ReddRadar
Agent skill
response-state-visualizer
Stream safe, staged previews of answers in CLI output. Use when you need to show how a response forms or changes state without exposing chain-of-thought.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/response-state-visualizer
SKILL.md
Response State Visualizer
Use this skill to show intent, plan signals, and draft previews while the answer is forming.
Workflow
- Enable the preview stream with
GPIA_RESPONSE_PREVIEW=1. - Emit stages like Intent, Keywords, Skills, Draft, Final.
- Keep previews short and safe (no hidden reasoning traces).
Script
- Run: python skills/dialogue/response-state-visualizer/scripts/demo_preview.py
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?