Productivity & Workflow Agent Skills

Parallel divergent ideation for coding agents.

Shape output for a reader with ADHD. Auto-trigger on operational, instructional, and multi-step work — setup tasks, debugging, config…

Set up a local development environment for the ADK Python project.

Act for an org admin — the admin API (scope directory, per-scope config & SOUL, any scope's memory, transcripts & captured prompts, files…

Automate Premiere Pro sequences and markers, exchange EDL/XML data, and prepare Media Encoder jobs with scripting workflows.

Advances a roadmap by one node: resolves the next ready session in its DAG, then extends the DAG with what the answer made sharp.

Use when a task is too large for one model pass, needs parallel research or generation across many subtasks (like researching a dozen…

macOS screen capture, window recording, GIF conversion, and agent evidence bundles from the terminal.

Upgrades, audits, and synchronizes agent configuration repositories across skills, tools, hooks, and plugins using multi-platform best…

Desktop automation through the real Rust agent-desktop CLI, published in Printing Press through a small bridge.

Artefact-driven gates from analyst and planner through bounded implementation, owner closeout, acceptance, release and the final human…

Use when creating, editing, or deploying custom agent instructions or skills shared by Codex and Claude.

Use when writing or editing instructions for agents, including AGENTS.md, CLAUDE.md, SKILL.md, project rules, or reusable agent prompts.

Use when deciding when and how to commit items to a project memory system.

A simple Polish agent memory system – identity (CLAUDE.md), on-demand map (MEMORY.md), client notes and learning loop (uwagai.md)…

Message an agent's parent, siblings, or direct children through the daemon.

The judgment layer for operating as a principal's trusted agent — how to think and behave, not which rule applies.

Coordinates multi-agent workflows across 251 specialized domain roles with centralized task dispatching and independent quality review…

Coordinate multiple coding agents safely across host issues (GitHub or GitLab), git worktrees, dependency-aware execution, rebases, CI…

Look up which agent or team owns a kind of work in this repository.

Make an AI agent run on a schedule, loop, or interval — cron, heartbeats, recurring autonomous checks.