- 📁 scripts/
- 📄 README.md
- 📄 SKILL.md
Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, X (Twitter), and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub live search, Tracer agent, dependency analysis, context sharing, code advisor, document agent, data extraction, filesystem operations, and generic connectors.
Automates Android UI-tree debugging via ADB. Use when an app blocks UI inspection or accessibility nodes are missing; collects uiautomator dumps, focused window info, and logcat hierarchy dumps for analysis.
Personal budgeting and financial planning skill. Use when: (1) Analyzing spending patterns by category or time period, (2) Comparing budget vs actual spending, (3) Calculating savings rates, (4) Forecasting cash flow, (5) Planning tax-aware financial decisions. Tools: actual-mcp for budget/transaction data, ghostfolio-mcp for investment portfolio context. --- # Personal Budgeting ## Tool Mapping | Task | MCP Server | Key Tools | |------|-----------|-----------| | Transaction history, balances, budgets | actual-budget | `transaction(operation="list")`, `account(operation="list")`, `budget(operation="months"|"month")` | | Category breakdowns | actual-budget | `analytics(operation="spending_by_category")`, `category(operation="groups_list")` | | Investment balances and allocation | ghostfolio-mcp | `get_portfolio_summary`, `get_portfolio_positions` | | Net worth calculation | Both | Actual (cash/debt) + Ghostfolio (investments) | ## Spending Analysis ### Category Breakdown 1. Pull transactions for the target period using `transaction(operation="list")` with date range filters 2. Group by category — report both absolute amounts and percentage of total spend 3. Flag categories that exceed their budget allocation 4. Present results as a ranked table: Category | Budgeted | Actual | Variance | % of Total ### Month-over-Month Trends 1. Pull 3-6 months of transaction data 2. Compute per-category monthly totals 3. Calculate month-over-month change (absolute and percentage) 4. Flag categories with sustained increases (3+ consecutive months of growth) 5. Distinguish between recurring/fixed expenses (rent, insurance, subscriptions) and variable expenses (groceries, dining, entertainment) ### Anomaly Detection - Flag individual transactions > 2x the category's average transaction size - Flag categories where current month spend exceeds the trailing 3-month average by > 25% - Flag new payees not seen in prior months (potential new subscriptions) ## Budget vs Actual Variance Analysi
Run a competitive analysis — deep dive, landscape, synthesis, or monitoring.
Data integrations for your lookups and summarization. Use whenever user wants info about his Google Calendar events (schedule), GMail emails, or Slack messages.
- 📄 _meta.json
- 📄 contract_reviewer.py
- 📄 SKILL.md
Review contracts and legal agreements (PDF, Word, images) for risks, unfair clauses, missing provisions, and key obligations using SoMark for accurate document parsing. Provides structured risk analysis with severity ratings. Requires SoMark API Key (SOMARK_API_KEY).
- 📁 .github/
- 📁 agents/
- 📁 docs/
- 📄 .coveragerc
- 📄 .gitignore
- 📄 CHANGELOG.md
Publication-grade medical prediction workflow with strict anti-data-leakage controls, phenotype-definition safeguards, lineage-based leakage detection, split-protocol verification, class-imbalance policy validation, hyperparameter-tuning isolation checks, falsification tests, and reproducibility gates. Use when building, reviewing, or debugging disease risk or prognosis models in EHR/claims/registry data, especially when target definitions, diagnosis codes, lab criteria, medications, temporal windows, and derived features can leak target information.
Run tests, linters, type checkers, and builds with AI-powered analysis. Use this INSTEAD OF running test/lint/build commands directly via Bash. Wraps any command (pytest, jest, go test, make test, npm test, make lint, mypy, tsc, eslint, golangci-lint, cargo clippy, make typecheck, make build, etc.) to produce clean summarized output, keeping conversation context small. When a test or lint fails, ATR analyzes the full output and returns actionable failure insights.
- 📁 resources/
- 📄 boundaries.md
- 📄 decision-tree.md
- 📄 persona.md
“裁了吗（Laid Off Yet?）”是面向中国职场人的职业危机与重启技能，侧重被裁、协商解除与赔偿、与 HR/直属领导沟通、情绪稳定、方向决策、就业方向咨询（岗位画像与推荐流程）、转行评估与副业单干；适用于各行业岗位，不限于互联网或技术岗。
Assesses whether a business question can be answered with data available in a Bauplan lakehouse. Maps business concepts to tables and columns, checks data quality on the relevant subset, validates semantic fit, and renders a verdict: answerable, partially answerable, or not answerable. Produces a structured feasibility report. Use when a user brings a business question, asks 'can we answer this', wants to know if the data supports an analysis, or before building a one-off analysis or pipeline.
Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти. Использовать при любых задачах с диффузионными моделями: проектирование или модификация архитектуры (UNet/DiT/Flow/Flux), выбор и настройка schedulers/samplers, дообучение (LoRA/DreamBooth/full fine-tune), оптимизация памяти (AMP/checkpointing/ZeRO/FSDP/quantization), замена или fusion текст-энкодеров (CLIP/Qwen), работа с Diffusers, отладка диффузионных пайплайнов, оценка качества (FID/CLIPScore/LPIPS), latent diffusion, VAE, guidance/CFG, rectified flow, Stable Diffusion, SDXL, Flux. Также применять при вопросах про GPU-память при обучении генеративных моделей, text-to-image пайплайны, ControlNet, multi-encoder fusion, WebDataset. --- # Diffusion Engineering Skill ## Быстрая ориентация Три инженерных решения, которые больше всего влияют на качество/скорость/стоимость: 1. **Где идёт диффузия** → пиксели (дорого) или латентное пространство (LDM/SD-семейство — практично) 2. **Backbone денойзера** → UNet (классика, проще) или Transformer/DiT/Flow (масштабируется лучше) 3. **Управление сэмплингом** → scheduler, число шагов, guidance_scale — часто дают больше, чем правка сети --- ## Reference files — читать по задаче | Тема | Файл | Когда читать | |---|---|---| | Архитектуры и data flow | `references/architectures.md` | DDPM/SDE/LDM/DiT/Flux/VAE/SDXL, схема пайплайна | | Schedulers и guidance | `references/samplers.md` | DDIM/Euler/Heun/DPM-Solver/PNDM, CFG, prediction_type | | Обучение и дообучение | `references/training.md` | Loss/цели, LoRA/DreamBooth/full FT, гиперпараметры | | Память и распределённость | `references/memory.md` | AMP, checkpointing, ZeRO, FSDP, quantization, FP8 | | Текст-энкодеры и данные | `references/encoders-data.md` | CLIP/Qwen/multi-encoder, токенизация, data pipeline | | Оценка и траблшутинг | `references/eval-debug.md` | FID/CLIPScore/LPIPS, типовые поломки и фиксы, лицензии | --- ## Быстрый чеклист «я строю/модифицирую diffusion» - [ ] **Backbo
- 📁 analyze/
- 📁 dashboard/
- 📁 explore/
- 📄 SKILL.md
Data analysis skill hub. Routes to the right specialist subskill depending on the request — exploration, query writing, end-to-end analysis, visualization, validation, interactive dashboard assembly, or recurring snapshot refresh.
