Validate and audit agent conversations against explicit compliance criteria — framework compliance, ground-check coverage, hallucination detection, tool-call transparency, and decision documentation. Use only when the user explicitly asks to test, audit, or validate agent interaction behavior. Off by default; invoke deliberately.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-rules:agent-interaction-unit-testThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill activates the framework's canonical **Agent Interaction Unit Test** rules — an
This skill activates the framework's canonical Agent Interaction Unit Test rules — an
explicit, opt-in audit mode. Do not work from this stub — load the source of truth (the
framework keeps all rule text in modules/):
${CLAUDE_PLUGIN_ROOT}/modules/agent-interaction-unit-test/RULES.md.<lang>, where
<lang> is the user's configured language (${user_config.language}, default en). Fall
back to RULES.md.en if that language file is absent.SAFETY_PRECAUTION and First-Run Procedure headers in that file are activation
guards for other platforms — under Claude Code, enabling this plugin is the
activation, so disregard them.${CLAUDE_PLUGIN_ROOT}/modules/agent-interaction-unit-test/CORE-RULES.md.Never enable testing mode automatically — it runs only on explicit request. Honor the
enable_agent_unit_test option. Related: [[memory-rules]], [[critical-thinking-rules]].
npx claudepluginhub paupawsan/agentic-rules --plugin agentic-rulesProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.