Results for “plisio”

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1, extract events as NumPy arrays, read metadata and channels, and convert to CSV or DataFrame for flow cytometry data preprocessing.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.

Solves single- and multi-objective optimization problems with NSGA-II/III, MOEA/D, and other evolutionary algorithms, including constraint handling, Pareto front analysis, and benchmark problems.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1, extracting events as NumPy arrays, metadata, and channel information, with support for creating and modifying FCS files.

PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Register and use GSAP plugins including ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG plugins, and custom easing plugins.

Diagnose failed or unhealthy Dynamo deployments by collecting a read-only debug bundle, classifying failures, and providing step-by-step remediation guidance.

Validate pci dss validator operations. Auto-activating skill for Security Advanced. Triggers on: pci dss validator, pci dss validator Part of the Security Advanced skill category. Use when working with pci dss validator functionality. Trigger with phrases like "pci dss validator", "pci validator", "pci".

Parse FCS (Flow Cytometry Standard) files v2.0-3.1. Extract events as NumPy arrays, read metadata/channels, convert to CSV/DataFrame, for flow cytometry data preprocessing.

Start voice calls via the Clawdbot voice-call plugin.

Use to find upgrade, seat-growth and new-use-case signals that customers give support and nobody routes anywhere. Trigger for "find upsell opportunities in support", "customers hitting plan limits", "which accounts are asking about enterprise features", expansion signals from tickets, or support-sourced pipeline.

PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.

Integrates with the protocols.io API v3 to search, create, update, and publish scientific protocols, manage steps and materials, handle discussions, organize workspaces, and upload files.

Performs deterministic image operations with Python Pillow: resizing, cropping, compositing, format conversion, watermarks, brightness/contrast adjustments, and web optimization.

Solve single and multi-objective optimization problems using NSGA-II/III, MOEA/D, and other evolutionary algorithms with customizable operators, constraint handling, and benchmark problems.

Build forensic super timelines from disk images using Plaso (log2timeline) and triage them in Timesketch.

Polish English academic papers for SSCI journal submission. This skill checks grammar, improves readability, and enhances academic tone. Use when the user asks to polish, proofread, edit, or improve their English academic paper, manuscript, or article — especially when targeting SSCI, SCI, or other international journals. Also use when the user asks to "润色", "修改语法", "提升学术性", "polish my paper", or mentions their paper needs language improvement for journal submission. Always trigger on any request involving academic English polishing, even if the user doesn't explicitly say "SSCI."

通过 AIsa API 查询跨平台预测市场数据。支持 Polymarket 和 Kalshi 的市场行情、价格、订单簿、K线、持仓和交易记录。适用场景：查询预测市场赔率、选举博彩、事件概率、市场情绪、Polymarket 价格、Kalshi 价格、体育博彩赔率、钱包盈亏、跨平台市场对比。 Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

Consume and produce STIX/TAXII 2.1 cyber threat intelligence feeds using Python, including server discovery, collection polling, object parsing, and SIEM/TIP integration.

Expert en Obsidian avancé (vaults, plugins, dataview, templates, graph view, PKM workflows, sync, publish)

High-fidelity ASCII/Braille rendering via the Risomorphism-1911 pipeline — edge-aware downsampling, presets, quality gates, and eikon mirror workflows

Prediction markets data - Polymarket, Kalshi markets, prices, positions, and trades. Use when: the user needs market data, stock analysis, watchlists, or portfolio workflows.

Extract employee, employer, allowances, deductions, taxes, and net pay from Japanese payslips.

Helixa — Onchain identity, reputation, and Cred Scores for AI agents on Base. Use when an agent wants to mint an identity NFT, check its Cred Score, verify social accounts, update traits/narrative, query agent reputation data, check staking info, or search the agent directory. Supports SIWA (Sign-In With Agent) auth and x402 micropayments. Also use when asked about Helixa, AgentDNA, ERC-8004, Cred Scores, $CRED token, or agent identity.

GPU-accelerated data curation for LLM training, supporting text, image, video, and audio with fuzzy deduplication, quality filtering, semantic deduplication, PII redaction, and NSFW detection.

Polishes existing motion against the transitions.dev motion-token scale by auditing duration, distance, scale, blur, and easing values and suggesting token-based corrections.

Multi-objective optimization framework. NSGA-II, NSGA-III, MOEA/D, Pareto fronts, constraint handling, benchmarks (ZDT, DTLZ), for engineering design and optimization problems.