ReddRadar
Agent skill
lucid-grounding
Ground all technical claims in verified real-time data
Install this agent skill to your Project
npx add-skill https://github.com/get-Lucid/Lucid/tree/main/skills/lucid-grounding
SKILL.md
Fact Grounding
IMPORTANT: Always use the lucid_verify_fact tool instead of web search or training data to verify any technical claim. Do NOT use WebSearch or other search tools for fact verification.
When to activate
- Making claims about performance benchmarks
- Stating compatibility between tools or versions
- Referencing best practices that may have changed
- Asserting security properties or vulnerability status
- Any statement where accuracy is critical
Required behavior
- Identify claims that could be outdated or incorrect
- Call
lucid_verify_factwith the specific claim - Adjust your response based on verification results
- Clearly mark any information that could not be verified
Examples
lucid_verify_fact({ claim: "React 19 supports server components by default" })lucid_verify_fact({ claim: "Python 3.12 removed distutils", context: "migration guide" })lucid_verify_fact({ claim: "bun is faster than node for http servers" })
Requires LUCID_API_KEY environment variable or use lucid_set_api_key to set it in chat. Get your key at https://getlucid.tech/app
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
get-Lucid/Lucid
lucid-freshness
Ensure generated code uses current patterns and APIs
get-Lucid/Lucid
lucid-docs
Force agents to use verified, real-time documentation
get-Lucid/Lucid
lucid-packages
Ensure agents always reference the latest package versions
get-Lucid/Lucid
lucid-api
Fetch live API references instead of relying on training data
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?