文档写作 AI 技能

发现文档写作相关 Skills，比较来源仓库和用途，查看适合你工作流的技能说明。

分类目录: 文档写作

最近收录最多 Forks 编辑推荐更多筛选

文档写作清除筛选

GitHub

model-inversion

pluginagentmarketplace

Privacy attacks to extract training data and sensitive information from AI models

☆ 1查看技能

GitHub

input-output-guardrails

pluginagentmarketplace

Implementing safety filters, content moderation, and guardrails for AI system inputs and outputs

☆ 1查看技能

GitHub

testing-methodologies

pluginagentmarketplace

Structured approaches for AI security testing including threat modeling, penetration testing, and red team operations

☆ 1查看技能

GitHub

secure-deployment

pluginagentmarketplace

Security best practices for deploying AI/ML models to production environments

☆ 1查看技能

GitHub

prompt-hacking

pluginagentmarketplace

Advanced prompt manipulation including direct attacks, indirect injection, and multi-turn exploitation

☆ 1查看技能

GitHub

llm-jailbreaking

pluginagentmarketplace

Advanced LLM jailbreaking techniques, safety mechanism bypass strategies, and constraint circumvention methods

☆ 1查看技能

GitHub

adversarial-training

pluginagentmarketplace

Defensive techniques using adversarial examples to improve model robustness and security

☆ 1查看技能

GitHub

automated-testing

pluginagentmarketplace

CI/CD integration and automation frameworks for continuous AI security testing

☆ 1查看技能

GitHub

code-injection

pluginagentmarketplace

Test AI systems for code injection vulnerabilities including prompt-to-code attacks and agent exploitation

☆ 1查看技能

GitHub

model-extraction

pluginagentmarketplace

Techniques to extract model weights, architecture, and training data through API queries

☆ 1查看技能

GitHub

certifications-training

pluginagentmarketplace

Professional certifications, CTF competitions, and training resources for AI security practitioners

☆ 1查看技能

GitHub

red-team-reporting

pluginagentmarketplace

Professional security report generation, executive summaries, finding documentation, and remediation tracking

☆ 1查看技能

GitHub

security-testing

pluginagentmarketplace

Comprehensive security testing automation for AI/ML systems with CI/CD integration

☆ 1查看技能

GitHub

prompt-injection-testing

pluginagentmarketplace

Master prompt injection attacks, jailbreak techniques, input manipulation, and payload crafting for LLM security testing

☆ 1查看技能

GitHub

benchmark-datasets

pluginagentmarketplace

Standard datasets and benchmarks for evaluating AI security, robustness, and safety

☆ 1查看技能

GitHub

git-basics

pluginagentmarketplace

Git fundamentals - init, add, commit, status, log, and core concepts

☆ 1查看技能

GitHub

basic-workflow

pluginagentmarketplace

Daily Git workflow - add, commit, push, pull cycle for everyday development

☆ 1查看技能

GitHub

collaboration

pluginagentmarketplace

Team collaboration - remote, fetch, pull, push, clone, and team workflows

☆ 1查看技能

GitHub

branching

pluginagentmarketplace

Git branching strategies - create, switch, merge, rebase, and workflows

☆ 1查看技能

GitHub

github-features

pluginagentmarketplace

GitHub platform features - PRs, issues, actions, projects, and automation

☆ 1查看技能

GitHub

git-intro

pluginagentmarketplace

Introduction to Git version control - what, why, and first steps

☆ 1查看技能

GitHub

advanced-git

pluginagentmarketplace

Advanced Git - interactive rebase, cherry-pick, bisect, reflog, and power user operations

☆ 1查看技能

GitHub

verification-before-completion

zebbern

Use when about to claim work is complete, fixed, or passing. Run verification commands and confirm output before making any success claims. Evidence before assertions.

☆ 1查看技能

GitHub

test-driven-development

zebbern

Use when implementing any feature or bugfix. Write the test first, watch it fail, write minimal code to pass. Red-Green-Refactor cycle.

☆ 1查看技能

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。