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: secret-shares

英文目录

AnkiDroid: Anki flashcards on Android. Your secret trick to achieve superhuman information retention.

11K
Stars
84/100
信任
分类: education审计

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.

4.0K
Stars
70/100
信任
分类: agent-frameworks审计

A Vault swiss-army knife: A CLI tool to init, unseal and configure Vault (auth methods, secret engines).

2.3K
Stars
73/100
信任
分类: devops审计

A command-line interface for Todoist that includes agent skill installation for popular coding assistants.

277
Stars
74/100
信任
分类: productivity审计

Agent skills for coding assistants to interact with Langfuse's LLM tracing, prompt management, and evaluation platform.

214
Stars
75/100
信任
分类: coding-agents审计

Discounted cash flow valuation and intrinsic value analysis for public companies. Use when the brief asks for DCF, fair value, intrinsic value, price target, undervalued or overvalued analysis, or "what is this company worth?"

91K
Stars
77/100
信任
分类: design-creative审计

Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.

25K
Stars
77/100
信任
分类: engineering / code quality审计

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.

25K
Stars
77/100
信任
分类: design-creative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

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

941
Stars
67/100
信任
分类: rag-knowledge审计

Better privacy without special software

1.7K
Stars
62/100
信任
分类: legal-compliance审计