feat(agents): добавлены skills для PDF, docs, slides, jupyter и spreadsheet

- Зачем:
  - расширены возможности AI-ассистентов для работы с документами и презентациями
- Что:
  - добавлен skill pdf для работы с PDF файлами
  - добавлен skill doc для работы с Word документами
  - добавлен skill slides для создания презентаций PowerPoint
  - добавлен skill jupyter-notebook для работы с Jupyter ноутбуками
  - добавлен skill spreadsheet для работы с таблицами (Excel/CSV)
  - изменена модель Claude с sonnet на opus
- Проверка:
  - проверка доступности skills в AI-ассистентах

agents/.agents/skills/jupyter-notebook/references/experiment-patterns.md

@@ -0,0 +1,10 @@
+# Experiment Patterns
+
+Use this structure for exploratory and experimental work:
+
+- Title and objective: state the question and the success criteria.
+- Setup and reproducibility: import only what you need, set a seed early, and keep configuration in one short cell.
+- Plan: list hypotheses, sweeps, and metrics before running code.
+- Minimal baseline: start with the smallest runnable example and confirm it runs end-to-end before adding complexity.
+- Results and notes: summarize findings in markdown near the relevant code and record key metrics in a small dictionary or table-like structure.
+- Next steps: decide whether to continue, pivot, or stop, and capture follow-up ideas as short bullets.

agents/.agents/skills/jupyter-notebook/references/notebook-structure.md

@@ -0,0 +1,17 @@
+# Notebook Structure
+
+Jupyter notebooks are JSON documents with this high-level shape:
+
+- `nbformat` and `nbformat_minor`
+- `metadata`
+- `cells` (a list of markdown and code cells)
+
+When editing `.ipynb` files programmatically:
+
+- Preserve `nbformat` and `nbformat_minor` from the template.
+- Keep `cells` as an ordered list; do not reorder unless intentional.
+- For code cells, set `execution_count` to `null` when unknown.
+- For code cells, set `outputs` to an empty list when scaffolding.
+- For markdown cells, keep `cell_type="markdown"` and `metadata={}`.
+
+Prefer scaffolding from the bundled templates or `new_notebook.py` (for example, `$CODEX_HOME/skills/jupyter-notebook/scripts/new_notebook.py`) instead of hand-authoring raw notebook JSON.

agents/.agents/skills/jupyter-notebook/references/quality-checklist.md

@@ -0,0 +1,11 @@
+# Quality Checklist
+
+Before delivering a notebook:
+
+- Run it top-to-bottom at least once (or as much as the environment allows).
+- Ensure early cells set all required state; avoid hidden state from prior runs.
+- Keep outputs tidy. Avoid giant outputs when a short summary works.
+- Prefer small tables, key metrics, or short printouts.
+- Keep the narrative skimmable. Use headings and short bullets, and avoid long paragraphs.
+- Leave helpful TODOs only when necessary, and label them clearly.
+- If execution is not possible, call out the risk and how to validate locally.

agents/.agents/skills/jupyter-notebook/references/tutorial-patterns.md

@@ -0,0 +1,9 @@
+# Tutorial Patterns
+
+Use this structure for teaching and walkthroughs:
+
+- Audience, prerequisites, and learning goals: say who it is for, list what they should already know, and state what they will be able to do by the end.
+- Outline: provide a short numbered outline so readers can skim.
+- Step-by-step flow: pair a short markdown explanation with a small code cell that runs on its own and a brief interpretation of the result.
+- Exercises: include at least one exercise that reinforces the key concept and provide an answer scaffold in the next cell.
+- Pitfalls and extensions: call out one common mistake and how to fix it, and suggest one optional extension for curious readers.