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: delete

英文目录

Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

18K
Stars
87/100
信任
分类: design-creative审计

Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tenstorrent on clouds, Kubernetes, and bare metal.

2.2K
Stars
85/100
信任
分类: agent-skills审计

Entity Framework EF Core efcore Bulk Batch Extensions with BulkCopy in .Net for Insert Update Delete Read (CRUD), Truncate and SaveChanges operations on SQL Server, PostgreSQL, MySQL, SQLite, Oracle

4.0K
Stars
73/100
信任
分类: data-analysis审计

A powerful browser extension to create, edit and delete cookies

1.6K
Stars
75/100
信任
分类: legal-compliance审计

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

51K
Stars
83/100
信任
分类: research审计

Agent skills for Fallow codebase intelligence tool that helps AI agents detect unused code, duplication, circular dependencies, complexity hotspots, and architecture drift in JavaScript and TypeScript projects.

114
Stars
73/100
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

Mint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.

25K
Stars
73/100
信任
分类: research审计

Dapper Plus - High-Efficient Bulk Actions (Insert, Update, Delete, and Merge) for .NET

429
Stars
66/100
信任
分类: data-analysis审计