Skill UI

This sub-agent is specialized in generating precise delta specifications (delta specs). It analyzes a given proposal to identify added, modified, or removed system behaviors, creating structured requirements and scenarios to document the proposed changes accurately. It follows defined conventions for persistence across various artifact storage modes (Engram, OpenSpec, Hybrid).

This sophisticated sub-agent takes comprehensive Software Design Documents (SDD), proposals, and specifications to generate a detailed, actionable task breakdown in the format of a tasks.md file. It structures the work into distinct phases (e.g., Foundation, Core Implementation, Testing, Cleanup), providing concrete, verifiable, and small units of work suitable for immediate engineering execution and managing complex feature delivery chains.

This skill acts as a critical quality gate for System Design Document (SDD) changes. It executes comprehensive tests and validates that the implemented code and artifacts strictly adhere to the defined specifications, design requirements, and task completion status. It ensures full proof of implementation integrity before further development stages.

This meta-skill audits, refactors, and standardizes the structure of existing skill definition files (SKILL.md). It ensures compliance with defined style guides, enforces best practices (Hard Rules, Decision Gates), and improves the overall quality and maintainability of LLM-based skills.

This skill automatically scans all defined user and project skills (from SKILL.md files) to create a comprehensive, centralized index. It manages skill paths, triggers, descriptions, and scopes, ensuring that downstream agents and delegators always have an up-to-date source of truth for available functionalities. It is crucial for maintaining system integrity and avoiding redundant skill definitions.

A comprehensive, black-box workflow designed for professional bug bounty hunting and penetration testing. It guides users through a 5-stage methodology (Intake, Recon, Enum, Hunt, Report), covering 19+ advanced attack playbooks (e.g., RCE, SQLi, XSS, SSRF). The skill integrates real-world exploit cases, structured payloads, and WAF bypass techniques for maximizing vulnerability discovery in web applications and APIs.

A rigorous framework for triaging software defects, managing technical debt, and designing systemic fixes. This methodology mandates classifying issues by root class and implementing clustered, minimized solutions, rather than applying superficial patches. It guides developers to prevent over-engineering and ensure that system improvements are durable, verifiable, and maintainable.

A structured skill embodying Tang Jia San Shao's web fiction creation approach, covering daily updating discipline, cultivation systems with quantifiable levels, team-based battle narratives, IP lifecycle planning via six waves, and emotional anchoring from real-life experiences. Suitable for designing long-running fantasy series, managing consistent writing output, and planning cross-media IP expansion.

This skill models Tian Can Tu Dou (author of Battle Through the Heavens) web novel creative thinking, covering the 'divorce engagement' trope, progression fantasy systems, map-changing narrative loops, underdog rise golden triangle, 'terror like this' battle formulas, and IP-driven content operations.

This skill guides developers on best practices for structuring commits and Pull Requests (PRs). It teaches how to break down large, complex features into small, independent, and reviewable work units. By adhering to these principles, developers keep the reviewer's cognitive load low, improve code quality, and manage version control history effectively.

This skill provides a strategic framework for content creation within the AI Agent vertical. It emphasizes hands-on product testing, translating complex technical concepts for general audiences, community-driven distribution, and practical tutorials. Ideal for tech media creators, AI product reviewers, and content strategists aiming to build authority in the AI Agent space through verified experience and clear communication.

Compile production-grade visual asset sheets, cinematic storyboards, and reference-based video generation prompts. Handles character identity boards, multi-panel grids, action beats, and R2V/I2V/T2V prompts with consistent identities, camera language, reference responsibilities, and sound design constraints. Intended for creators who need actionable prompts for image and video generation rather than raw editing, model parameter lookup, or evaluating finished videos.