Reusable SKILL.md capabilities that give your agent new expertise — installed into .claude/skills/ and friends.
Control HomeKit devices via the local Casa app and API (localhost-only).
Imports JIRA tickets (via API or web scraping) and converts them to local story files. Supports single tickets, bulk imports via JQL, and optional dev workflow kickoff. Works with or without API credentials.
Create and manage budgets, track spending, and plan savings. Use when the user wants to budget, track expenses, plan savings, or allocate income. Triggers on "budget", "expenses", "savings goal", "track spending", "monthly budget", "50/30/20", "envelope budget".
The official detailed guide for developing, testing, deploying, and auditing TRON smart contracts using the Sunhat toolkit.
How to properly create Claude Code skills - teaches global vs project-local, naming conventions, and proper file structure
Play Zork text adventure via dfrotz. Use /zork <command> to play (e.g., /zork go north), /zork for status, /zork new to restart, /zork setup to configure Obsidian sync.
Move notes from the Inbox to their respective folders based on their frontmatter category.
Resets workflow artifacts (.otto/ directory). Removes sessions, tasks, and specs. Use when starting over. Destructive - requires confirmation.
Use the pdsx CLI for ATProto record operations. Requires auth for writes, supports batch operations via stdin.
Audit and scaffold sprint documentation rituals based on MANIFESTO.md. Use when the user wants to follow the research -> spec -> prompt -> implement -> document workflow, generate checklists/templates, or evaluate documentation quality for a sprint.
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
UX Vern - Cool architecture, but can the user find the button? Empathy-driven design thinking.
Expert debugging methodology. Triggers on debug, investigate, fix bug, troubleshoot.
Query codebases semantically using LLMs. Use when asking questions about libraries, frameworks, or source code — searches actual source, not outdated docs.
Run Agent Workbench (awb) interactive UI components from Codex or the CLI. Use when the user needs a confirmation, checklist, input, table, code or markdown view, or a visual playground. Always follow interactive runs with awb wait and the returned ID. Use tmux for long-running commands (see awb --help).
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.
Launch lgtm TUI to review a markdown file with line-by-line commenting
View call logs for the Vocal Bridge voice agent. Can list recent calls or show details of a specific session including transcript.
Retro Vern - We solved this with cron jobs and a CSV in 2004. Grizzled veteran, historical perspective.
Stream real-time debug events from the Vocal Bridge voice agent. Shows transcriptions, agent responses, tool calls, and errors.