发现 Skills

Configure Mistral AI local development with hot reload, testing, and mocking. Use when setting up a development environment, configuring test workflows, or establishing a fast iteration cycle with Mistral AI. Trigger with phrases like "mistral dev setup", "mistral local development", "mistral dev environment", "develop with mistral".

Npm Scripts Optimizer - Auto-activating skill for DevOps Basics. Triggers on: npm scripts optimizer, npm scripts optimizer Part of the DevOps Basics skill category.

Implement Perplexity query sanitization, citation validation, result caching, and conversation context management for search workflows. Trigger with phrases like "perplexity data", "perplexity PII", "perplexity citations", "perplexity cache", "perplexity context".

Configure enterprise SSO integration for Windsurf. Activate when users mention "sso configuration", "single sign-on", "enterprise authentication", "saml setup", or "identity provider". Handles enterprise identity integration. Use when working with windsurf enterprise sso functionality. Trigger with phrases like "windsurf enterprise sso", "windsurf sso", "windsurf".

Use when a character feels flat, too competent, or unrelatable—identifies the Sacred Flaw (Storr's Theory of Control) and dials the Three Sliders (Sanderson) to create earned vulnerability.

帮助用户撰写符合规范的思想汇报文档。当用户需要写思想汇报、入党思想汇报、季度思想汇报、思想总结等时触发此skill。 本skill会引导用户完成从初稿生成到个性化优化的完整流程，确保输出严格符合党组织要求的格式和内容规范。 适用于大学生、入党积极分子等需要定期提交思想汇报的场景。

Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for programmatic ELN workflows.

Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.

Statistical visualization with pandas integration. Use for quick exploration of distributions, relationships, and categorical comparisons with attractive defaults. Best for box plots, violin plots, pair plots, heatmaps. Built on matplotlib. For interactive plots use plotly; for publication styling use scientific-visualization.

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/laboratory), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.

Proactively search for security threats, vulnerabilities, and suspicious patterns in applications and infrastructure before they cause damage. Use when conducting security audits, identifying vulnerabilities, analyzing security logs, detecting suspicious patterns, investigating potential breaches, performing penetration testing, or implementing security monitoring.

Meeting minutes consolidation workflow: aggregates meeting minutes within a specified time range and generates a structured report. Use this when you need to organize meeting notes, produce a weekly meeting summary, or review meeting content over a period of time.

Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.

Create algorithmic art using p5.js with seeded randomness, flow fields, and particle systems. Use when you need to generate generative art, create computational aesthetics, or build interactive artistic visualizations. Automatically activates when discussing: "generative art", "algorithmic art", "p5.js visualization", "computational aesthetics".

Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search

Unified content extraction and action planning. Use when user says "tapestry <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.

RAG-specific best practices for LlamaIndex, ChromaDB, and Celery workers. Covers ingestion, retrieval, embeddings, and performance.

Conventional commits with secret scanning, PR description writing, changelog generation, and branch strategy

Translates beliefs (probabilities) into optimal actions (bet/pass/hedge) using quantitative frameworks including edge calculation, Kelly Criterion bet sizing, forecast extremizing, and Brier score optimization. Use when converting probabilities into decisions, calculating edge against market odds, sizing bets optimally, extremizing aggregated forecasts, improving Brier scores, or when user mentions betting strategy, Kelly Criterion, edge calculation, Brier score, extremizing, or translating belief into action.

Reviews scientific documents for logical clarity, argument soundness, and rigor by auditing hypothesis-data alignment, claim-evidence chains, quantitative precision, hedging calibration, and terminology consistency across any document type. Use when reviewing scientific argumentation, checking claims vs evidence, auditing terminology, or when user mentions check clarity, review logic, scientific soundness, hypothesis-data alignment, or claims vs evidence.

Run SEO and GEO audits on URLs covering technical SEO, content quality, E-E-A-T signals, and AI citation readiness. Use when evaluating search performance or diagnosing ranking issues.

Deploy and evaluate FastWAM (Fast World Action Model) on the LIBERO and LIBERO-Plus benchmarks. Covers environment setup, checkpoint download, Wan2.2 model preparation, single-GPU and multi-GPU evaluation, per-task and per-category result aggregation. Use this skill whenever someone needs to install FastWAM, run inference on LIBERO tasks, debug model loading issues (CUDA version mismatch, HF repo redirects, ActionDiT preprocessing), parallelize evaluation across GPUs, or compare FastWAM results against other VLA models like LingBot-VA.

Use when implementing chaos engineering, designing fault injection experiments, or building resilience testing practices. Covers chaos principles and experiment design.