Loading...
Loading...
Found 1,864 Skills
Calculate agreement between human ground truth and machine labels for a text LLM judge metric, then analyze transcripts and reviewer notes to propose an improved metric prompt. One metric at a time.
Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference and the root cause is unknown.
Quickly screen inbound deal flow — CIMs, teasers, and broker materials — against the fund's investment criteria. Extracts key deal metrics, runs a pass/fail framework, and outputs a one-page screening memo. Use when reviewing new deal flow, triaging inbound materials, or deciding whether to take a first call. Triggers on "screen this deal", "review this CIM", "should we look at this", "triage this teaser", or "deal screening".
Iterate on RAG systems with structured evals instead of eyeballing. This skill should be used when the user is tuning a RAG pipeline — changing retrieval prompts, swapping models, adjusting chunking, or debugging poor answers — and wants a cheap, ranked set of experiments with cost tracking and structured feedback on the stack. Also use when the user asks "how do I know if my RAG is working?", "this RAG eval is burning money", or "what should I try next on retrieval?".
Use when the user asks "what can Cekura do", "what commands are available", "help me with Cekura", "what skills do I have", "show me Cekura features", "what's available", "how do I use Cekura", or needs guidance on which Cekura skill to use for their task. Also relevant as the entry point when a user has just installed cekura-skills for the first time.
Process external code review feedback with technical rigor. Use when receiving feedback from another LLM, human reviewer, or CI tool. Verifies claims before implementing, tracks disposition.
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
Identify stocks where market sentiment is significantly more negative than fundamentals warrant — the gap between narrative and reality. Use when the user asks to find contrarian opportunities, stocks with sentiment-fundamental misalignment, oversold but fundamentally strong companies, stocks punished by negative narratives, or wants to analyze whether market fear is justified for specific stocks or sectors.
Expert-level real estate systems, property management, MLS integration, CRM, virtual tours, and market analysis
Эксперт по interview scorecards. Используй для структурированных интервью и оценки кандидатов.
Generate and explore ideas effectively. Use when starting new projects, solving problems, or exploring solutions. Covers ideation techniques and divergent thinking.
Principal AI Architect and Machine Learning Engineer.