Publisher · agent skills · page 2
Agent skills by internlm
internlm publishes 28 audited skills on 1 repository: 23 SAFE, 2 CAUTION, 3 BLOCK.
Cite
Cite this page
ModelsAtlas. “Agent skills by internlm”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/internlm/page/2
InternLM/WildClawBench
Extract frames or short clips from videos using ffmpeg.
InternLM/WildClawBench
Prompt-injection and data-exfiltration screening for untrusted text. Use before summarizing web/email/social content, before replying, and especially before writing anything to memory. Provides a safe memory append…
InternLM/WildClawBench
Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest. Use when the user wants a paper digest, a JSON feed of recent papers, or to run the arXiv/HF pipeline.
InternLM/WildClawBench
Scans your OpenClaw environment for leaked secrets — API keys, tokens, credentials in .env files, installed skills, and shell history. Runs silently on startup, deep scans on demand. Fixes issues with your permission.