Loading...
Loading...
Found 1,304 Skills
Causal digital twin for marketing simulation — predict campaign ROI, run counterfactual KOL swaps, and audit causal graphs before spending a dollar.
GANG validator skill. You are a validator, performing rule-based verification to check if the worker's handoff meets the val standards and issuing a verdict.
Generate and curate evaluation datasets — structured generation via dimensions-tuples-NL, quick from description, expansion from existing data, plus dataset maintenance through deduplication, rebalancing, and gap-filling. Use when creating eval data, expanding test coverage, or cleaning datasets. Do NOT use when sufficient real production data exists (use analyze-trace-failures instead). Do NOT use for evaluator creation (use build-evaluator).
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill safety, or run a security audit.
AI Agent long-term memory system with cross-session, cross-project persistence. Triggers: - /remember - Store memories - /recall - Search memories - /forget - Delete/archive memories - /memory-status - Check status - When needing to persist important conversation insights - When sharing user preferences across projects
Query decomposition for multi-concept retrieval. Use when handling complex queries spanning multiple topics, implementing multi-hop retrieval, or improving coverage for compound questions.
Audit and refactor existing SKILLs. Use when improving drafts, fixing quality, or aligning to spec. For creating new skills from scratch use skill-creator (anthropics/skills).
Parameter-efficient fine-tuning with Low-Rank Adaptation (LoRA). Use when fine-tuning large language models with limited GPU memory, creating task-specific adapters, or when you need to train multiple specialized models from a single base.