Search
AI & LLM Engineering · By glebis
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Writes fictional but realistic coaching or therapy session transcripts for evals, demos and few-shot examples, in several modalities and export formats. | glebis/ | 391 | — | ~2.9k | Automated safety check: Pass | MIT | 3 days ago |
| 2 | Search and download images via Google Custom Search API with LLM-powered selection. | glebis/ | 391 | — | ~1.4k | Automated safety check: Notes | MIT | 3 days ago |
| 3 | Run quick, offline, private LLM tasks on local models via llama.cpp, reusing models already downloaded by Ollama. | glebis/ | 391 | — | ~1.4k | Automated safety check: Pass | MIT | 3 days ago |
| 4 | 4.RAG Eval Iterate on RAG systems with structured evals instead of eyeballing. | glebis/ | 391 | — | ~1.5k | Automated safety check: Pass | MIT | 3 days ago |
| 5 | Three-layer PII anonymization for session transcripts (therapy, coaching, consulting, mentoring). | glebis/ | 391 | — | ~841 | Automated safety check: Pass | MIT | 3 days ago |
| 6 | 6.Setup Set up, install, and configure CONFIDE local de-identification — installs Python deps (natasha, scrubadub, phonenumbers, pymorphy2), ensures Ollama + pulls the default qwen2.5:3b model, detects… | glebis/ | 391 | — | ~1.1k | Automated safety check: Pass | MIT | 3 days ago |
| 7 | Index and search Claude Code sessions using semantic embeddings (Gemini). | glebis/ | 391 | — | ~402 | Automated safety check: Pass | MIT | 3 days ago |
| 8 | 8.Cull This skill should be used when the user wants to view, review, rate, organize, search, or export images / AI-art generations with the Cull app. | glebis/ | 391 | — | ~1.9k | Automated safety check: Pass | MIT | 3 days ago |
