AGENT SKILLS · MISSION KIT / codealive-ai

codealive-ai · Agent Skills

3 Skills with substantive, source-verified documentation. Open a card to read the original instructions and review package and installation details.

codealive-ai
Community

prompt-engineering

Universal prompt engineering techniques for any LLM. Use when crafting, optimizing, or reviewing prompts for AI models. Triggers on requests like "improve this prompt", "write a system prompt", "optimize my instructions", "help me prompt engineer", "audit this prompt", "review my prompt", or when building agentic systems that need structured prompts.

1h installs
1
GitHub stars
133
Updated
Sep 7
codealive-ai
Community

coordinator-mode

Switch this session into Coordinator Mode: a long-lived role that plans, designs verification, delegates implementation to cheaper executors, accepts results on evidence, and keeps a journal that survives context compaction. Use only when the user explicitly turns Coordinator Mode on or asks to resume it (\"coordinator mode\", \"orchestrator mode\", \"режим координации\"). Not for one-off delegation or reviews (use pragmatic-orchestration), and never for a delegated worker.

1h installs
1
GitHub stars
73
Updated
Nov 19
codealive-ai
Community

pragmatic-orchestration

Orchestrate coding agents economically: reach an accepted result cheaper and faster by delegating implementation, research, review and media work to the cheapest capable model, in parallel where possible, while the orchestrator keeps design and acceptance. Runs external coding agents (Codex, Claude Code, OpenCode, native Grok Build, Gemini, Devin CLI, Antigravity CLI, Cursor CLI) through the porch CLI; the same briefing and acceptance rules apply to built-in subagents. Use for delegating or para

1h installs
1
GitHub stars
73
Updated
Nov 19