Skills for AI agents

Your AI configures Vite projects including plugins, environment variables, proxy setup, and build optimization. It handles dev server, SSR, library mode, and troubleshooting common Vite issues.

Your AI edits and structures existing video footage into polished content. It manages cutting, overlays, subtitles, voiceovers, and reframing using FFmpeg, Remotion, ElevenLabs, Descript, and CapCut workflows.

Your AI coordinates multiple agents as a team using work items, ownership, Kanban states, and merge gates. It manages shared workflow visibility, branch isolation, and control pane handoffs for multi-agent project collaboration.

Your AI generates videos applying a distilled style pack, planning cuts by measured rhythm and grading with LUTs. It weaves generated and existing footage into finished edits with overlays and 3D props, verifying results numerically.

Your AI measures reference videos into reusable style packs with color grades, shot-length distributions, stills, overlays, and text specs. It captures and reproduces the look and pacing of footage for consistent creative direction.

Your AI adopts Swift 6.2 concurrency with single-threaded defaults and explicit background offloading using @concurrent. It resolves data-race errors and designs MainActor-isolated types for safe async code.

Your AI reviews Spring Boot services for authentication, authorization, validation, CSRF, secrets, headers, and rate limiting. It covers JWT, OAuth2, session cookies, method security, and dependency vulnerability scanning.

Your AI audits all Claude skills and commands for quality using quick or full scan modes. It evaluates changed or all skills with batch subagent checks and caches results for ongoing quality control.

Your AI checks if agents truly follow given skills, rules, and definitions by running scenarios at different prompt strictness levels. It captures and classifies tool call sequences and generates detailed compliance reports with timelines.

Scan repositories for remotely reachable vulnerabilities that qualify for bug bounties or responsible disclosure. It focuses on exploitable issues like SSRF, auth bypass, injection flaws, and path traversal, ignoring low-signal local-only risks.

Your AI uses two independent reviewers to check output before delivery, reducing bias and errors. Both must approve the content, ensuring compliance and accuracy for published or production-ready results.

Your AI blocks or warns before destructive commands on production systems or during autonomous runs. It restricts edits to allowed directories and intercepts risky commands like forced git pushes or data drops.

Your AI scans installed skills to extract recurring principles and distills them into or updates rule files. It collects facts exhaustively, cross-reads for matches, and revises rules to keep knowledge consistent and complete.

Your AI manages product returns from authorization to refund and fraud detection. It applies grading frameworks, disposition decisions, and warranty claims handling informed by 15+ years of returns operations experience.

Your AI decides when to use regex or an LLM to parse structured text, saving cost and improving accuracy. It starts with regex for consistent patterns and adds LLM only for uncertain edge cases in quizzes, forms, or invoices.

Your AI manages repeated rollouts and recursive reasoning with explicit decision and coherence marks. It records trial data, search spaces, and candidate evaluations in append-only ledgers for transparent evidence trails.

Your AI builds and reviews Rails 7.1+ apps using community patterns for controllers, services, queries, jobs, and views. It enforces directory structure, skinny controllers, ActiveRecord idioms, and Hotwire integration.

Turn large feature requests into verified, manageable work units for multi-agent execution. It organizes RFC intake, DAG decomposition, unit validation, merge queues, and integration checks.

Your AI reviews and improves Quarkus authentication, authorization, and input validation. It covers JWT/OIDC setup, role-based access, CSRF protection, secrets management, and dependency security checks.

Your AI sequences and balances manufacturing jobs to maximize throughput and meet delivery targets. It handles job priorities, line balancing, changeover trade-offs, and disruption responses across ERP, MES, and scheduling tools.

Your AI manages issue and pull request flow between GitHub and Linear to keep public work visible and internal tasks organized. It triages PR backlogs, links active work, and decides which items need internal tracking in Linear.

Your AI translates product intent or roadmap items into explicit implementation-ready capability plans. It exposes constraints, interfaces, and unresolved decisions before multi-service work starts to clarify engineering contracts.

Your AI crafts a complete OpenClaw lobster persona including identity, SOUL.md, rules, name, and avatar prompt. It can generate avatar images if a supported image skill is installed, or provide prompts for manual creation.

Your AI manages drafts of outbound messages requiring human approval before sending. It tracks drafts, operator decisions, and delivery receipts to ensure audit trails and prevent duplicate or unauthorized sends.