Browse Skills

Analyze narrated screen recordings and audio files through the talkthrough MCP server — triage feedback into findings, extract specs/backlogs/action items from recordings, and correlate spoken remarks with logs via wall-clock timestamps.

Analyze narrated screen recordings and audio files to extract transcripts, timestamps, OCR text, and correlate spoken remarks with logs. Used to triage feedback, generate specs/backlogs, and extract action items from recordings.

A structured five-step thinking loop that helps AI agents make better decisions by weighing reversibility, gathering evidence, redesigning bets, attacking their own reasoning, and delivering a clear answer. Fires automatically on high-stakes choices or user indecision.

Switches the agent to a terse output mode, reducing token usage by ~50-70% while keeping code, commands, and technical terms exact. Use when you need brief replies or want to save costs.

Automatically trim, summarize, or drop stale content from the context window to save tokens while preserving task state. Use during long sessions, large file dumps, or before calling expensive models.

Condenses long tool outputs, logs, diffs, or documents into concise summaries while preserving key details. Use when you need to save context tokens on bulky payloads.

Compacts JSON and other structured data by removing whitespace, collapsing arrays, and shortening keys to reduce token usage in LLM outputs, without breaking parseability.

Condense prior conversation turns into a summary, merge near-duplicates, and keep recent messages verbatim to save context tokens without losing task state.

Enforces a hard token budget per task/response by tracking estimates, stopping before limits, and summarizing if exceeded. Helps when users specify a token cap or want to limit spending.

Automatically detects long sessions, high token usage, or bulky context and enables the appropriate Paleo token-saving skills to optimize token consumption without manual intervention.

A structured product review framework that helps decide whether a product direction should continue, be verified, or be reframed, using UX3 dimensions (User, Evidence, Business). Ideal for AI-assisted product decision-making with human-in-the-loop.

Design or refactor CLI tools for AI agent consumption with patterns for non-interactive execution, machine-readable output, idempotent operations, and progressive help discovery.