Durchsuchen und installieren Sie Tausende von AI Agent Skills im Killer-Skills-Verzeichnis. Kompatibel mit Claude Code, Windsurf, Cursor und mehr.
Use when writing TypeScript code that interacts with dependencies, handles credentials, executes child processes, or manages configuration. Provides Shai-Hulud supply chain attack countermeasures at the code level including safe dependency usage, credential handling, subprocess hardening, and runtime integrity patterns.
babysit-pr ist ein Automatisierungstool, das GitHub-Pull-Anfragen überwacht und verwaltet
Escalatory browser verification - open the app in a real browser and test the feature you built. Use after showing READY FOR REVIEW when the user asks you to verify in a browser.
Framework for reviewing and improving agent skills for quality, effectiveness, and compliance with the agent-skills standard. Use when auditing existing skills, providing feedback on skill PRs, improving skill descriptions, or troubleshooting underperforming skills.
Inspect GitHub PR for CI failures, merge conflicts, update-branch requirements, reviewer comments, change requests, and unresolved review threads. Create fix plans and implement after user approval. Resolve review threads and notify reviewers after fixes.
Inspect GitHub PR for CI failures, merge conflicts, update-branch requirements, reviewer comments, change requests, and unresolved review threads. Create fix plans and implement after user approval. Resolve review threads and notify reviewers after fixes.
Enforces project code conventions for Vue/Nuxt, TypeScript, styling (UnoCSS/SCSS), icons, composables, and commits. Use when writing or reviewing code in this repo, adding components, hooks, or styles, or when asked about project coding standards.
Use when creating, editing, or reviewing blog post frontmatter - especially excerpts, tags, or OpenGraph metadata. Use when placeholder values like tag1 or A brief description appear. Use when adding new posts or publishing drafts.
Start a new tutoring session. Reads progress, shows concepts due for review, suggests what to work on next. Use when user says start session, begin, lets start, or at the beginning of a learning session.
Standardize development for Convert steps in wolf-sv-parser. Use when asked to implement, continue, or review a Convert STEP XXXX task (e.g., convert step 17). Cover reading docs/convert/convert-progress.md, implementing code/tests, updating docs/convert/{convert-architecture,convert-workflow,convert-progress}, and asking for review.
Validates PR code against Architecture Decision Records (ADRs). Uses oracle for deep analysis of implementation compliance. Use when asked to validate a PR against an ADR, check ADR compliance, or review implementation adherence to architectural decisions.
Review code changes and pull requests for business fit, implementation approach, regressions, observability, security, and code quality. Use when reviewing uncommitted local code changes, reviewing the latest commit against the previous commit, or reviewing a pull request.