
from prompts12
Detects which execution environment an agent is running in (Claude Code, Vercel Sandbox, or local dev) and exposes available tools and capabilities for safe, en
Runtime Context detects the agent's execution environment and reports which tools and capabilities are available (e.g., Skill()/Agent() in Claude Code, bash/readFile/writeFile in Vercel Sandboxes, or limited text-only local dev). It provides a detection script and guidance for system/SOUL authors so agents can adapt behavior or fail clearly when required tools are missing.
Use this skill at the start of tasks where an agent must decide whether it can run scripts, read/write files, spawn subagents, or call other skills. Typical scenarios: deploying multi-host agents, writing cross-runtime SOUL.md prompts, or building skills that should run both in hosted sandboxes and in developer environments.
Designed for orchestration environments that expose Skill()/Agent() tools (Claude Code) and sandboxed environments with bash/file tools (Vercel Sandbox). Works conceptually with Claude-based agents, sandboxed CLI agents, and local dev runs where file access is available.
This skill has not been reviewed by our automated audit pipeline yet.
Hunter–Skeptic–Referee Code Review
Orchestrates a three-phase adversarial code review (Hunter, Skeptic, Referee) to find, challenge, and verify bugs with high precision and reduced bias.
Remind — Conversation Recall
Search and recall past Claude Code/agent conversation sessions to find decisions, code snippets, and context for continuation or reference.
Humanize
Revision and editing rules to remove AI-like patterns from prose so output reads more natural and human — applied automatically to any human-facing text before