buddyh

Screenshot every view/screen of an app for marketing, product sites, and documentation. Use when asked to "screenshot the app", "capture all views", "get marketing screenshots", "screenshot every screen", or "product shots". Works with macOS native apps (screencapture), web apps (Puppeteer/Playwright), and Electron apps.

Recover working context from a prior Claude Code session by reading its JSONL conversation log and turning it into a clean handoff for Codex or another agent. Use when the user wants Codex to continue where Claude left off in the same repo, asks you to get up to speed on previous work, wants to resume a Claude thread after an interruption or outage, or needs help finding and summarizing the relevant file in ~/.claude/projects/.

Deep dive on any topic. Decomposes into subtopics, researches each in parallel with thorough source gathering, then synthesizes into a comprehensive report (4,000-10,000+ words, 40-100+ sources). Scales depth dynamically based on topic complexity. Use when asked for a deep dive, deep research, comprehensive analysis, or thorough investigation of a topic.

Send messages to other Claude Code or Codex sessions via tmux. Hand off complex debugging context, get second opinions, share detailed technical findings across sessions.

Branch the current Claude Code or Codex session into a new tmux session. Creates a parallel conversation that can diverge independently. Use when you want to explore an alternative approach without losing your current context.

Spawn a new Claude Code or Codex session in a project directory with context handoff. This skill should be used when discussion shifts to a different project/repo and the user wants to work on it in a dedicated session. Creates a handoff document with relevant context from the current conversation, then launches a new tmux session ready to continue.

Refactor bloated skill.md files using progressive disclosure pattern. Moves detailed content to references/ while keeping skill.md focused and discoverable. Use when a skill is approaching 500 lines or needs better organization.

Control Amazon Echo/Alexa devices via the `alexacli` CLI. Use when the user asks to speak/announce on Echo devices, send voice commands to Alexa, control smart home devices, list Alexa devices, or trigger routines.

Search conversation history across ALL local AI coding-agent sessions — Claude Code, Codex, Grok, pi, OpenCode, Antigravity, and Droid — powered by the seshy CLI. Every result includes the native command to resume that session. Use when the user asks to find previous conversations, search chat history, look up what was discussed before, or find a past session about a specific topic. Triggers on "/conversation-search", "/search", "search conversations", "find where we discussed", "what session talked about", "search my history for".

Discover and resume past AI coding-agent sessions with the seshy CLI — across Claude Code, Codex, Grok, pi, OpenCode, Antigravity, and Droid. Use to list/summarize the sessions for a repo, resume the most recent one, browse the latest sessions across every repo, produce a machine-readable index of all sessions, or hide headless (claude -p / codex exec) runs. Triggers on "seshy", "what sessions do I have", "resume my last session", "recent sessions", "sessions in this repo", "resume the previous conversation", "pick up where I left off". For searching session CONTENTS (find where something was discussed), use the conversation-search skill instead.

Live narration of your screen activity with 7 styles (sports, nature, horror, noir, reality_tv, asmr, wrestling) and live switching.

AI Newsroom: Generate professional podcasts, debates, and news briefings from any topic using ElevenLabs.

Create or refresh a markdown-first living story for active projects. Use when asked to maintain an evidence-based project story, compile project state from repos, carry open threads forward, verify recent wins, or run the Living Story loop.

Map the full blast radius of a code change before making it — every breaking reference, transitive (ripple) caller, affected test, and historically co-changing file — using the `br` CLI (LSP-backed, cross-language impact analysis). Use this whenever the user is about to rename, change the signature of, or remove a function, method, type, API endpoint, database column, or config/env key, or asks "what breaks if I change X", "what depends on this", "what calls this", "impact analysis", "is this safe to change/refactor", or "check the blast radius" — even if they don't say "blast radius" explicitly. Especially reach for it before refactoring shared code.