documentation, code writing, debugging, security scanning, and git operations to the optimal agent. Saves ~50% on API costs. --- # 🐉 Hydra — Multi-Headed Speculative Execution > *"Cut off one head, two more shall take its place."* > Except here — every head is doing your work faster and cheaper. ## Why Hydra Exists Autoregressive LLM inference is memory-bandwidth bound — the time per token scales with model size regardless of task difficulty. Speculative decoding solves this at the token level by having a small "draft" model propose tokens that a large "target" model verifies in parallel. Hydra applies the same principle at the **task level**. Most coding tasks don't need the full reasoning power of Opus. File searches, simple edits, test runs, documentation, boilerplate code — these are "easy tokens" that a faster model handles just as well. By routing them to Haiku or Sonnet heads and reserving Opus for genuinely hard problems, we get: - **2–3× faster task completion** (Haiku responds ~10× faster than Opus) - **~50% reduction in API costs** (Haiku 4.5 is 5× cheaper per token than Opus 4.6) - **Zero quality loss** on tasks within each model's capability band ## How Hydra Works — The Multi-Head Loop ``` User Request │ ├──────────────────────────────────────────────────────┐ │ │ ▼ ▼ ┌─────────────────────────────┐ ┌──────────────────────────────┐ │ 🧠 ORCHESTRATOR (Opus) │ │ 🟢 hydra-scout │ │ Classifies task │ │ IMMEDIATE pre-dispatch: │ │ Plans waves │ │ "Find fil
TencentCloudBase
from GitHub
开发与编程
Use this skill when developing Node.js backend services or CloudBase cloud functions (Express/Koa/NestJS, serverless, backend APIs) that need AI capabilities. Features text generation (generateText), streaming (streamText), AND image generation (generateImage) via @cloudbase/node-sdk ≥3.16.0. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended), DeepSeek (deepseek-v3.2 recommended), and hunyuan-image for images. This is the ONLY SDK that supports image generation. NOT for browser/Web apps (use ai-model-web) or WeChat Mini Program (use ai-model-wechat).
kevindutra
from GitHub
开发与编程
Review code changes in crit's multi-file TUI with syntax highlighting and diff markers. After the review, address any comments.
Rune-kit
from GitHub
开发与编程
Pre-implementation red-team analysis. Challenges plans before code is written — finds edge cases, security holes, scalability bottlenecks, error propagation risks, and integration conflicts. Catches flaws at plan time (10x cheaper than post-implementation).
vedantb2
from GitHub
开发与编程
Clerk backend REST API
Compare ERB and JavaScript template outputs for the offline scoring SPA. Use when working on ERB-to-JS conversion, debugging template parity issues, or verifying that changes to scoring views work correctly in both ERB and SPA modes.
imbue-ai
from GitHub
开发与编程
Interact with third-party or self-hosted services (Slack, Google Workspace, Dropbox, GitHub, Linear, Coolify...) using their HTTP APIs on the user's behalf.
rhennigan
from GitHub
开发与编程
Add a new custom CodeInspector rule to detect problematic Wolfram Language patterns.