Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
Interview the user to turn project vision and decisions into README and ADR documentation.
Drive an existing browser through CDP for authenticated, visual, or interactive web automation.
Control cmux workspaces, panes, surfaces, and agent sessions safely from macOS terminal workflows.
Launch Codex CLI as an isolated subagent for bounded coding, review, or verification tasks.
Run read-only exposure checks for security advisories and write a structured local audit report.
Use DeepAPI for supported scraping, research, and email workflows with explicit credentials and approval.
Delegate bounded work to other AI agents while preserving context, ownership, and progress checks.
Distribute a skill across configured agent skill folders while respecting local symlink layouts.
Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.
Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.
Create folder-scoped CLAUDE.md and AGENTS.md guidance for future agents working in that area.
Draft and explain persistent goal-loop prompts for long-running agent work with clear stop conditions.
Build structured strategy documents by asking one question at a time and patching the file.
Open Markdown reliably in cmux panes and recover from blank rendered surfaces.
Register custom Pi Agent model slugs so saved OpenRouter variants resolve correctly.
Give Pi Agents a safe web-search and fetch workflow using the installed pi-web-access package.
Commit and push skill changes to the configured skills repository after review and validation.
Read every ADR in a project before summarizing architectural context or decisions.
Turn vague research needs into one precise deep-research prompt with context and output criteria.
Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.
Walk a user through setup or installation one step at a time with the remaining steps visible.
Rewrite the previous response more briefly while preserving the substance.
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.