Search
AI & LLM Engineering · By softspark
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Creates new specialized agents with frontmatter, tools, delegation. | softspark/ | 179 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | 3 days ago |
| 2 | Content moderation with Claude: pre-filter vs LLM-classify, categories, thresholds, HITL. | softspark/ | 179 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 3 | 3.Evaluate Evaluates RAG retrieval and LLM-as-judge metrics (faithfulness, relevancy, context precision). | softspark/ | 179 | — | ~1.1k | Automated safety check: Notes | Apache-2.0 | 3 days ago |
| 4 | 4.Evolve Analyzes agent/skill failures, drafts prompt/permission fixes. | softspark/ | 179 | — | ~1k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 5 | 5.Index Reindexes KB for semantic search via vector store (Qdrant). An agent skill from softspark/ai-toolkit. | softspark/ | 179 | — | ~840 | Automated safety check: Notes | Apache-2.0 | 3 days ago |
| 6 | Structured JSON output from Claude: native JSON schemas, strict tools, local validation, refusal and truncation handling. | softspark/ | 179 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 7 | Capability-aware model routing for Codex, Copilot, Claude and provider APIs. | softspark/ | 179 | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 8 | Anthropic API prompt caching: TTL, breakpoints, stacking, invalidation, hit rate. | softspark/ | 179 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 9 | RAG: embeddings, chunking, hybrid search (BM25+vector), reranking, CRAG, multi-hop. | softspark/ | 179 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
