技能目录

为 AI Agent 发现可复用技能。

按任务搜索真实的 GitHub 技能,并在使用前查看 Stars、信任、审计、分类和安装路径。

每个推荐都保留与其仓库、审计和安装路径的明确关联。

搜索结果: endpoint

英文目录
Cli75

A versatile command-line tool for interacting with Google Workspace APIs, designed for both human users and AI agents.

30K
Stars
75/100
信任
分类: utility审计

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

12K
Stars
85/100
信任
分类: development审计

UmaDev orchestrates multiple AI coding CLIs to act as a team of roles for software development.

241
Stars
78/100
信任
分类: coding-agents审计

Use when reviewing a PR, API, IPC channel, endpoint, parameter, type, config, or architectural extension point that adds or expands shared surface area, especially when consumers are absent, exports are unused or speculative, existing consumers are hack-heavy, forward compatibility is claimed, or multiple similar APIs may express one demand.

51K
Stars
78/100
信任
分类: research审计

Use when user wants to create a GitHub issue for the current repository. Must read and follow the repository's issue template format.

51K
Stars
76/100
信任
分类: coding-agents审计

A comprehensive monitoring, recommendation, and OpenAI-compatible gateway system for AI API endpoints with layered probing, health scoring, and self-hosted deployment.

185
Stars
72/100
信任
分类: development审计

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

34K
Stars
70/100
信任
分类: research审计

Use when working with cognee's permission system — understanding or changing how users, roles, and tenants get access to datasets, how ACL grants work, where permissions are enforced in add/cognify/search/delete, and how the grant records surface in the memory-provenance view.

30K
Stars
73/100
信任
分类: research审计

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

1.9K
Stars
72/100
信任
分类: media-automation审计

Open-source cross-platform endpoint detection engine for Windows, macOS, and Linux using ETW, ESF, eBPF, Sigma, YARA, IOCs, and ECS NDJSON alerts.

377
Stars
70/100
信任
分类: devops审计

Your Claude Pro/Max subscription in any tool — Cursor, Cline, Aider, Agent SDK — at subscription pricing, not per-token bills. One local endpoint that replays Claude Code's wire shape so your traffic stays in the subscription pool.

286
Stars
67/100
信任
分类: development审计