GITHUB AGENT SKILLS / 技能收录

给你的 AI 助手
装上专业技能

我们从 GitHub 持续收录、审核并分类优质的 Agent Skills,按职业与使用场景整理,复制一行命令即可安装到 Claude Code、Cursor 等智能体。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

qubit-calculus
qubit-calculus/Qubit

plan

Plan mode for Hermes — inspect context, write a markdown plan into the active workspace's `.hermes/plans/` directory, and do not execute the work.

★ 0
duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

agent-memory-discipline

Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.

后端与接口Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

ai-slop-cleaner

Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.

★ 0
qubit-calculus
qubit-calculus/Qubit

xitter

Interact with X/Twitter via the x-cli terminal client using official X API credentials. Use for posting, reading timelines, searching tweets, liking, retweeting, bookmarks, mentions, and user lookups.

后端与接口Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

agentica-spawn

Spawn Agentica multi-agent patterns

★ 0
qubit-calculus
qubit-calculus/Qubit

openhue

Control Philips Hue lights, rooms, and scenes via the OpenHue CLI. Turn lights on/off, adjust brightness, color, color temperature, and activate scenes.

★ 0
rubicanjr
rubicanjr/FinCognis

agentica-server

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

后端与接口
★ 0
qubit-calculus
qubit-calculus/Qubit

research-paper-writing

End-to-end pipeline for writing ML/AI research papers — from experiment design through analysis, drafting, revision, and submission. Covers NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Integrates automated experiment monitoring, statistical analysis, iterative writing, and citation verification.

内容创作者视觉设计写作与文案
★ 0
rubicanjr
rubicanjr/FinCognis

agentica-sdk

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

agentica-prompts

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

★ 0
rubicanjr
rubicanjr/FinCognis

agentica-infrastructure

Reference guide for Agentica multi-agent infrastructure APIs

★ 0
qubit-calculus
qubit-calculus/Qubit

blogwatcher

Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI. Add blogs, scan for new articles, and track what you've read.

★ 0
rubicanjr
rubicanjr/FinCognis

agentica-claude-proxy

Guide for integrating Agentica SDK with Claude Code CLI proxy

★ 0
duc-duy-1612
duc-duy-1612/Online-Delivery-Systems-Web

agent-evals

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.

运维与部署Skill与智能体开发
★ 0
qubit-calculus
qubit-calculus/Qubit

arxiv

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

后端与接口资料检索与研究
★ 0
rubicanjr
rubicanjr/FinCognis

agentic-workflow

Agentic Workflow Pattern

Skill与智能体开发
★ 0
rubicanjr
rubicanjr/FinCognis

agent-tamagotchi

Terminal pet that lives in your statusline. 12 species, 5 stats (DEBUGGING, PATIENCE, CHAOS, WISDOM, SPEED). Reacts to your workflow - happy when tests pass, sad when builds fail, excited during swarm mode. Deterministic species from user ID.

Skill与智能体开发
★ 0
qubit-calculus
qubit-calculus/Qubit

godmode

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Hermes-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or red-team model robustness.

Skill与智能体开发
★ 0