Explore skills

Empower non-developers to use agent tools like Codex, Antigravity, and Claude Code more clearly and safely. This skill is useful for clarifying requests, explaining bash commands, isolating risky work, creating backups, capturing preferences, reviewing for security, or improving the tool itself.

Check for and apply updates from the vallorcine source repository

Design and scaffold a backend for an existing frontend. Users review a design document (endpoints, DB schema, auth) and then receive scaffolded code upon approval.

Analyze and classify agent skills for safety using local evaluation with structured risk assessment and optional verifiable attestation.

Help entry point — answers questions and routes to the right command

Generates an HTML viewer for browsing past Claude Code conversation history. It extracts data from JSONL session files to build a searchable and filterable UI. Invoke with /history.

Turn a raw Whisper SRT (or any transcript) into clean, well-formatted subtitles and produce a subtitled video. Optimized for spoken-word audio where preserving disfluencies matters.

Monitor and rebalance a multi-asset portfolio using real-time quotes, sector allocation, and risk metrics from the Finskills API.

context-density-optimizer is an AgentSkill for pruning bloated working context before implementation, review, debugging, or planning work.

Records Claude Code or OpenClaw work as EPI evidence. Use when the user requests to record, save, export, audit, trace, debug a run, create an .epi artifact, or asks for reproducible execution evidence.

Smart Money Intelligence for Your AI Agent.

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data.